podium

open-swe

37 of 51 criteria have a sourced finding; 33 were also cross-checked by a second agent. Every comparison that includes open-swe links here for scope, limitations, atomic answers and sources.

Humans approve the rubric, templates and prototype; they do not review every finding. An agent source cross-check is not a hands-on product test. A missing sourced finding is not evidence that a capability is absent.

Rubric
0.3 · 51 criteria
Source checks
2026-11-08 to 2026-11-13
Agent cross-checked
33 criteria
Comparisons
1

Access and agent choice

ACC-01

Client access

Sourced partial

Experimental desktop installation supports Apple Silicon macOS Ventura or later. The web dashboard is the recommended Robin client. Installing the desktop app links robin and oswe CLI commands. The dashboard starts and continues threads; local desktop Changes, Terminal and file browser use the selected checkout. The browser layout explicitly adapts its sidebar for phone-width screens.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI, Public source-built Robin iOS development client · Version: ae120fc74d21a7b3aaaaa34a1774718408fad021; macOS desktop/nightly and source-built iOS development client have separate requirements. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
Not separately cross-checked
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
9 atomic answers
  • Desktop os [supported] Experimental desktop installation supports Apple Silicon macOS Ventura or later. Sources: open-swe:desktop.
  • Mobile apps [partial] An iOS client exists as source that you build with Xcode as a development build; it is not in any release or app store. The README says only iOS is supported, so there is no Android app. Sources: open-swe:src2-oswe-mobile, open-swe:src2-oswe-release.
  • Browser [supported] The web dashboard is the recommended Robin client. Sources: open-swe:desktop.
  • Mobile browser [supported] The browser client implements a full-screen mobile sidebar overlay below 767px so the chat stays visible. Sources: open-swe:gap39-browser-mobile.
  • Cli [supported] Installing the desktop app links robin and oswe CLI commands. Sources: open-swe:desktop.
  • Editor extensions [unknown] Client access, editor_extensions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Task actions [supported] The dashboard starts and continues threads; local desktop Changes, Terminal and file browser use the selected checkout. Sources: open-swe:desktop.
  • Notifications [unknown] Client access, notifications: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Cross device continuity [partial] Cloud threads can be started and continued from the dashboard, GitHub, Slack or Linear. Threads bridged to a Mac show up on other devices, but only the owning Mac can continue them. Sources: open-swe:src2-oswe-readme-flow, open-swe:src2-oswe-desktop-bridge.

Sources: open-swe:desktop, open-swe:src2-oswe-mobile, open-swe:src2-oswe-release, open-swe:src2-oswe-readme-flow, open-swe:src2-oswe-desktop-bridge, open-swe:gap39-browser-mobile

Sourced partial

Robin runs its own Deep Agents loop on Managed Deep Agents; the Claude Code connection is a read-only mirror. Anthropic, OpenAI and Google model examples are documented separately from the agent loop. Forking agent_catalog configures tools, models, subagents and loop rules. The scoped model/runtime catalog does not integrate the other compared coding-CLI sessions.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
Not separately cross-checked
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
5 atomic answers
  • Harnesses [supported] Robin runs its own Deep Agents loop on Managed Deep Agents; the Claude Code connection is a read-only mirror. Sources: open-swe:readme, open-swe:mirror.
  • Model providers [supported] Anthropic, OpenAI and Google model examples are documented separately from the agent loop. Sources: open-swe:custom.
  • Custom adapters [supported] Forking agent_catalog configures tools, models, subagents and loop rules. Sources: open-swe:custom.
  • Session integration [partial] Robin owns the Deep Agents model/tool loop. Claude Code sync is read-only; it cannot prompt, steer or stop that Claude Code session. No native external coding-CLI session adapters were found in the scoped runtime/model catalog. Sources: open-swe:src2-oswe-claudesync, open-swe:gap39-agent-models.
  • Mixed harness operation [unknown] Agent and model choice, mixed_harness_operation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:readme, open-swe:mirror, open-swe:custom, open-swe:src2-oswe-claudesync, open-swe:gap39-agent-models

Sourced partial

Deployments use model-provider API keys or LangSmith Gateway credentials. Managed Deep Agents is required by the shipped backend; deploying without it requires adapting the code. The native model runtime uses API/Gateway credentials rather than coding-agent subscription login reuse.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
Not separately cross-checked
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
7 atomic answers
  • Agent subscriptions [unsupported] The shipped own-agent loop uses model API/Gateway credentials; the read-only Claude Code mirror is not agent execution under a reused subscription. Sources: open-swe:gap39-agent-models, open-swe:mirror.
  • Api accounts [supported] Deployments use model-provider API keys or LangSmith Gateway credentials. Sources: open-swe:install, open-swe:custom.
  • Vendor credits [unknown] Subscriptions, API keys and vendor credits, vendor_credits: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Local models [unknown] Subscriptions, API keys and vendor credits, local_models: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Account switching [unknown] Subscriptions, API keys and vendor credits, account_switching: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Vendor account requirement [supported] Managed Deep Agents is required by the shipped backend; deploying without it requires adapting the code. Sources: open-swe:readme.
  • Provider restrictions [unknown] Subscriptions, API keys and vendor credits, provider_restrictions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:install, open-swe:custom, open-swe:readme, open-swe:gap39-agent-models, open-swe:mirror

Agent cross-checked partial

Setup documents backend deployment, GitHub App, Slack App, allowlists and model credentials. Desktop Work mode creates a task folder without requiring a repository. Desktop local project mode supports current checkouts and new Git worktrees. Remote-free behavior was not tested. LangGraph Platform deployment and LangSmith sandbox prerequisites are documented. Standalone Docker deployment needs PostgreSQL, Redis, credentials and the Managed Deep Agents service.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
7 atomic answers
  • First task setup [supported] Setup documents backend deployment, GitHub App, Slack App, allowlists and model credentials. Sources: open-swe:install.
  • No git [supported] Desktop Work mode creates a task folder without requiring a repository. Sources: open-swe:desktop.
  • Local git without remote [partial] Desktop local project mode supports current checkouts and new Git worktrees. Remote-free behavior was not tested. Sources: open-swe:desktop.
  • Hosted git [unknown] Onboarding and project prerequisites, hosted_git: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Prerequisite guidance [unknown] Onboarding and project prerequisites, prerequisite_guidance: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Managed cloud setup [supported] LangGraph Platform deployment and LangSmith sandbox prerequisites are documented. Sources: open-swe:install.
  • Byo vps onboarding [supported] Standalone Docker deployment needs PostgreSQL, Redis, credentials and the Managed Deep Agents service. Sources: open-swe:install.

Sources: open-swe:install, open-swe:desktop

Agent cross-checked partial

robin/oswe are product CLI entry points. FastAPI dashboard APIs share the deployment origin with the web dashboard. The Robin MCP endpoint exposes thread lookup and human-review request/dismiss operations to local sessions. Signed GitHub and Slack webhook routes start and continue agent work. Machine callers can start system-owned threads through scoped credentials; dashboard callers use authenticated sessions.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
8 atomic answers
  • Cli [supported] robin/oswe are product CLI entry points. Sources: open-swe:desktop.
  • Api [supported] FastAPI dashboard APIs share the deployment origin with the web dashboard. Sources: open-swe:install.
  • Sdk [unknown] Programmable access, sdk: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Mcp server [supported] The Robin MCP endpoint exposes thread lookup and human-review request/dismiss operations to local sessions. Sources: open-swe:mirror, open-swe:human-review.
  • Webhooks [supported] Signed GitHub and Slack webhook routes start and continue agent work. Sources: open-swe:install.
  • Operations [unknown] Programmable access, operations: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Authentication [supported] Machine callers can start system-owned threads through scoped credentials; dashboard callers use authenticated sessions. Sources: open-swe:install.
  • Stability [unknown] Programmable access, stability: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:desktop, open-swe:install, open-swe:mirror, open-swe:human-review

Agent cross-checked partial

Product-managed instance, workspace and personal MCP connections support headers or OAuth; collaborative threads exclude personal credentials. Custom Python tools and middleware are documented configuration points. Repository AGENTS.md and prompt/skill configuration are documented.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
7 atomic answers
  • Mcp client [supported] Product-managed instance, workspace and personal MCP connections support headers or OAuth; collaborative threads exclude personal credentials. Sources: open-swe:custom.
  • Plugins [unknown] External tools and extensions, plugins: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Custom tools [supported] Custom Python tools and middleware are documented configuration points. Sources: open-swe:custom.
  • Instructions import [supported] Repository AGENTS.md and prompt/skill configuration are documented. Sources: open-swe:custom.
  • Authentication [unknown] External tools and extensions, authentication: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Permission scope [unknown] External tools and extensions, permission_scope: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Integration owner [unknown] External tools and extensions, integration_owner: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:custom

Agent cross-checked partial

Robin Desktop uses Electron and downloads a backend-selected UI archive.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
4 atomic answers
  • Desktop implementation [supported] Robin Desktop uses Electron and downloads a backend-selected UI archive. Sources: open-swe:desktop.
  • Mobile implementation [unknown] Client implementation, mobile_implementation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Hybrids [unknown] Client implementation, hybrids: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Implementation evidence [unknown] Client implementation, implementation_evidence: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:desktop

Planning and context

Agent cross-checked partial

Work starts in the dashboard, GitHub conversations, Slack or optional Linear delegation. Linear mentions or delegation open an agent session; follow-up continues in Linear. GitHub and Slack integrations route repository work to persistent threads.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
9 atomic answers
  • Local creation [unknown] Intake and external tracker relationship, local_creation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Prompt intake [supported] Work starts in the dashboard, GitHub conversations, Slack or optional Linear delegation. Sources: open-swe:readme.
  • External import [supported] Linear mentions or delegation open an agent session; follow-up continues in Linear. Sources: open-swe:install.
  • Chat git triggers [supported] GitHub and Slack integrations route repository work to persistent threads. Sources: open-swe:install.
  • Authoritative tracker [unknown] Intake and external tracker relationship, authoritative_tracker: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Stable ids [unknown] Intake and external tracker relationship, stable_ids: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Sync [unknown] Intake and external tracker relationship, sync: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Supported edits [unknown] Intake and external tracker relationship, supported_edits: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • External roundtrips [unknown] Intake and external tracker relationship, external_roundtrips: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:readme, open-swe:install

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Agent cross-checked partial

Shared repository instructions, organization skills and private user instructions have documented scopes. Workspace threads load organization skills; private owner threads can load personal skills.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
10 atomic answers
  • Instructions [supported] Shared repository instructions, organization skills and private user instructions have documented scopes. Sources: open-swe:custom, open-swe:install.
  • Skills [supported] Workspace threads load organization skills; private owner threads can load personal skills. Sources: open-swe:install.
  • Project docs [unknown] Shared context and memory, project_docs: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Memory [unknown] Shared context and memory, memory: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Scope [unknown] Shared context and memory, scope: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Provenance [unknown] Shared context and memory, provenance: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Correction [unknown] Shared context and memory, correction: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Deletion [unknown] Shared context and memory, deletion: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Freshness [unknown] Shared context and memory, freshness: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Takeover continuity [unknown] Shared context and memory, takeover_continuity: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:custom, open-swe:install

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Agent cross-checked partial

Robin has durable native future-work suggestions with summary/details, repository/workspace and context links, independent of the originating thread. Their schema has no work-state field; Task records group coordinator/worker sessions rather than provide a general issue/backlog workflow.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-13 (9 days old)
Agent cross-check
2026-11-17
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
17 atomic answers
  • Create [supported] The product-owned suggest_task tool persists summary/details and context links without starting work. Sources: open-swe:gap39-future-work.
  • Edit [unknown] Native issue management and idea backlog, edit: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Discuss [unknown] Native issue management and idea backlog, discuss: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Prioritize [unknown] Native issue management and idea backlog, prioritize: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Label [unknown] Native issue management and idea backlog, label: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Assign [unknown] Native issue management and idea backlog, assign: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Filter [unknown] Native issue management and idea backlog, filter: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Archive [unknown] Native issue management and idea backlog, archive: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Reopen [unknown] Native issue management and idea backlog, reopen: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Project epic views [unknown] Native issue management and idea backlog, project_epic_views: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Idea parking [supported] Future work is recorded without launching it. Sources: open-swe:gap39-future-work.
  • Explicit dispatch [unknown] Native issue management and idea backlog, explicit_dispatch: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Task session separation [supported] SuggestedTask has its own durable UUID and can outlive its originating thread. Sources: open-swe:gap39-future-work.
  • Metadata [unknown] Native issue management and idea backlog, metadata: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Durable states [unsupported] SuggestedTask has no state field and Task records only group coordinator and worker threads with a delegated flag, so no product-owned task carries open, in-progress or done state. Sources: open-swe:d80-suggest, open-swe:d80-task, open-swe:d80-taskmig.
  • External tracker requirement [unknown] Native issue management and idea backlog, external_tracker_requirement: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:gap39-future-work, open-swe:d80-suggest, open-swe:d80-task, open-swe:d80-taskmig

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Coordination and automation

COORD-01

Parallel work

Agent cross-checked partial

Independent cloud threads and separate local worktrees can run in parallel.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-10
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
5 atomic answers
  • Concurrent sessions [supported] Independent cloud threads and separate local worktrees can run in parallel. Sources: open-swe:readme, open-swe:desktop.
  • Concurrent tasks [supported] Within a run, the agent can send research and independent work to subagents or task workers. Sources: open-swe:src2-oswe-readme-flow.
  • Quotas [unknown] Parallel work, quotas: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Observed concurrency [unknown] Parallel work, observed_concurrency: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Status visibility [unknown] Parallel work, status_visibility: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:readme, open-swe:desktop, open-swe:src2-oswe-readme-flow

Agent cross-checked partial

Local desktop refuses starting another active agent in the same tree or switching its branch underneath it.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
7 atomic answers
  • Human assignment [unknown] Ownership and dispatch, human_assignment: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Agent assignment [unknown] Ownership and dispatch, agent_assignment: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Claims [unknown] Ownership and dispatch, claims: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Queues [unknown] Ownership and dispatch, queues: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Routing [unknown] Ownership and dispatch, routing: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Duplicate prevention [supported] Local desktop refuses starting another active agent in the same tree or switching its branch underneath it. Sources: open-swe:desktop.
  • Ownership enforcement [unknown] Ownership and dispatch, ownership_enforcement: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:desktop

Agent cross-checked partial

The runtime configures general-purpose subagents for independent work. Configuration separates main and subagent models and reasoning effort. Robin configures Deep Agents subagents through its own agent catalog.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
12 atomic answers
  • Roles [supported] The runtime configures general-purpose subagents for independent work. Sources: open-swe:custom.
  • Model harness effort [supported] Configuration separates main and subagent models and reasoning effort. Sources: open-swe:custom.
  • Messages [unknown] Inspectable delegation and communication, messages: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Results return [unknown] Inspectable delegation and communication, results_return: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Cross harness [unknown] Inspectable delegation and communication, cross_harness: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Orchestration owner [supported] Robin configures Deep Agents subagents through its own agent catalog. Sources: open-swe:custom.
  • Activation [unknown] Inspectable delegation and communication, activation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Authentication [unknown] Inspectable delegation and communication, authentication: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Live progress [unknown] Inspectable delegation and communication, live_progress: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Retained results [unknown] Inspectable delegation and communication, retained_results: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Followup [unknown] Inspectable delegation and communication, followup: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Invocation [unknown] Inspectable delegation and communication, invocation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:custom

Agent cross-checked partial

Recurring automation can start system-owned coding threads. GitHub, Slack and optional Linear events can initiate work.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-10
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
8 atomic answers
  • Schedules [supported] Recurring automation can start system-owned coding threads. Sources: open-swe:readme, open-swe:install.
  • Events [supported] GitHub, Slack and optional Linear events can initiate work. Sources: open-swe:install.
  • Recurring tasks [unknown] Unattended triggers, recurring_tasks: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Completion conditions [unknown] Unattended triggers, completion_conditions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Scheduler location [supported] Scheduled automations run on the backend as system-owned threads. Sources: open-swe:src2-oswe-schedules.
  • Overlaps [unknown] Unattended triggers, overlaps: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Retries [unknown] Unattended triggers, retries: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Client independence [supported] Scheduled runs and GitHub, Slack or Linear events start backend threads without an open client. Scheduled runs don't need the creator's OAuth token. Sources: open-swe:src2-oswe-schedules, open-swe:src2-oswe-readme-flow.

Sources: open-swe:readme, open-swe:install, open-swe:src2-oswe-schedules, open-swe:src2-oswe-readme-flow

Agent cross-checked partial

Slack Stop interrupts ordinary thread work, while other participants queued work may continue. Slack follow-ups queue behind an active run; the UI tracks submitted follow-up modes.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
10 atomic answers
  • Pause [unknown] Intervention and attention, pause: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Stop [supported] Slack Stop interrupts ordinary thread work, while other participants queued work may continue. Sources: open-swe:install.
  • Resume [unknown] Intervention and attention, resume: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Steer [supported] Slack follow-ups queue behind an active run; the UI tracks submitted follow-up modes. Sources: open-swe:install.
  • Notifications [unknown] Intervention and attention, notifications: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Pending decisions [unknown] Intervention and attention, pending_decisions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Escalation [unknown] Intervention and attention, escalation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Visible errors [unknown] Intervention and attention, visible_errors: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Chat terminal parity [unknown] Intervention and attention, chat_terminal_parity: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Retained history [unknown] Intervention and attention, retained_history: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:install

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Execution and reliability

Agent cross-checked partial

This Mac bridges a selected local folder to the backend-managed agent loop. The control plane has standalone Docker deployment; shipped execution still depends on Managed Deep Agents. Cloud coding uses persistent per-thread LangSmith Linux sandboxes. Local desktop runs stop being reachable when the owning app quits. Cloud thread execution is backend-managed.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
12 atomic answers
  • Local [supported] This Mac bridges a selected local folder to the backend-managed agent loop. Sources: open-swe:desktop.
  • Byo remote [unknown] Laptop-independent execution, byo_remote: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Self hosted [supported] The control plane has standalone Docker deployment; shipped execution still depends on Managed Deep Agents. Sources: open-swe:install.
  • Managed cloud [supported] Cloud coding uses persistent per-thread LangSmith Linux sandboxes. Sources: open-swe:readme, open-swe:custom.
  • Hybrid [unknown] Laptop-independent execution, hybrid: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Provisioning [unknown] Laptop-independent execution, provisioning: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Payer [unknown] Laptop-independent execution, payer: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Resources [unknown] Laptop-independent execution, resources: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Region [unknown] Laptop-independent execution, region: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Expiry [unknown] Laptop-independent execution, expiry: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Client disconnect [partial] Local desktop runs stop being reachable when the owning app quits. Cloud thread execution is backend-managed. Sources: open-swe:desktop, open-swe:readme.
  • Other device continuation [unknown] Laptop-independent execution, other_device_continuation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:desktop, open-swe:install, open-swe:readme, open-swe:custom

Agent cross-checked partial

Local desktop can create a dedicated Git worktree per thread. Local task folders and worktrees are not filesystem security sandboxes; cloud sandboxes have powerful shell/network tools.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-10
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
12 atomic answers
  • Checkout [unknown] Workspace and process isolation, checkout: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Branch [unknown] Workspace and process isolation, branch: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Worktree [supported] Local desktop can create a dedicated Git worktree per thread. Sources: open-swe:desktop.
  • Container [partial] Cloud threads run in isolated LangSmith Linux sandboxes, which can boot from snapshots built from a Docker image. The repository does not say whether the sandbox is a container or a VM. Sources: open-swe:src2-oswe-sandbox.
  • Vm [partial] The repository does not name the isolation technology behind LangSmith sandboxes, so VM or microVM isolation is not established. Sources: open-swe:src2-oswe-sandbox.
  • Os sandbox [unknown] Workspace and process isolation, os_sandbox: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Filesystem [unknown] Workspace and process isolation, filesystem: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Process [unknown] Workspace and process isolation, process: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Network [unknown] Workspace and process isolation, network: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Secrets [partial] Local bridge commands get the login shell environment with secret-shaped variables removed, except GITHUB_TOKEN and GH_TOKEN. Sources: open-swe:src2-oswe-desktop-bridge.
  • Code separation [unknown] Workspace and process isolation, code_separation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Security boundary [partial] Local task folders and worktrees are not filesystem security sandboxes; cloud sandboxes have powerful shell/network tools. Sources: open-swe:desktop, open-swe:readme.

Sources: open-swe:desktop, open-swe:readme, open-swe:src2-oswe-sandbox, open-swe:src2-oswe-desktop-bridge

Agent cross-checked partial

Local threads keep their transcript on the backend and can reopen the bridge on follow-up. An unreachable cloud sandbox is not silently replaced.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
12 atomic answers
  • Client disconnect [unknown] Recovery, expiry and continuity, client_disconnect: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Worker crash [unknown] Recovery, expiry and continuity, worker_crash: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Service restart [unknown] Recovery, expiry and continuity, service_restart: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Expiry [unknown] Recovery, expiry and continuity, expiry: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Transcript reload [supported] Local threads keep their transcript on the backend and can reopen the bridge on follow-up. Sources: open-swe:desktop.
  • Process reconnect [unknown] Recovery, expiry and continuity, process_reconnect: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Task resume [unknown] Recovery, expiry and continuity, task_resume: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • State reconstruction [unknown] Recovery, expiry and continuity, state_reconstruction: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Context loss [unknown] Recovery, expiry and continuity, context_loss: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Duplicate actions [unknown] Recovery, expiry and continuity, duplicate_actions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Manual repair [supported] An unreachable cloud sandbox is not silently replaced. Sources: open-swe:readme.
  • Multi day continuity [unknown] Recovery, expiry and continuity, multi_day_continuity: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:desktop, open-swe:readme

Agent cross-checked partial

Admins can capture workspace toolchain snapshots for later sandboxes. Runtime proxy rules inject GitHub App credentials for cloud Git operations.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
10 atomic answers
  • Dependencies [unknown] Development environment reliability, dependencies: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Caches [unknown] Development environment reliability, caches: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Snapshots [supported] Admins can capture workspace toolchain snapshots for later sandboxes. Sources: open-swe:install, open-swe:custom.
  • Services [unknown] Development environment reliability, services: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Ports [unknown] Development environment reliability, ports: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Secrets [supported] Runtime proxy rules inject GitHub App credentials for cloud Git operations. Sources: open-swe:custom.
  • Duplicate installs [unknown] Development environment reliability, duplicate_installs: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Collisions [unknown] Development environment reliability, collisions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Remote setup [unknown] Development environment reliability, remote_setup: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Automatic repair [unknown] Development environment reliability, automatic_repair: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:install, open-swe:custom

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Agent cross-checked partial

LangSmith is the default trace provider.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
13 atomic answers
  • Logs [unknown] Truthful status and operational statistics, logs: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Traces [supported] LangSmith is the default trace provider. Sources: open-swe:readme.
  • Failure reasons [unknown] Truthful status and operational statistics, failure_reasons: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Usage export [unknown] Truthful status and operational statistics, usage_export: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Task stats [unknown] Truthful status and operational statistics, task_stats: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Agent stats [unknown] Truthful status and operational statistics, agent_stats: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Project stats [unknown] Truthful status and operational statistics, project_stats: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Time stats [unknown] Truthful status and operational statistics, time_stats: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Failure status [unknown] Truthful status and operational statistics, failure_status: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Approval status [unknown] Truthful status and operational statistics, approval_status: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Reconnect consistency [unknown] Truthful status and operational statistics, reconnect_consistency: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Performance method [unknown] Truthful status and operational statistics, performance_method: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Responsiveness [unknown] Truthful status and operational statistics, responsiveness: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:readme

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Human collaboration and control

Agent cross-checked partial

Workspace and Slack collaborative threads can be prompted by participants without using personal MCP credentials.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
11 atomic answers
  • Visibility [unknown] Live human collaboration, visibility: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Discussion [unknown] Live human collaboration, discussion: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Comments [unknown] Live human collaboration, comments: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Presence [unknown] Live human collaboration, presence: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Coprompting [supported] Workspace and Slack collaborative threads can be prompted by participants without using personal MCP credentials. Sources: open-swe:custom.
  • Ordering [unknown] Live human collaboration, ordering: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Conflicts [unknown] Live human collaboration, conflicts: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Attribution [unknown] Live human collaboration, attribution: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Permissions [unknown] Live human collaboration, permissions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Plan restrictions [unknown] Live human collaboration, plan_restrictions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Owner online [unknown] Live human collaboration, owner_online: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:custom

Agent cross-checked partial

Configured admins administer all workspaces; signed-in users can use every workspace. Per-workspace role-based membership and access are explicitly deferred.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-17
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
9 atomic answers
  • Organization roles [supported] Configured admins administer all workspaces; signed-in users can use every workspace. Sources: open-swe:workspace.
  • Project roles [unsupported] Per-workspace role-based membership and access are explicitly deferred. Sources: open-swe:workspace.
  • Task roles [unknown] Roles and access boundaries, task_roles: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Membership [unknown] Roles and access boundaries, membership: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Sso [unknown] Dashboard sign-in is delegated to LangSmith OAuth (a hosted service), so any SSO is LangSmith configuration; Robin source documents and implements no identity-provider integration of its own. Sources: open-swe:d80-login, open-swe:d80-agents.
  • Provisioning [unknown] Roles and access boundaries, provisioning: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Unauthorized access [unknown] Roles and access boundaries, unauthorized_access: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Revocation [unknown] Roles and access boundaries, revocation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Plan scope [unknown] Roles and access boundaries, plan_scope: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:workspace, open-swe:d80-login, open-swe:d80-agents

Agent cross-checked partial

Workflow-file push approvals cover detected pushes rather than every shell/API write. Workspace bindings do not narrow installation-wide sandbox GitHub access.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
14 atomic answers
  • Command [partial] Workflow-file push approvals cover detected pushes rather than every shell/API write. Sources: open-swe:readme.
  • Tool [unknown] Approvals and temporary access, tool: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Network [unknown] Approvals and temporary access, network: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Secret [partial] Workspace bindings do not narrow installation-wide sandbox GitHub access. Sources: open-swe:workspace.
  • Delivery [unknown] Approvals and temporary access, delivery: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Approver identity [unknown] Approvals and temporary access, approver_identity: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Lifetime [unknown] Approvals and temporary access, lifetime: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Allow [unknown] Approvals and temporary access, allow: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Deny [unknown] Approvals and temporary access, deny: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Revoke [unknown] Approvals and temporary access, revoke: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Tunnels [unknown] Approvals and temporary access, tunnels: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Defaults [unknown] Approvals and temporary access, defaults: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Safer modes [unknown] Approvals and temporary access, safer_modes: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Enforcement [unknown] Approvals and temporary access, enforcement: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:readme, open-swe:workspace

Agent cross-checked partial

Opted-in dashboard mutations and marked agent tools persist actor-attributed activity; unmarked operations are excluded.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
11 atomic answers
  • Actions [partial] Opted-in dashboard mutations and marked agent tools persist actor-attributed activity; unmarked operations are excluded. Sources: open-swe:audit.
  • Approvals [unknown] Decision and activity history, approvals: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Edits [unknown] Decision and activity history, edits: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Discussion [unknown] Decision and activity history, discussion: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Decisions [unknown] Decision and activity history, decisions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Cross user persistence [unknown] Decision and activity history, cross_user_persistence: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Cross session persistence [unknown] Decision and activity history, cross_session_persistence: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Export [unknown] Decision and activity history, export: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Mutability [unknown] Decision and activity history, mutability: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Retention [unknown] Decision and activity history, retention: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Integrity [unknown] Decision and activity history, integrity: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:audit

Agent cross-checked partial

Opt-in Slack cards show a PR summary, size, branches and reviewers with GitHub review links.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
13 atomic answers
  • Pending reviews [supported] Opt-in Slack cards show a PR summary, size, branches and reviewers with GitHub review links. Sources: open-swe:human-review.
  • Change understanding [unknown] Review experience and guidance, change_understanding: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Evidence navigation [unknown] Review experience and guidance, evidence_navigation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Comments [unknown] Review experience and guidance, comments: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Request changes [unknown] Review experience and guidance, request_changes: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Shipping guidance [unknown] Review experience and guidance, shipping_guidance: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Effort [unknown] Review experience and guidance, effort: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Missed evidence [unknown] Review experience and guidance, missed_evidence: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Keyboard [unknown] Review experience and guidance, keyboard: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Narrow screen [unknown] Review experience and guidance, narrow_screen: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Context switching [unknown] Review experience and guidance, context_switching: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Roles [unknown] Review experience and guidance, roles: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Retained context [unknown] Review experience and guidance, retained_context: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:human-review

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Verification and delivery

Agent cross-checked partial

Desktop Changes compares against the initial Git snapshot and links the discovered PR.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
13 atomic answers
  • Diffs [supported] Desktop Changes compares against the initial Git snapshot and links the discovered PR. Sources: open-swe:desktop.
  • Documents [unknown] Retained artifacts and outputs, documents: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Screenshots [unknown] Retained artifacts and outputs, screenshots: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Recordings [unknown] Retained artifacts and outputs, recordings: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Previews [unknown] Retained artifacts and outputs, previews: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Test outputs [unknown] Retained artifacts and outputs, test_outputs: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Reviewer outputs [unknown] Retained artifacts and outputs, reviewer_outputs: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Persistence [unknown] Retained artifacts and outputs, persistence: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Child findings [unknown] Retained artifacts and outputs, child_findings: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Prompt leakage [unknown] Retained artifacts and outputs, prompt_leakage: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:desktop

Agent cross-checked partial

Human-review requests are refused for drafts, conflicts or failing required checks; this is a review-request gate.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
11 atomic answers
  • Tests [unknown] Verification and spec gates, tests: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Lint [unknown] Verification and spec gates, lint: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Types [unknown] Verification and spec gates, types: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Ci [unknown] Verification and spec gates, ci: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Independent review [unknown] Verification and spec gates, independent_review: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Spec checks [unknown] Verification and spec gates, spec_checks: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Required checks [partial] Human-review requests are refused for drafts, conflicts or failing required checks; this is a review-request gate. Sources: open-swe:human-review.
  • Failure blocking [unknown] Verification and spec gates, failure_blocking: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Requirement conflicts [unknown] Verification and spec gates, requirement_conflicts: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Configured policy [unknown] Verification and spec gates, configured_policy: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Enforced policy [unknown] Verification and spec gates, enforced_policy: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:human-review

Agent cross-checked partial

Robin opens and updates PRs, runs reviews and responds to CI feedback. Review findings can be published to GitHub.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-10
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
9 atomic answers
  • Branches [unknown] Git and pull request workflow, branches: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Worktrees [supported] A local desktop thread can get its own git worktree on a placeholder branch, which the agent renames. Sources: open-swe:src2-oswe-desktop-worktree.
  • Commits [unknown] Git and pull request workflow, commits: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Pull requests [supported] Robin opens and updates PRs, runs reviews and responds to CI feedback. Sources: open-swe:readme.
  • Comments [supported] Review findings can be published to GitHub. Sources: open-swe:readme.
  • Ci response [supported] With /baby-sit, Robin monitors opted-in PRs, diagnoses CI failures and reruns only flaky jobs that the evidence supports. Sources: open-swe:src2-oswe-readme-flow.
  • Rebase [unknown] Git and pull request workflow, rebase: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Conflicts [unknown] Git and pull request workflow, conflicts: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Product state [unknown] Git and pull request workflow, product_state: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:readme, open-swe:src2-oswe-desktop-worktree, open-swe:src2-oswe-readme-flow

Agent cross-checked partial

Configured standard Slack human review can merge once reviewers approve, subject to its policy and feature flag.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
6 atomic answers
  • Approve [unknown] Merge and deployment authority, approve: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Merge [partial] Configured standard Slack human review can merge once reviewers approve, subject to its policy and feature flag. Sources: open-swe:human-review.
  • Release [unknown] Merge and deployment authority, release: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Deploy [unknown] Merge and deployment authority, deploy: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Exact revision [unknown] Merge and deployment authority, exact_revision: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Authority enforcement [unknown] Merge and deployment authority, authority_enforcement: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:human-review

Agent cross-checked partial

Review requests and desktop Changes link the relevant PR.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
9 atomic answers
  • Delivery status [unknown] Completion evidence and rollback, delivery_status: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Retained evidence [unknown] Completion evidence and rollback, retained_evidence: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Rollback [unknown] Completion evidence and rollback, rollback: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Revert [unknown] Completion evidence and rollback, revert: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Stale approval invalidation [unknown] Completion evidence and rollback, stale_approval_invalidation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:human-review, open-swe:desktop

Agent cross-checked partial

Optional merge queue observes GitHub candidates; native observation does not execute merges or tests.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
12 atomic answers
  • Review queue [unknown] Batch review and high-volume shipping, review_queue: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Summaries [unknown] Batch review and high-volume shipping, summaries: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Grouping [unknown] Batch review and high-volume shipping, grouping: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Risk size filters [unknown] Batch review and high-volume shipping, risk_size_filters: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Findings [unknown] Batch review and high-volume shipping, findings: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Artifacts [unknown] Batch review and high-volume shipping, artifacts: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Request changes [unknown] Batch review and high-volume shipping, request_changes: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Exact revision approval [unknown] Batch review and high-volume shipping, exact_revision_approval: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Dependency queues [partial] Optional merge queue observes GitHub candidates; native observation does not execute merges or tests. Sources: open-swe:queue.
  • Next actions [unknown] Batch review and high-volume shipping, next_actions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Stale approval invalidation [unknown] Batch review and high-volume shipping, stale_approval_invalidation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Check deduplication [unknown] Batch review and high-volume shipping, check_deduplication: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:queue

Ownership, privacy and economics

Agent cross-checked partial

Robin code is MIT licensed; vendor/ material is outside this repository grant. The MIT grant covers Robin backend code with the same vendor/ exclusion.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
6 atomic answers
  • Client license [supported] Robin code is MIT licensed; vendor/ material is outside this repository grant. Sources: open-swe:license, open-swe:readme.
  • Server license [supported] The MIT grant covers Robin backend code with the same vendor/ exclusion. Sources: open-swe:license, open-swe:readme.
  • Hosted extensions [unknown] Source and license, hosted_extensions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Source visibility [unknown] Source and license, source_visibility: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Source revision [unknown] Source and license, source_revision: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Hosted parity [unknown] Source and license, hosted_parity: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:license, open-swe:readme

Agent cross-checked partial

The core backend and web UI can be deployed using the documented Docker image. The unmodified backend requires Managed Deep Agents and LangSmith credentials.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
8 atomic answers
  • Self hosting [supported] The core backend and web UI can be deployed using the documented Docker image. Sources: open-swe:install.
  • Vendor dependencies [supported] The unmodified backend requires Managed Deep Agents and LangSmith credentials. Sources: open-swe:install, open-swe:readme.
  • Export [unknown] Hosting and exit, export: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Import [unknown] Hosting and exit, import: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Formats [unknown] Hosting and exit, formats: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Cancellation [unknown] Hosting and exit, cancellation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Account independence [unknown] Hosting and exit, account_independence: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • History portability [unknown] Hosting and exit, history_portability: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:install, open-swe:readme

Agent cross-checked partial

The documented optional PostHog and Segment integrations send nothing without keys. This does not describe every trace or audit store. Leaving POSTHOG_API_KEY and SEGMENT_BROWSER_WRITE_KEY unset disables those optional telemetry integrations.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
15 atomic answers
  • Code data [unknown] Data handling and telemetry, code_data: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Prompts [unknown] Data handling and telemetry, prompts: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Credentials [unknown] Data handling and telemetry, credentials: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Logs [unknown] Data handling and telemetry, logs: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Artifacts [unknown] Data handling and telemetry, artifacts: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Retention [unknown] Data handling and telemetry, retention: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Deletion [unknown] Data handling and telemetry, deletion: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Training [unknown] Data handling and telemetry, training: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Residency [unknown] Data handling and telemetry, residency: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Subprocessors [unknown] Data handling and telemetry, subprocessors: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Telemetry disclosure [unknown] Data handling and telemetry, telemetry_disclosure: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Telemetry defaults [partial] The documented optional PostHog and Segment integrations send nothing without keys. This does not describe every trace or audit store. Sources: open-swe:install.
  • Telemetry controls [supported] Leaving POSTHOG_API_KEY and SEGMENT_BROWSER_WRITE_KEY unset disables those optional telemetry integrations. Sources: open-swe:install.
  • Provider separation [unknown] Data handling and telemetry, provider_separation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:install

Sourced partial

open-swe (Robin) is MIT open source with no price of its own; deploying it as-is requires LangChain's Managed Deep Agents and uses LangSmith sandboxes by default, and the README does not price either. Model execution uses user-supplied provider API keys or LangSmith Gateway credentials; those external service costs are not an Open SWE plan price.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: First-party pricing sources read 2026-11-10 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-10 (12 days old)
Agent cross-check
Not separately cross-checked
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
12 atomic answers
  • Currency [unknown] No first-party source states currency for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Interval [unknown] No first-party source states interval for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Seats [unknown] No first-party source states seats for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Seat minimum [unknown] No first-party source states seat minimum for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Workspace fees [unknown] No first-party source states workspace fees for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Included usage [unknown] No first-party source states included usage for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Credits [unknown] No first-party source states credits for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Trial [unknown] No first-party source states trial for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Overages [unknown] No first-party source states overages for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Taxes [unknown] No first-party source states taxes for a paid plan. Checked: langchain-ai/open-swe README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
  • Model cost [supported] Deployments use model-provider API credentials or LangSmith Gateway, billed externally; the application itself has no paid licence plan. Sources: open-swe:install, open-swe:custom, open-swe:gap39-agent-models.
  • Compute cost [partial] LangSmith is the default sandbox provider, and as-is deployment needs Managed Deep Agents. The README gives no cost, and other sandbox providers or local execution can be configured. Sources: open-swe:readme-nov10.

Sources: open-swe:license-nov10, open-swe:readme-nov10, open-swe:install, open-swe:custom, open-swe:gap39-agent-models

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Agent cross-checked partial

The project warns of breaking changes and calls desktop experimental; web UI is recommended. The README says issues and external contributions are not currently accepted. Desktop nightly release notes are publicly available.

Scope
Surfaces: Robin web dashboard and backend, Experimental Robin macOS Electron client and CLI · Version: Repository 82364a02943300ade58376cbd19123425bcf4f4a; first-party source pass 2026-11-08. Desktop is experimental; web UI recommended. Managed Deep Agents remains required. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-08 (14 days old)
Agent cross-check
2026-11-08
  • Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
8 atomic answers
  • Release stage [supported] The project warns of breaking changes and calls desktop experimental; web UI is recommended. Sources: open-swe:readme, open-swe:desktop.
  • Access restrictions [unknown] Availability and support, access_restrictions: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Support [supported] The README says issues and external contributions are not currently accepted. Sources: open-swe:readme.
  • Response commitments [unknown] Availability and support, response_commitments: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Release activity [supported] Desktop nightly release notes are publicly available. Sources: open-swe:release.
  • Status history [unknown] Availability and support, status_history: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Deprecation [unknown] Availability and support, deprecation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Export options [unknown] Availability and support, export_options: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:readme, open-swe:desktop, open-swe:release

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Agent cross-checked partial

Robin is MIT open source. The desktop app and CLI are free downloads from GitHub releases, currently nightly pre-releases. LangChain's own deployment requires sign-in and shows no plans or pricing. Deploying it as-is depends on Managed Deep Agents and LangSmith sandboxes, which the repository does not price.

Scope
Surfaces: Experimental Robin macOS Electron client and CLI, Robin web dashboard and backend · Version: desktop-v0.3.16-nightly.20261110161458 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-10 (12 days old)
Agent cross-check
2026-11-10
  • No installed-product test was run.
  • Desktop releases are nightly pre-releases.
  • Costs for Managed Deep Agents, LangSmith sandboxes and models are not in the repository.
10 atomic answers
  • Ongoing free [supported] The desktop app, CLI and backend source are free to download under MIT, with no paid tier in the README, licence or releases. Sources: open-swe:src2-oswe-release.
  • Trial [unknown] Useful free tier and evaluation access, trial: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Credits trial [unknown] Useful free tier and evaluation access, credits_trial: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Self host cost [partial] The software itself is free. Running it needs model provider keys and, as-is, Managed Deep Agents and LangSmith sandboxes, which are priced outside the repository. Sources: open-swe:src2-oswe-models, open-swe:src2-oswe-sandbox.
  • Paid only [unknown] Useful free tier and evaluation access, paid_only: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Early access [unknown] Useful free tier and evaluation access, early_access: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Free scenarios [unknown] Useful free tier and evaluation access, free_scenarios: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Card required [unknown] Useful free tier and evaluation access, card_required: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Usage caps [unknown] Useful free tier and evaluation access, usage_caps: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.
  • Paid evaluation [unknown] Useful free tier and evaluation access, paid_evaluation: Robin's checked sources did not establish this requirement or its rubric scenario. No installed-product fixture was run.

Sources: open-swe:src2-oswe-release, open-swe:src2-oswe-hosted, open-swe:src2-oswe-models, open-swe:src2-oswe-sandbox

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Sources

open-swe:desktop

Robin desktop/README.md

Experimental Electron client supports Apple Silicon macOS Ventura or later. Bundled robin/oswe CLI and local bridge run tasks in checkouts or worktrees. Local runs need the app open; Changes shows a session diff.

Kind
documented
Locator
Overview; This Mac; Work mode; Install on macOS
Source date
Not stated
Retrieved
2026-11-08
open-swe:src2-oswe-mobile

Robin iOS client README

The iOS Expo client is built from source with Xcode as a development build on a simulator or connected iPhone; the README states only iOS is supported. No App Store or release asset is documented.

Kind
documented
Locator
mobile/README.md lines 1-31 (Robin for iOS; Run it), commit ae120fc
Source date
Not stated
Retrieved
2026-11-10
open-swe:src2-oswe-readme-flow

Robin README capabilities

Robin builds, opens or updates PRs, uses subagents for independent work, monitors opted-in PRs with /baby-sit and reruns evidence-backed flaky jobs, and runs schedules. Work starts and continues from the dashboard, GitHub, Slack or Linear; cloud coding runs in persistent per-thread Linux sandboxes, LangSmith by default.

Kind
documented
Locator
README.md lines 41-62 (What Robin does; How it works), commit ae120fc
Source date
Not stated
Retrieved
2026-11-10
open-swe:src2-oswe-desktop-bridge

Robin Desktop This Mac

A This Mac thread is an ordinary backend thread whose sandbox is the local project; commands run with the login shell environment minus secret-shaped variables. It runs only while the app is open, is visible from web and other computers, but only that Mac can continue it.

Kind
documented
Locator
desktop/README.md lines 11-21 (This Mac), commit ae120fc
Source date
Not stated
Retrieved
2026-11-10
open-swe:src2-oswe-release

Robin Desktop Nightly 20261110161458 release assets

The latest desktop release is a free pre-release with only arm64 macOS app builds plus free standalone CLI binaries for macOS and Linux; no Windows or Linux desktop app and no iOS build is attached.

Kind
documented
Locator
Release desktop-v0.3.16-nightly.20261110161458 assets: Robin-0.3.16-nightly...-arm64-mac.dmg/.zip, robin-darwin-arm64/x64.tar.gz, robin-linux-arm64/x64.tar.gz, robin-SHA256SUMS (pre-release)
Source date
2026-11-10
Retrieved
2026-11-10
open-swe:gap39-browser-mobile

Robin mobile browser layout

The browser client explicitly uses a mobile full-screen sidebar overlay and collapses it below 767px so the chat remains visible. This is the cloud-thread browser client; This Mac threads retain their documented owning-Mac restrictions.

Kind
source-inspected
Locator
readStoredCollapsed, lines 30-42; browser sidebar layout
Source date
Not stated
Retrieved
2026-11-13
Commit
ae120fc74d21a7b3aaaaa34a1774718408fad021
Path
ui/src/components/sidebar-layout.tsx
open-swe:readme

Robin README.md

Robin is the current name for this repository. The backend uses Deep Agents and LangGraph, supports parallel threads and subagents, accepts GitHub/Slack/Linear input, and delivers PRs. Managed Deep Agents is required as shipped.

Kind
documented
Locator
What Robin does; How it works; Control and safety
Source date
Not stated
Retrieved
2026-11-08
open-swe:custom

Robin docs/CUSTOMIZATION.md

Per-thread LangSmith Linux sandboxes, snapshots and local bridges are configurable. Models use API credentials or LangSmith Gateway. Workspace and personal MCP scopes, skills and repository instructions are configurable.

Kind
documented
Locator
Sandbox; Model; Tools; Workspace MCP servers; System prompt
Source date
Not stated
Retrieved
2026-11-08
open-swe:mirror

Robin docs/reference/claude-code-sync.md

Claude Code hooks mirror local sessions into private read-only dashboard threads. Mirrors cannot be prompted, steered or stopped in Robin; uploaded sessions can start a separate continuable thread.

Kind
documented
Locator
Guarantees; What a thread shows
Source date
Not stated
Retrieved
2026-11-08
open-swe:src2-oswe-claudesync

Robin Claude Code mirroring

Claude Code hook events are posted to Robin so each Claude Code session appears as a private, read-only dashboard thread; Robin does not drive the session.

Kind
documented
Locator
docs/reference/claude-code-sync.md lines 1-4 (Mirroring Claude Code sessions), commit ae120fc
Source date
Not stated
Retrieved
2026-11-10
open-swe:gap39-agent-models

Robin agent runtime and model configuration

Every run model loop runs on Managed Deep Agents and uses Robin-configured models, subagents, tools and loop rules. Bounded inspection of mda runtime/model catalog and sandbox tool surface found no runnable integration of the nine compared external coding-CLI harnesses. Claude Code hooks are separately documented read-only mirrors; provider access uses API/Gateway credentials.

Kind
documented
Locator
Opening ToolSurface description; Sandbox; Model
Source date
Not stated
Retrieved
2026-11-13
open-swe:install

Robin docs/INSTALLATION.md

Web dashboard and FastAPI share one deployment. Docker self-hosting still requires Managed Deep Agents. GitHub/Slack are required, Linear optional. PostHog and Segment capture are disabled without their keys. Shared Slack threads accept queued participant prompts.

Kind
documented
Locator
Deployment; credentials; optional tracking; machine callers; thread scope
Source date
Not stated
Retrieved
2026-11-08
open-swe:human-review

Robin docs/reference/human-review.md

Feature-flagged Slack human review cards track reviewer sign-up, PR summary and GitHub links. Required-check failures, drafts, closed and conflicted PRs block requests; supplementary specialists are separately selected.

Kind
documented
Locator
Requesting; Reviewers; Configuration
Source date
Not stated
Retrieved
2026-11-08
open-swe:gap39-future-work

Robin durable future-work suggestions

Robin persists independent suggested_task records with summary/details, repository/workspace and context links without starting work. The suggestion schema has no open/in-progress/done state. Its Task table instead groups coordinator/worker agent threads, and task status returns thread-derived worker status. This establishes native idea capture, not a general stateful issue/backlog interface.

Kind
source-inspected
Locator
SuggestedTask and SuggestedTaskContent schemas; create; tools/suggest_task.py; tasks/store.py and service.py task_details
Source date
Not stated
Retrieved
2026-11-13
Commit
ae120fc74d21a7b3aaaaa34a1774718408fad021
Path
openswe/tasks/suggestions.py
open-swe:d80-suggest

open-swe openswe/tasks/suggestions.py

A SuggestedTask has summary, details, workspace, repository, thread, task and PR links, context links and audit fields; it has no status or state field.

Kind
source-inspected
Locator
openswe/tasks/suggestions.py l18-l38; SuggestedTask model; main HEAD (no stable release; only desktop nightlies) (64dd120)
Source date
Not stated
Retrieved
2026-11-16
Commit
64dd120b6a2aa7b5f13fef30f97a0e987523c2c6
Path
openswe/tasks/suggestions.py
open-swe:d80-task

open-swe openswe/tasks/store.py

A Task row holds a title, workspace, coordinator thread id and a delegated flag; it groups coordinator and worker threads and has no open/in-progress/done state.

Kind
source-inspected
Locator
openswe/tasks/store.py l27-l41; Task model; main HEAD (no stable release; only desktop nightlies) (64dd120)
Source date
Not stated
Retrieved
2026-11-16
Commit
64dd120b6a2aa7b5f13fef30f97a0e987523c2c6
Path
openswe/tasks/store.py
open-swe:d80-taskmig

open-swe openswe/database/migrations/versions/0051_179eb756b3cf_task_coordination.py

The task table columns are id, coordinator_thread_id, title, workspace_id and delegated; a later migration adds goal_check text.

Kind
source-inspected
Locator
openswe/database/migrations/versions/0051_179eb756b3cf_task_coordination.py l13-l21; task table migration; main HEAD (no stable release; only desktop nightlies) (64dd120)
Source date
Not stated
Retrieved
2026-11-16
Commit
64dd120b6a2aa7b5f13fef30f97a0e987523c2c6
Path
openswe/database/migrations/versions/0051_179eb756b3cf_task_coordination.py
open-swe:src2-oswe-schedules

Robin scheduled automations

Scheduled automations run as system-owned threads on the backend, open PRs as the GitHub App, and do not need the creator's OAuth token.

Kind
documented
Locator
docs/INSTALLATION.md lines 844-850 (Thread ownership and PR authorship), commit ae120fc
Source date
Not stated
Retrieved
2026-11-10
open-swe:src2-oswe-sandbox

Robin sandbox customization

Each thread runs in a LangSmith cloud sandbox that Managed Deep Agents creates when the run starts, using the deployment's LangSmith API key; defaults are 4 vCPUs, 16 GiB memory, 128 GiB disk, a 2 h idle TTL and deletion 7 days after stop, all configurable. The isolation technology (container or VM) is not named. A bridged thread runs on its owner's machine instead.

Kind
documented
Locator
docs/CUSTOMIZATION.md lines 22-63 (1. Sandbox; Who creates sandboxes), commit ae120fc
Source date
Not stated
Retrieved
2026-11-10
open-swe:workspace

Robin docs/reference/workspaces.md

All signed-in users see all workspaces; configured admins administer all. Public/private thread visibility differs. Per-workspace membership and roles are explicitly deferred; repository routing is not credential isolation.

Kind
documented
Locator
Access; GitHub access; Sandbox identity; Dashboard
Source date
Not stated
Retrieved
2026-11-08
open-swe:d80-login

open-swe openswe/dashboard/auth_routes.py

Dashboard sign-in redirects to LangSmith OAuth, or to a local dev login that acts as the gh CLI user; Robin implements no identity-provider integration of its own.

Kind
source-inspected
Locator
openswe/dashboard/auth_routes.py l77-l91; auth_login; main HEAD (no stable release; only desktop nightlies) (64dd120)
Source date
Not stated
Retrieved
2026-11-16
Commit
64dd120b6a2aa7b5f13fef30f97a0e987523c2c6
Path
openswe/dashboard/auth_routes.py
open-swe:d80-agents

open-swe AGENTS.md

Every agent, reviewer and review-scout thread runs on Managed Deep Agents, which owns the model loop, sandbox and tools; the backend refuses to start without MDA_RUNTIME_URL.

Kind
documented
Locator
AGENTS.md l14-l18; Architecture; main HEAD (no stable release; only desktop nightlies) (64dd120)
Source date
Not stated
Retrieved
2026-11-16
open-swe:audit

Robin docs/AUDIT_LOGS.md

Only opted-in marked dashboard mutations and tool operations are persisted with verified actors. Read routes and arbitrary MCP calls are excluded; general arguments and payloads are omitted.

Kind
documented
Locator
Capture policy
Source date
Not stated
Retrieved
2026-11-08
open-swe:src2-oswe-desktop-worktree

Robin Desktop worktrees

New worktree gives a local thread its own git worktree on a placeholder open-swe/local-<id> branch that the agent renames, so several local threads can run at once.

Kind
documented
Locator
desktop/README.md lines 35-36 (New worktree), commit ae120fc
Source date
Not stated
Retrieved
2026-11-10
open-swe:queue

Robin docs/MERGE_QUEUE.md

Optional native merge-queue observer reads GitHub state without merging or dispatching tests. Custom smoke-validation configuration is operator-managed, disabled by default, and not permission to merge.

Kind
documented
Locator
Native observation; Configuration; Human controls
Source date
Not stated
Retrieved
2026-11-08
open-swe:license

Robin LICENSE

Robin code is MIT licensed; README excludes vendor/ material from that grant.

Kind
source-inspected
Locator
MIT grant
Source date
Not stated
Retrieved
2026-11-08
Commit
82364a02943300ade58376cbd19123425bcf4f4a
Path
LICENSE
open-swe:readme-nov10

open-swe (Robin) README

Says the project (now called Robin) is MIT open source and deployable in your own infrastructure. Deploying it as-is requires LangChain's Managed Deep Agents, and LangSmith is the default sandbox provider. The README gives no price for either.

Kind
documented
Locator
Intro NOTE block; 'Customize' bullet; sandbox paragraph; 'License'
Source date
Not stated
Retrieved
2026-11-10
open-swe:license-nov10

langchain-ai/open-swe LICENSE (MIT)

The MIT License lets anyone obtain, use, copy and modify the software free of charge.

Kind
documented
Locator
Permission grant, first paragraph
Source date
Not stated
Retrieved
2026-11-10
open-swe:release

Robin desktop-v0.3.14-nightly.20261108081800

Public release desktop-v0.3.14-nightly.20261108081800 was published 2026-11-08.

Kind
documented
Locator
Release heading and notes
Source date
2026-11-08
Retrieved
2026-11-08
open-swe:src2-oswe-models

Robin model credentials

The deployer sets at least one model provider key (Anthropic, OpenAI and others) or routes all model calls through the LangSmith LLM Gateway with one LangSmith key.

Kind
documented
Locator
docs/INSTALLATION.md lines 288-300 (Model provider keys; LangSmith LLM Gateway), commit ae120fc
Source date
Not stated
Retrieved
2026-11-10
open-swe:src2-oswe-hosted

Robin sign-in page (LangChain deployment)

LangChain runs a sign-in-gated Robin deployment at openswe.langchain.dev; the page shows only a LangSmith sign-in and no signup, plan or pricing information.

Kind
documented
Locator
openswe.langchain.dev root redirects to /login; page offers Continue with LangSmith, fetched 2026-11-10
Source date
2026-11-10
Retrieved
2026-11-10

Comparisons with open-swe

Compare open-swe with any other product on adecomparison.com.