podium

no_human

50 of 51 criteria have a sourced finding; 43 were also cross-checked by a second agent. Every comparison that includes no_human 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
2026-11-16
Agent cross-checked
43 criteria
Comparisons
1

Access and agent choice

ACC-01

Client access

Agent cross-checked partial

Desktop app (macOS arm64 DMG, Windows unsigned exe, Linux .deb and AppImage x86_64), a web board served on loopback, the nh CLI with a shell, an MCP stdio bridge and a Claude Code plugin. No mobile apps; the board has no authentication so phone access is not a supported path.

Scope
Surfaces: no_human desktop app (Electron shell around the local nh server), Web board on 127.0.0.1:8420, nh CLI and shell, MCP stdio bridge, Claude Code plugin and GitHub Action reviewer gate · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
9 atomic answers
  • Desktop os [supported] macOS (arm64 DMG), Windows unsigned installer and Linux .deb/AppImage ship per release; windows and linux docs mark parts unverified. Sources: no-human:release, no-human:windows, no-human:linux.
  • Mobile apps [unsupported] No iOS or Android app in desktop, web or plugins. Sources: no-human:srch-mobile.
  • Browser [supported] nh start serves the board and worker on 127.0.0.1:8420. Sources: no-human:readme, no-human:api.
  • Mobile browser [partial] server.host can bind another address, but the board API is unauthenticated and loopback-checked; no phone workflow is documented. Sources: no-human:boundary, no-human:config.
  • Cli [supported] nh with shell, task, status, review, diff, approve, reject, reply, wake and more. Sources: no-human:cli, no-human:readme.
  • Editor extensions [partial] A Claude Code plugin and MCP bridge file tasks from the editor session; no VS Code or JetBrains extension. Sources: no-human:plugin, no-human:srch-mobile.
  • Task actions [supported] Add, pause, resume, cancel, retry, answer questions, review, diff, approve, reject and send back from board or CLI. Sources: no-human:api, no-human:cli.
  • Notifications [partial] Slack and Teams messages when a task needs you plus a Needs answer lane; no push to a phone. Sources: no-human:readme, no-human:adapters.
  • Cross device continuity [unsupported] State is a local SQLite database on one machine. Sources: no-human:site, no-human:srch-cloud.

Sources: no-human:release, no-human:readme, no-human:windows, no-human:linux, no-human:srch-mobile, no-human:api, no-human:boundary, no-human:config, no-human:cli, no-human:plugin, no-human:adapters, no-human:site, no-human:srch-cloud

Agent cross-checked partial

Three coder backends: claude (Claude Agent SDK driving the claude CLI, default), codex (codex exec) and local (the claude CLI pointed at your own Anthropic-compatible server). Planner, supervisor, intake and by default the reviewer stay on Claude; the reviewer can be assigned a different backend per role, so a codex coder with a Claude reviewer is a mixed-harness run.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
5 atomic answers
  • Harnesses [supported] claude and codex CLIs plus a local-server mode of the claude CLI. Sources: no-human:backends.
  • Model providers [partial] Anthropic, OpenAI and any Anthropic-compatible server; the model picker lists enabled models; other providers need the local mode. Sources: no-human:backends, no-human:config.
  • Custom adapters [unsupported] The backend list is closed to three entries; the local mode is the only extension point. Sources: no-human:backends.
  • Session integration [supported] Embeds the Claude Agent SDK and runs codex exec --json with per-task preflight. Sources: no-human:backends, no-human:claude.
  • Mixed harness operation [supported] A codex coder with a Claude reviewer bills two vendors in one task. Sources: no-human:backends.

Sources: no-human:backends, no-human:config, no-human:claude

Agent cross-checked partial

Claude subscription OAuth (claude setup-token) or Anthropic API key; Codex through an OpenAI API key or a ChatGPT login (codex_auth_mode subscription); local Anthropic-compatible servers. One billing path per run is enforced by scrubbing other credentials. No vendor credits; no account required.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
7 atomic answers
  • Agent subscriptions [supported] Claude OAuth token in subscription mode (default) and Codex ChatGPT subscription mode. Sources: no-human:security, no-human:backends.
  • Api accounts [supported] ANTHROPIC_API_KEY in api_key mode and OPENAI_API_KEY for codex. Sources: no-human:security, no-human:backends.
  • Vendor credits [unsupported] No vendor credits; the local tier is free and inference is billed by the user's provider. Sources: no-human:site.
  • Local models [supported] llm.local_model and llm.local_base_url point the claude CLI at your own server. Sources: no-human:config, no-human:backends.
  • Account switching [partial] nh auth use switches the auth mode and backend; one credential per run. Sources: no-human:cli, no-human:security.
  • Vendor account requirement [supported] No no_human account; official builds forward the wizard email to a hosted registration intake. Sources: no-human:site, no-human:email.
  • Provider restrictions [partial] INTEGRATIONS_LEGAL.md records the legal position and unresolved points for Codex authentication and other integrations. Sources: no-human:legal.

Sources: no-human:security, no-human:backends, no-human:config, no-human:site, no-human:cli, no-human:email, no-human:legal

Agent cross-checked partial

Quickstart in five minutes: install prerequisites, nh init (token, config, first repo), add a task from a title or a GitHub/GitLab/Jira/Linear/monday ticket, run, review, approve. Needs a git repository; PR opening and landing use a GitHub or GitLab remote. No managed cloud or VPS installer.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
7 atomic answers

Sources: no-human:quickstart, no-human:readme, no-human:srch-spec, no-human:config, no-human:adapters, no-human:site, no-human:srch-cloud

Agent cross-checked partial

nh CLI, a local HTTP API behind the board (tasks, approvals, events, metrics, config), an MCP stdio bridge (task_add, task_status), a Claude Code plugin and a GitHub Action reviewer gate. Board API has no authentication beyond loopback checks; no SDK or inbound webhooks.

Scope
Surfaces: nh CLI and shell, Web board on 127.0.0.1:8420, MCP stdio bridge, Claude Code plugin and GitHub Action reviewer gate · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
8 atomic answers

Sources: no-human:cli, no-human:api, no-human:mcp-server, no-human:action, no-human:boundary, no-human:srch-spec, no-human:plugin, no-human:readme, no-human:adapters, no-human:changelog

Agent cross-checked partial

Intake integrations (Jira, Linear, monday, GitHub, GitLab) with write-back, Slack and Teams notices, CI backends, a Claude Code plugin and the MCP bridge. The coder reads project settings and skills through the Claude Agent SDK; no general MCP client configuration, plugin marketplace or custom tool API of its own.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
7 atomic answers
  • Mcp client [partial] The coder session loads project settings so MCP servers configured in the repository are available; no no_human MCP configuration surface. Sources: no-human:claude.
  • Plugins [partial] Claude Code plugin and nh skills (nh skills add) exist; no third-party plugin API. Sources: no-human:plugin, no-human:cli.
  • Custom tools [partial] Verifiers and playbooks add checks and rules; no custom tool registry. Sources: no-human:verification, no-human:cli.
  • Instructions import [supported] Repository .no_human.yml and project.yml plus nh rules and skills. Sources: no-human:config, no-human:cli.
  • Authentication [supported] Tokens stored in ~/.no_human/.env (0600) and never in config or repo. Sources: no-human:security, no-human:config.
  • Permission scope [partial] Coder runs bypassPermissions by default with acceptEdits optional; tracker filters live in config. Sources: no-human:security, no-human:readme.
  • Integration owner [supported] no_human code owns intake, notices and CI adapters; the Claude CLI owns MCP. Sources: no-human:adapters.

Sources: no-human:adapters, no-human:claude, no-human:readme, no-human:plugin, no-human:cli, no-human:verification, no-human:config, no-human:security

Agent cross-checked partial

Electron desktop shell around a Python server and a web board built with npm; the desktop attaches to a local nh server or spawns the frozen one. No mobile client.

Scope
Surfaces: no_human desktop app (Electron shell around the local nh server), Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
4 atomic answers

Sources: no-human:desktop, no-human:distribution, no-human:srch-mobile

Planning and context

Agent cross-checked partial

Tasks start from a freeform title or sentence, a GitHub or GitLab issue URL, or Jira, Linear and monday.com tickets polled via filters; each ticket is scoped with the user (intake grill). With write-back on, ticket status and the PR link go back to the tracker. The tracker stays authoritative for tickets; no_human keeps task and attempt records.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
9 atomic answers
  • Local creation [supported] nh task add with a title or sentence works with no tracker. Sources: no-human:quickstart.
  • Prompt intake [supported] Plain-English intake in the shell and board. Sources: no-human:readme.
  • External import [supported] Jira Cloud, Linear, monday.com polling and GitHub/GitLab issue import. Sources: no-human:readme, no-human:adapters.
  • Chat git triggers [partial] Tracker polling and issue URLs; no chat or comment triggers. Sources: no-human:adapters.
  • Authoritative tracker [partial] The tracker remains authoritative for tickets; no_human holds tasks. Sources: no-human:adapters.
  • Stable ids [supported] Task IDs and ticket references. Sources: no-human:quickstart.
  • Sync [partial] One-way polling in; write-back of status and PR link is optional and off by default. Sources: no-human:readme.
  • Supported edits [partial] Status transition and PR link comments, matched by status category or label. Sources: no-human:readme.
  • External roundtrips [partial] Ticket editing and prioritisation happen in the tracker. Sources: no-human:adapters.

Sources: no-human:readme, no-human:adapters, no-human:quickstart

Agent cross-checked partial

A plan is written before any code from the ticket and repo (understanding as acceptance criteria, files, approach, test plan, scope, verification command); the intake grill asks clarifying questions; plan skip is stated in the event stream; per-attempt resume checkpoints exist. No plan editor with revisions.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
7 atomic answers
  • Plans [supported] Plan with acceptance criteria, files and verification command before coding. Sources: no-human:readme.
  • Acceptance criteria [supported] Checkable acceptance criteria in the plan; reviewer ticks each with file and line. Sources: no-human:readme, no-human:verification.
  • Editors [partial] Answers and send-back feedback steer the plan; no direct plan editor. Sources: no-human:api, no-human:cli.
  • Revisions [partial] Attempts and events are retained; no plan version history. Sources: no-human:api.
  • Amendment [partial] Pause, send back or reply with an answer; a running attempt checkpoints. Sources: no-human:api, no-human:config.
  • Restart persistence [supported] WIP-PARTIAL commits and resume_from survive nh stop. Sources: no-human:config.

Sources: no-human:readme, no-human:verification, no-human:api, no-human:cli, no-human:config

Agent cross-checked partial

Tasks can be split into subtasks (split proposals), follow another task (--follows), and wait on dependencies with DEPENDENCY_WAIT blockers and merge-stack link, plan and run for stacked PRs; priority orders the queue; no epics or free-depth hierarchy.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
9 atomic answers
  • Epics [unsupported] No epic object found. Sources: no-human:srch-spec.
  • Hierarchy [partial] Tasks split into subtasks and merge stacks link PRs; one level of subtasks. Sources: no-human:api, no-human:cli.
  • Blockers [supported] Blocker taxonomy including DEPENDENCY_WAIT with wake conditions. Sources: no-human:blockers.
  • Readiness [partial] Needs-you, waiting, working and done lanes; blockers carry wake conditions. Sources: no-human:blockers, no-human:readme.
  • Enforcement [partial] Blocked tasks wait on a wake condition; merge-stack runs in order on the user's command. Sources: no-human:blockers, no-human:cli.
  • State propagation [partial] Supersession warning on approve; no rollup. Sources: no-human:changelog.
  • Task to epic [unsupported] No epic. Sources: no-human:srch-spec.
  • Identity retention [partial] Split drafts create subtasks linked to the parent. Sources: no-human:api.
  • Workflow constraints [supported] The plan, implement, review pipeline is fixed but configurable by tier and routing. Sources: no-human:verification, no-human:config.

Sources: no-human:api, no-human:blockers, no-human:cli, no-human:srch-spec, no-human:readme, no-human:changelog, no-human:verification, no-human:config

Agent cross-checked partial

Repository config (.no_human.yml, project.yml), nh rules, playbooks, skills, memories (learnings with confirm, reject, retire and a 45-day archive sweep) and a wiki job feed later tasks; quarantine for suspect memories. Shared team brain is an announced Pro item.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
10 atomic answers
  • Instructions [supported] Rules, playbooks and repo-carried config. Sources: no-human:cli, no-human:config.
  • Skills [supported] nh skills add/list/remove/propose. Sources: no-human:cli.
  • Project docs [supported] Docs generation and wiki jobs read project docs. Sources: no-human:cli.
  • Memory [supported] Learnings with lifecycle, confirm and reject. Sources: no-human:api, no-human:config.
  • Scope [partial] Per project and repo; team scope is announced only. Sources: no-human:site, no-human:config.
  • Provenance [partial] Memories link source tasks; citation format not documented. Sources: no-human:api.
  • Correction [supported] Confirm, reject, pause, retire and restore endpoints. Sources: no-human:api.
  • Deletion [supported] Delete endpoint for learnings. Sources: no-human:api.
  • Freshness [supported] 45-day auto-archive sweep with flood control. Sources: no-human:config.
  • Takeover continuity [partial] Local database persists for the next operator on the machine. Sources: no-human:config.

Sources: no-human:api, no-human:config, no-human:cli, no-human:site

Agent cross-checked partial

A repository map, wiring evidence (is the symbol reachable), lint and net-new type diagnostics feed the reviewer; a brain/context layer indexes the repo; no external knowledge connectors beyond trackers; attachments accepted on tasks.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
10 atomic answers
  • Indexing [partial] Repo map and a brain module; index details not documented as a user feature. Sources: no-human:verification, no-human:adapters.
  • External knowledge [partial] Tracker tickets and wiki jobs; no knowledge connectors. Sources: no-human:adapters.
  • Multimodal inputs [partial] Task attachments are accepted. Sources: no-human:api.
  • Freshness [partial] Evidence is computed from the current worktree each review. Sources: no-human:verification.
  • Access scope [supported] Limited to the task worktree and configured repos. Sources: no-human:config.
  • Api retrieval [unsupported] No retrieval API. Sources: no-human:api.
  • Citations [supported] Reviewer findings cite file and line; preflight catches citation drift. Sources: no-human:verification.
  • Conflict detection [partial] Wiring evidence flags unreachable additions; no architecture conflict check. Sources: no-human:verification.
  • Review enforcement [supported] Reviewer gate blocks on failed checklist. Sources: no-human:verification.

Sources: no-human:verification, no-human:adapters, no-human:api, no-human:config

Agent cross-checked partial

Native board with lanes Needs answer, Working, Review PR, Backlog, Done, Failed; task priority high/medium/low, search, retitle, pause, resume, cancel, retry; tracker backlog picker; no labels or assignee fields. Tasks and attempts are separate entities.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
17 atomic answers
  • Create [supported] nh task add, board New task and tracker picks. Sources: no-human:readme.
  • Edit [partial] Retitle and config; plan edits by feedback. Sources: no-human:cli.
  • Discuss [partial] Reply and send-back threads with the agent; single operator. Sources: no-human:api.
  • Prioritize [supported] high, medium, low dispatch priority. Sources: no-human:config.
  • Label [unsupported] No labels found. Sources: no-human:srch-spec.
  • Assign [unsupported] No assignee; single operator. Sources: no-human:srch-team.
  • Filter [supported] Lanes and repo/project filters. Sources: no-human:api, no-human:readme.
  • Archive [partial] Done and Failed lanes; learnings archive; no task archive. Sources: no-human:readme.
  • Reopen [supported] retry, restore-approval and send-back. Sources: no-human:cli.
  • Project epic views [partial] Project and repo views; no epics. Sources: no-human:api.
  • Idea parking [supported] Backlog lane keeps tracker tickets until started. Sources: no-human:readme.
  • Explicit dispatch [supported] Start selected backlog tickets or run the drain. Sources: no-human:readme, no-human:quickstart.
  • Task session separation [supported] Task, attempts and events are separate. Sources: no-human:api.
  • Metadata [supported] Repo, tracker link, attempts, tokens, cost, tier and tags. Sources: no-human:readme.
  • Durable states [supported] Persistent statuses with events log. Sources: no-human:api.
  • External tracker requirement [partial] Usable without a tracker; planning at scale uses Jira, Linear or monday. Sources: no-human:readme.

Sources: no-human:readme, no-human:api, no-human:config, no-human:cli, no-human:srch-spec, no-human:srch-team, no-human:quickstart

Agent cross-checked partial

Agents (the coder) work inside a task, ask a specific question that parks the task (Needs answer), create no issues of their own; the MCP bridge and Claude Code plugin let another agent add and check tasks. Task IDs are shared by board, CLI, API and MCP; subtask split proposals and blockers are system-created.

Scope
Surfaces: MCP stdio bridge, Claude Code plugin and GitHub Action reviewer gate, Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
14 atomic answers

Sources: no-human:mcp-server, no-human:api, no-human:blockers, no-human:cli, no-human:plugin, no-human:srch-spec, no-human:srch-team, no-human:security, no-human:changelog, no-human:readme, no-human:config

Agent cross-checked unsupported

No living product specification: acceptance criteria belong to each task plan and memories are rules, not requirements; no revisions, drift detection or spec review gate.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
9 atomic answers
  • Persistent requirements [unsupported] No persistent requirements object, approvals, drift detection or spec review integration found in docs or src. Sources: no-human:srch-spec.
  • Human edits [unsupported] No persistent requirements object, approvals, drift detection or spec review integration found in docs or src. Sources: no-human:srch-spec.
  • Agent edits [unsupported] No persistent requirements object, approvals, drift detection or spec review integration found in docs or src. Sources: no-human:srch-spec.
  • Revisions [unsupported] No persistent requirements object, approvals, drift detection or spec review integration found in docs or src. Sources: no-human:srch-spec.
  • Approvals [unsupported] No persistent requirements object, approvals, drift detection or spec review integration found in docs or src. Sources: no-human:srch-spec.
  • Later retrieval [unsupported] No persistent requirements object, approvals, drift detection or spec review integration found in docs or src. Sources: no-human:srch-spec.
  • Drift detection [unsupported] No persistent requirements object, approvals, drift detection or spec review integration found in docs or src. Sources: no-human:srch-spec.
  • Review integration [unsupported] No persistent requirements object, approvals, drift detection or spec review integration found in docs or src. Sources: no-human:srch-spec.

Sources: no-human:srch-spec, no-human:readme

Coordination and automation

COORD-01

Parallel work

Agent cross-checked partial

Concurrency is off by default; when enabled a worker pool (default 2 workers) runs tasks in parallel worktrees; the header shows busy workers and queued count; lanes show needs-you, working, review and done. Overnight drain runs a bounded pool.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
5 atomic answers
  • Concurrent sessions [supported] Parallel task workers, each in its own worktree. Sources: no-human:config.
  • Concurrent tasks [supported] Pool of workers with --until-empty drains. Sources: no-human:quickstart, no-human:config.
  • Quotas [partial] concurrency.max_workers defaults to 2 when enabled; account rate limits park tasks. Sources: no-human:config.
  • Observed concurrency [unknown] Measured concurrency is a benchmark fact; no ADEMark entry exists. Sources: no-human:config.
  • Status visibility [supported] Board lanes, workers busy and queued counts, oldest waiting time. Sources: no-human:readme.

Sources: no-human:config, no-human:quickstart, no-human:readme

Agent cross-checked partial

A queue ordered by high/medium/low priority dispatches pending tasks to workers; quota-parked resumes first; leases prevent two workers owning a task (lease takeover after 600 s); no human assignment.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
7 atomic answers

Sources: no-human:config, no-human:srch-team, no-human:backends, no-human:changelog

Agent cross-checked partial

Product-owned pipeline of roles: planner, coder, an independent fresh-context reviewer (different model, never saw the coder transcript), supervisor, utility and intake agents; results return as plan, checklist and PR body; model per tier is configurable; the user does not invoke subagents directly. Cross-vendor coder and reviewer possible.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
12 atomic answers
  • Roles [supported] Planner, coder, reviewer, supervisor, utility and intake roles. Sources: no-human:backends, no-human:verification.
  • Model harness effort [supported] llm.primary_model, review_model, codex model and reasoning effort, model picker. Sources: no-human:config, no-human:backends.
  • Messages [partial] Send-back feedback and reply; roles do not converse freely. Sources: no-human:api.
  • Results return [supported] Reviewer checklist, verdict and PR body. Sources: no-human:verification.
  • Cross harness [supported] Codex coder with Claude reviewer. Sources: no-human:backends.
  • Orchestration owner [supported] Product code owns the loop. Sources: no-human:verification.
  • Activation [supported] On by default; reviewer routing and tiers configurable. Sources: no-human:config.
  • Authentication [supported] Same credential path as the run. Sources: no-human:security.
  • Live progress [supported] Event stream per task. Sources: no-human:api.
  • Retained results [supported] Attempts, checklists and events persist. Sources: no-human:api.
  • Followup [supported] Send back or retry with feedback after completion. Sources: no-human:cli.
  • Invocation [partial] Roles run automatically; skills and playbooks adjust. Sources: no-human:cli.

Sources: no-human:verification, no-human:backends, no-human:config, no-human:api, no-human:security, no-human:cli

Agent cross-checked partial

No built-in scheduler: nh watch and the overnight drain (--until-empty from cron or CI) run pools, trackers are polled on a tick, a nightly eval and a wake watcher resume blocked tasks; GitHub Action runs on PR events. Runs on the local machine, so a closed laptop stops them.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
8 atomic answers

Sources: no-human:quickstart, no-human:blockers, no-human:action, no-human:readme, no-human:adapters, no-human:config, no-human:cli

Agent cross-checked partial

Pause, resume, cancel, retry, send-back, reply to a parked question, wake blockers and graceful stop with checkpoints; Slack and Teams notices when a task needs you; Needs answer lane and oldest-waiting counter; honest stop with a specific question.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
10 atomic answers

Sources: no-human:api, no-human:blockers, no-human:readme, no-human:cli, no-human:config, no-human:adapters, no-human:verification

Agent cross-checked partial

The board shows lanes across tasks with counts, oldest-waiting time, per-task attempts, tokens and elapsed time, a Stats page and last-24h shipped totals; blockers show the wake condition; no epics or dependency graph.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
8 atomic answers
  • Fleet fixture [supported] Board hero image shows five lanes across several tasks. Sources: no-human:readme.
  • Parent child [partial] Subtasks link to parents. Sources: no-human:api.
  • Dependencies [partial] Blocker and follows relations stored; graph not shown. Sources: no-human:blockers, no-human:changelog.
  • Attention [supported] Needs answer lane and counter. Sources: no-human:readme.
  • History [supported] Done lane, events and Stats. Sources: no-human:api.
  • Workload [supported] Workers busy/queued and tokens per task. Sources: no-human:readme.
  • Navigation errors [supported] Failed lane with reason. Sources: no-human:readme.
  • Fixture mode [unknown] Fixture-based verification is not run by this catalog. Sources: no-human:readme.

Sources: no-human:readme, no-human:api, no-human:blockers, no-human:changelog

Agent cross-checked partial

The pipeline is fixed but tunable: tiers, review routing by diff size, backend per task, repro-gate mode, verifiers per repo; natural-language intake in the shell; per-role models; changes mid-run by pause/send-back; the event stream shows what ran.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
10 atomic answers
  • Quick task [supported] Plain-English shell intake or nh task add. Sources: no-human:readme.
  • Growing epic [unsupported] No epic. Sources: no-human:srch-spec.
  • Presets [partial] Tiers and project profiles; a pipeline is always used. Sources: no-human:config.
  • Natural language [supported] The shell intake accepts plain English. Sources: no-human:readme.
  • Agent configuration [supported] Per-role models and effort, per-task backend. Sources: no-human:config, no-human:backends.
  • In run changes [partial] Pause, send back and reply; task config human-only edits. Sources: no-human:config.
  • Live roles [supported] Event stream names planner, coder, reviewer steps. Sources: no-human:api.
  • Retained relationships [supported] Attempts and events retained. Sources: no-human:api.
  • Discoverability [supported] Docs, nh doctor and onboarding wizard. Sources: no-human:quickstart.
  • Auth friction [partial] Needs a Claude or OpenAI credential; email requested at onboarding. Sources: no-human:security, no-human:email.

Sources: no-human:config, no-human:verification, no-human:readme, no-human:srch-spec, no-human:backends, no-human:api, no-human:quickstart, no-human:security, no-human:email

Execution and reliability

Agent cross-checked partial

Runs on the user's machine (desktop or nh serve): coder sessions use the local claude or codex CLI in per-task worktrees. No vendor cloud, no remote worker, no VPS mode in the release; Max cloud is waitlist-only. A closed laptop stops it.

Scope
Surfaces: no_human desktop app (Electron shell around the local nh server), Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: local · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
12 atomic answers

Sources: no-human:site, no-human:readme, no-human:config, no-human:srch-cloud, no-human:boundary, no-human:quickstart, no-human:desktop, no-human:srch-mobile

Agent cross-checked partial

Every task runs in a throwaway git worktree by default; a task can opt out and use the primary checkout. No container, VM or OS sandbox: the coder runs bypassPermissions by default, with acceptEdits optional and a codex sandbox network switch; credentials are scrubbed so one billing path is used.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
12 atomic answers
  • Checkout [supported] isolation.enabled false uses the primary checkout. Sources: no-human:config.
  • Branch [supported] Per-task branch and commits under a distinct identity. Sources: no-human:security.
  • Worktree [supported] git worktree per task under ~/.no_human/worktrees. Sources: no-human:config.
  • Container [partial] UNTRUSTED_PR_REVIEW describes reviewing external PRs in a container; the coder is not containerised. Sources: no-human:security.
  • Vm [unsupported] No VM option. Sources: no-human:srch-cloud.
  • Os sandbox [partial] Codex coder uses the codex sandbox with a network_access switch; the Claude coder does not. Sources: no-human:backends.
  • Filesystem [partial] Worktree separation only. Sources: no-human:config.
  • Process [unsupported] No process isolation. Sources: no-human:security.
  • Network [partial] codex_network_access false cuts network for the codex sandbox; otherwise open. Sources: no-human:config, no-human:backends.
  • Secrets [supported] Other credentials are scrubbed from the process environment; keys live in a 0600 .env. Sources: no-human:security.
  • Code separation [supported] Worktree per task. Sources: no-human:config.
  • Security boundary [unsupported] Docs state the agent has Bash and what it runs can leave the machine. Sources: no-human:security.

Sources: no-human:config, no-human:security, no-human:backends, no-human:srch-cloud

Agent cross-checked partial

Attempts checkpoint with [WIP-PARTIAL] commits and resume_from; nh stop waits a grace period; leases are taken over after 600 s; quota-parked tasks resume first; retry and restore-approval commands; orphan grace and a task-sleep style wake watcher. All state is local SQLite.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
12 atomic answers
  • Client disconnect [supported] The server keeps running without the window. Sources: no-human:desktop.
  • Worker crash [supported] Lease takeover after 600 s and orphaned task rows handled. Sources: no-human:config.
  • Service restart [supported] Graceful stop checkpoints attempts and resumes them. Sources: no-human:config.
  • Expiry [unsupported] No sandbox expiry. Sources: no-human:srch-cloud.
  • Transcript reload [supported] Events and attempt details reload from the database. Sources: no-human:api.
  • Process reconnect [partial] Workers resume work through checkpoint; processes are not reattached. Sources: no-human:config.
  • Task resume [supported] resume_from with the WIP commit. Sources: no-human:config.
  • State reconstruction [partial] State rebuilt from events and checkpoints. Sources: no-human:config.
  • Context loss [partial] Startup cost per attempt re-accumulates context. Sources: no-human:config.
  • Duplicate actions [partial] Leases limit duplicate owners; PR duplicate guard not documented. Sources: no-human:config.
  • Manual repair [supported] retry, restore-approval, unblock, nh doctor. Sources: no-human:cli.
  • Multi day continuity [supported] Overnight drain and wake conditions. Sources: no-human:quickstart, no-human:blockers.

Sources: no-human:config, no-human:blockers, no-human:cli, no-human:desktop, no-human:srch-cloud, no-human:api, no-human:quickstart

Agent cross-checked partial

setup_cmds per repo prepare a fresh task worktree (installs, builds); per-repo test, lint and type commands; no snapshots, services or port management beyond configured verifiers; no shared dependency cache.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
10 atomic answers
  • Dependencies [supported] setup_cmds run in each fresh worktree. Sources: no-human:config.
  • Caches [unsupported] No shared cache found. Sources: no-human:srch-spec.
  • Snapshots [unsupported] None. Sources: no-human:srch-cloud.
  • Services [partial] Verifiers and UI evidence commands can start services. Sources: no-human:config.
  • Ports [unsupported] No port allocation found. Sources: no-human:srch-spec.
  • Secrets [partial] .env credentials for the run; project secrets not injected. Sources: no-human:security.
  • Duplicate installs [unsupported] Each worktree installs separately. Sources: no-human:config.
  • Collisions [unsupported] No collision handling documented. Sources: no-human:config.
  • Remote setup [unsupported] No remote setup. Sources: no-human:srch-cloud.
  • Automatic repair [partial] nh doctor checks the install; setup failures are reported. Sources: no-human:quickstart.

Sources: no-human:config, no-human:srch-spec, no-human:srch-cloud, no-human:security, no-human:quickstart

Agent cross-checked partial

Bounded loop: 3 attempts, 500 turns per attempt, inactivity timeout 3600 s, reviewer timeouts, min viable attempt token floor, per-task budget cap set before it runs, convergence early-abort; honest stop with a structured budget record; account quota parking. No dollar cap.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
8 atomic answers
  • Time limits [supported] attempt_timeout_s 3600 inactivity, review timeouts, approve test timeouts. Sources: no-human:config.
  • Turn limits [supported] bounds.max_turns_per_attempt 500 and convergence abort. Sources: no-human:config.
  • Token limits [supported] Per-task weighted token budget and a floor for starting an attempt. Sources: no-human:config, no-human:site.
  • Spend limits [partial] Token budgets approximate spend; no dollar cap and Enterprise budget policy is announced. Sources: no-human:config, no-human:site.
  • Timeouts [supported] Several documented timeouts. Sources: no-human:config.
  • Retries [supported] Up to three implement/review cycles plus provider retry. Sources: no-human:config.
  • Provider failures [supported] Quota parking and honest stop with reason. Sources: no-human:verification.
  • Enforcement [supported] Enforced stops with recorded reasons. Sources: no-human:verification.

Sources: no-human:config, no-human:verification, no-human:site

Agent cross-checked partial

Event stream per task, attempt details with failure reasons, reviewer checklist, metrics endpoints, Stats page, usage ledger, last-24h shipped and token totals, pr-outcomes and a nightly eval; anonymous telemetry separate. Speed and memory figures come only from ADEMark, which has no no_human entry.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
13 atomic answers
  • Logs [supported] Events stream and attempt details. Sources: no-human:api.
  • Traces [partial] Event log of planner, coder, review steps; no distributed traces. Sources: no-human:api.
  • Failure reasons [supported] Structured failure categories (budget_exhausted, review_failed, tamper_blocked, and others). Sources: no-human:telemetry.
  • Usage export [partial] Metrics endpoints and bench publish; CSV export not found. Sources: no-human:api.
  • Task stats [supported] Per-task attempts, tokens and duration. Sources: no-human:readme.
  • Agent stats [partial] Stats by tier and role; per-agent view not named. Sources: no-human:api.
  • Project stats [supported] /api/projects and metrics windows. Sources: no-human:api.
  • Time stats [supported] Last 24 h and metrics window. Sources: no-human:readme, no-human:api.
  • Failure status [supported] Failed lane and reason categories. Sources: no-human:readme.
  • Approval status [supported] Needs answer and Review PR lanes. Sources: no-human:readme.
  • Reconnect consistency [supported] Board reads from the database; stream resumes. Sources: no-human:api.
  • Performance method [unknown] Speed and memory belong to ADEMark; no_human is not listed. Sources: no-human:readme.
  • Responsiveness [unknown] Responsiveness is a benchmark fact outside this catalog. Sources: no-human:readme.

Sources: no-human:api, no-human:readme, no-human:config, no-human:telemetry

Agent cross-checked partial

Per-task token counts and estimated dollar cost (for example ~$0.40 per PR estimate and last-24h totals), usage ledger with 90-day compaction, cost levers analysis, weighted tokens per attempt; subscription mode shows tokens not dollars charged; no budget alert system.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
14 atomic answers
  • Task cost [supported] Attempts show tokens and the card shows estimated cost. Sources: no-human:readme.
  • Session cost [supported] Per attempt token totals. Sources: no-human:readme.
  • Child cost [partial] Subtasks are separate tasks. Sources: no-human:api.
  • Epic cost [unsupported] No epic. Sources: no-human:srch-spec.
  • Harness aggregation [partial] Codex and Claude costs are billed by two vendors and recorded per run. Sources: no-human:backends.
  • Billed vs estimated [supported] Labelled estimate (est.). Sources: no-human:readme.
  • Tokens [supported] Total and weighted tokens. Sources: no-human:config.
  • Subscription allowance [partial] Subscription tokens counted; plan windows not shown. Sources: no-human:srch-cost.
  • Provider reconciliation [unsupported] No reconciliation. Sources: no-human:srch-cost.
  • Compute cost [unsupported] Local compute not tracked. Sources: no-human:srch-cost.
  • Refresh delay [unknown] Refresh timing not documented. Sources: no-human:config.
  • Alerts [unsupported] No alerts found. Sources: no-human:srch-cost.
  • Export [partial] Metrics API and published benchmark; no export button. Sources: no-human:api.
  • Drilldown [supported] Attempt details drill down. Sources: no-human:api.

Sources: no-human:readme, no-human:config, no-human:srch-cost, no-human:api, no-human:srch-spec, no-human:backends

Sourced partial

Worker pool with a default of 2 workers clamped to a CPU-derived ceiling (cpu_count // 3, minimum 2), pending queue and priority, per-task worktrees, per-task pytest-xdist worker bounds, review depth scaled by diff size, change-scoped test runs and full-suite fallback with timeouts, minimum viable attempt token floor; no RAM limits, live load awareness or check reuse across tasks.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • See atomic answers for the unmet or unknown parts.
12 atomic answers
  • Concurrency [supported] concurrency.max_workers. Sources: no-human:config.
  • Queues [supported] Pending queue ordered by priority; quota-parked first. Sources: no-human:config.
  • Cpu ram [partial] CPU only: pool width ceiling is cpu_count // 3 (minimum 2) and xdist auto workers per task are bounded to cpu // max_workers; no memory limit. Sources: no-human:sched-cpu.
  • Backpressure [partial] Quota parking and floor token gate before starting an attempt. Sources: no-human:config.
  • Host awareness [partial] The detected CPU count sets the pool ceiling at server start and Settings shows it; no live memory or load awareness found. Sources: no-human:sched-cpu.
  • Check reuse [partial] Change-scoped test runs avoid the full suite; no cache across tasks. Sources: no-human:config.
  • Check deduplication [unsupported] No deduplication across tasks. Sources: no-human:srch-spec.
  • Bounded tests [supported] approve_merge test timeouts 1800 s and 5400 s. Sources: no-human:config.
  • Cancellation [supported] cancel and graceful stop. Sources: no-human:config, no-human:api.
  • Fairness [partial] No aging; low priority can starve. Sources: no-human:config.
  • Recovery [supported] Lease takeover and checkpoints. Sources: no-human:config.
  • Shared limits [partial] The pool limit is global. Sources: no-human:config.

Sources: no-human:config, no-human:srch-spec, no-human:api, no-human:sched-cpu

Human collaboration and control

Agent cross-checked partial

Single-operator local app: no presence, comments between people or co-prompting; Slack and Teams notices go to a channel; the board API is unauthenticated on loopback.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
11 atomic answers

Sources: no-human:srch-team, no-human:readme, no-human:boundary, no-human:config, no-human:site

Agent cross-checked unsupported

No roles, SSO or provisioning in the local product; Enterprise tier lists SSO and SCIM (not released). Board access is loopback-only.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
9 atomic answers
  • Organization roles [unsupported] Bounded search found no accounts, roles, SSO or provisioning in the release; SSO and SCIM appear only on the waitlisted Enterprise tier. Sources: no-human:srch-team, no-human:site.
  • Project roles [unsupported] Bounded search found no accounts, roles, SSO or provisioning in the release; SSO and SCIM appear only on the waitlisted Enterprise tier. Sources: no-human:srch-team, no-human:site.
  • Task roles [unsupported] Bounded search found no accounts, roles, SSO or provisioning in the release; SSO and SCIM appear only on the waitlisted Enterprise tier. Sources: no-human:srch-team, no-human:site.
  • Membership [unsupported] Bounded search found no accounts, roles, SSO or provisioning in the release; SSO and SCIM appear only on the waitlisted Enterprise tier. Sources: no-human:srch-team, no-human:site.
  • Sso [unsupported] Bounded search found no accounts, roles, SSO or provisioning in the release; SSO and SCIM appear only on the waitlisted Enterprise tier. Sources: no-human:srch-team, no-human:site.
  • Provisioning [unsupported] Bounded search found no accounts, roles, SSO or provisioning in the release; SSO and SCIM appear only on the waitlisted Enterprise tier. Sources: no-human:srch-team, no-human:site.
  • Unauthorized access [unsupported] Bounded search found no accounts, roles, SSO or provisioning in the release; SSO and SCIM appear only on the waitlisted Enterprise tier. Sources: no-human:srch-team, no-human:site.
  • Revocation [unsupported] Bounded search found no accounts, roles, SSO or provisioning in the release; SSO and SCIM appear only on the waitlisted Enterprise tier. Sources: no-human:srch-team, no-human:site.
  • Plan scope [unsupported] Bounded search found no accounts, roles, SSO or provisioning in the release; SSO and SCIM appear only on the waitlisted Enterprise tier. Sources: no-human:srch-team, no-human:site.

Sources: no-human:srch-team, no-human:site

Agent cross-checked partial

The agent never merges: nh approve is the human action that lands a PR under git.approve_identity, with change-scoped test gating; coder permission mode is bypassPermissions by default or acceptEdits; reviewer and tamper guard are enforced; Merge-ready policy. No network or secret approval flows.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
14 atomic answers

Sources: no-human:security, no-human:config, no-human:verification, no-human:readme, no-human:cli, no-human:srch-cloud

Agent cross-checked partial

Append-only event log per task, attempt records, reviewer checklist comment on the PR, usage ledger, signed distinct git identity; local SQLite so an operator can alter it; no audit retention or integrity model (an audit trail is Enterprise-announced).

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
11 atomic answers
  • Actions [supported] Events per task. Sources: no-human:api.
  • Approvals [supported] Approval and reject events with reasons. Sources: no-human:cli, no-human:api.
  • Edits [supported] Commits and diffs under a distinct identity. Sources: no-human:security.
  • Discussion [partial] Replies and send-back feedback. Sources: no-human:api.
  • Decisions [partial] Reviewer verdicts and approval records. Sources: no-human:verification.
  • Cross user persistence [unsupported] Single operator. Sources: no-human:srch-team.
  • Cross session persistence [supported] Database persists. Sources: no-human:config.
  • Export [partial] API reads and bench publish; no export tool. Sources: no-human:api.
  • Mutability [partial] Local database editable by the operator. Sources: no-human:security.
  • Retention [partial] Usage ledger compaction at 90 days and memory archive at 45 days. Sources: no-human:config.
  • Integrity [unsupported] No integrity guarantee; audit trail announced for Enterprise only. Sources: no-human:site.

Sources: no-human:api, no-human:security, no-human:site, no-human:cli, no-human:verification, no-human:srch-team, no-human:config

Sourced partial

Review lane with the reviewer's evidence checklist (pass/fail with file and line), diff view, test results panel, tamper banner, reproduction gate verdict, plan with acceptance criteria, PR body sections the coder cannot author, and one-click approve or reject with reason; PR comment of the checklist; CLI review, diff and review-comments.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • See atomic answers for the unmet or unknown parts.
13 atomic answers
  • Pending reviews [supported] Review PR lane and nh status. Sources: no-human:readme, no-human:cli.
  • Change understanding [supported] Plan, checklist and diff. Sources: no-human:readme.
  • Evidence navigation [supported] Test results, events, tamper and repro verdicts per task. Sources: no-human:readme.
  • Comments [partial] Reviewer comment on the PR; review-comments command. Sources: no-human:config, no-human:cli.
  • Request changes [supported] Reject with reason or send back. Sources: no-human:cli.
  • Shipping guidance [supported] Review and approve step with NOT RUN clarity. Sources: no-human:readme.
  • Effort [unknown] Review effort is a usability measure outside source inspection. Sources: no-human:readme.
  • Missed evidence [supported] NOT RUN labelled on PR when no test command is found. Sources: no-human:readme.
  • Keyboard [partial] Task rows and cards open with Enter or Space, dialogs trap Tab focus and Escape closes slide-overs; no shortcut list or command palette found. Sources: no-human:web-kbd.
  • Narrow screen [supported] The web board has a phone layout at a 640px breakpoint shared by JavaScript and CSS; it is served on loopback, so a phone needs a separate unauthenticated bind. Sources: no-human:web-resp.
  • Context switching [partial] One task at a time; lanes list tasks. Sources: no-human:readme.
  • Roles [supported] Planner, coder and independent reviewer clearly separated. Sources: no-human:verification.
  • Retained context [supported] Checklist and events retained. Sources: no-human:api.

Sources: no-human:readme, no-human:verification, no-human:cli, no-human:config, no-human:api, no-human:web-kbd, no-human:web-resp

Agent cross-checked partial

Single-operator: no colleague takeover; the work and history live in one local database; the PR and checklist comment are the shared artefacts for colleagues; the Pro shared brain is waitlisted.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
12 atomic answers

Sources: no-human:srch-team, no-human:site, no-human:config, no-human:readme, no-human:security, no-human:backends

Verification and delivery

Sourced partial

Plan, diff, reviewer checklist, test results panel, tamper and repro-gate verdicts, event log, PR body with evidence sections and optional UI evidence (screenshots) per repo config; retained per task; no cross-task gallery.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • See atomic answers for the unmet or unknown parts.
13 atomic answers

Sources: no-human:readme, no-human:config, no-human:verification, no-human:cli, no-human:srch-spec, no-human:api, no-human:srch-ship

Agent cross-checked partial

Required by default: tests and lint (your commands), wiring and type evidence as inputs, tamper guard before review, reproduction gate (Python bug fixes by default), independent adversarial review, merge-ready policy and change-scoped tests at landing; CI backends (GitLab CI, GitHub Actions, Jenkins, CircleCI) optionally gate; failed checks block approval and landing. No persistent-spec checks.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
11 atomic answers

Sources: no-human:verification, no-human:readme, no-human:config, no-human:adapters, no-human:srch-spec

Agent cross-checked partial

Integrated: per-task worktrees and branches, deterministic VCS operations under a distinct identity, lint-gated commits, PR/MR opening on GitHub or GitLab, reviewer checklist comment, CI response through backends, squash landing and merge-stack for stacked PRs; supersession warnings.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
9 atomic answers
  • Branches [supported] Per-task branches. Sources: no-human:security.
  • Worktrees [supported] Worktree per task. Sources: no-human:config.
  • Commits [supported] Deterministic commits under a distinct identity. Sources: no-human:security.
  • Pull requests [supported] PRs and MRs open on your host with a structured body. Sources: no-human:readme.
  • Comments [supported] Reviewer checklist comment and post-review-comments endpoint. Sources: no-human:config, no-human:api.
  • Ci response [supported] CI backends trigger and poll; ci_fix tag on tasks. Sources: no-human:adapters, no-human:readme.
  • Rebase [partial] Squash landing; rebase handled in the loop. Sources: no-human:config.
  • Conflicts [partial] Merge-stack plan reports conflicts; resolution by the coder. Sources: no-human:cli.
  • Product state [supported] Task rows carry PR and status. Sources: no-human:readme.

Sources: no-human:security, no-human:readme, no-human:cli, no-human:config, no-human:api, no-human:adapters

Sourced partial

The human approves with nh approve or the board: approval squashes the branch into one commit, runs change-scoped tests, pushes the default branch and closes the PR (can be disabled to leave the merge to you); the agent never merges; merge-stack run calls gh pr merge on your command; no deploy or release.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • See atomic answers for the unmet or unknown parts.
6 atomic answers

Sources: no-human:security, no-human:config, no-human:cli, no-human:readme, no-human:srch-spec, no-human:srch-cloud, no-human:srch-ship

Sourced partial

Task rows link PR, status and verdicts; shipped endpoint records delivery; attempt records bind the tested tree; PR outcomes can be refreshed; superseded tasks warn on approve; no rollback or revert feature; approval records can be restored.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • See atomic answers for the unmet or unknown parts.
9 atomic answers

Sources: no-human:api, no-human:cli, no-human:config, no-human:readme, no-human:adapters, no-human:srch-cloud, no-human:srch-spec, no-human:srch-ship

Agent cross-checked partial

Review PR lane with checklists, nh status and review commands, merge-stack plan and run for dependent PRs, overnight drain to open PRs for review in the morning; no risk or size filters beyond review routing; stale approvals are re-tested at landing.

Scope
Surfaces: Web board on 127.0.0.1:8420, nh CLI and shell · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
12 atomic answers
  • Review queue [supported] Review PR lane and nh status. Sources: no-human:readme.
  • Summaries [supported] Plan, checklist and PR body summaries. Sources: no-human:readme.
  • Grouping [partial] Lanes group by state; stacks group PRs. Sources: no-human:cli.
  • Risk size filters [partial] Review routing treats risk-flagged diffs separately; no user filter. Sources: no-human:config.
  • Findings [supported] Retained checklists per attempt. Sources: no-human:api.
  • Artifacts [partial] Plan, test results and diff. Sources: no-human:readme.
  • Request changes [supported] Reject and send back. Sources: no-human:cli.
  • Exact revision approval [supported] Tested-tree comparison at landing. Sources: no-human:config.
  • Dependency queues [supported] merge-stack link, plan and run. Sources: no-human:cli.
  • Next actions [supported] Review and approve prompts, NOT RUN labels, Needs answer. Sources: no-human:readme.
  • Stale approval invalidation [supported] Tests re-run on a diverging tree. Sources: no-human:config.
  • Check deduplication [partial] Change-scoped tests; no cross-task dedupe. Sources: no-human:config.

Sources: no-human:readme, no-human:quickstart, no-human:cli, no-human:config, no-human:api

Ownership, privacy and economics

Agent cross-checked partial

MIT License for the whole repository (CLI, server, web board, desktop shell, plugin and Action); one public repository; official builds stamp a hosted registration endpoint for the onboarding email only. Pinned v0.2.4.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
6 atomic answers
  • Client license [supported] MIT for web board and desktop shell. Sources: no-human:license.
  • Server license [supported] MIT for the Python server and CLI. Sources: no-human:license, no-human:pyproject.
  • Hosted extensions [partial] Hosted registration intake exists for onboarding emails and Max cloud is planned; their code is not in the repository. Sources: no-human:email, no-human:site.
  • Source visibility [supported] Public repository no-human-ai/no_human. Sources: no-human:repoapi.
  • Source revision [supported] v0.2.4 at commit a00adde. Sources: no-human:release.
  • Hosted parity [unknown] Parity with Max cloud cannot be established; it is unreleased. Sources: no-human:site.

Sources: no-human:license, no-human:pyproject, no-human:repoapi, no-human:release, no-human:email, no-human:site

Sourced partial

Local-first: SQLite state and ~/.no_human config, no required vendor service, MCP and Action standalone; exports are the API and the git PRs; official builds forward only the onboarding email. Desktop updates via GitHub Releases; wheel on PyPI.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • See atomic answers for the unmet or unknown parts.
8 atomic answers
  • Self hosting [supported] Runs entirely on user hardware. Sources: no-human:site.
  • Vendor dependencies [partial] Onboarding email endpoint in official builds, PostHog telemetry (opt-out), a desktop update check against GitHub Releases that no setting disables, and model providers; none is required to run the server. Sources: no-human:email, no-human:telemetry, no-human:updater.
  • Export [partial] API and PRs; no bulk export. Sources: no-human:api.
  • Import [partial] Tracker and issue import. Sources: no-human:adapters.
  • Formats [supported] SQLite, YAML and git. Sources: no-human:config.
  • Cancellation [unsupported] No account to cancel. Sources: no-human:site.
  • Account independence [supported] Fully usable without a vendor account. Sources: no-human:site.
  • History portability [partial] History lives in the local database; PRs live on the git host. Sources: no-human:config.

Sources: no-human:distribution, no-human:config, no-human:site, no-human:email, no-human:telemetry, no-human:api, no-human:adapters, no-human:updater

Sourced partial

Code and prompts go to the chosen model providers and your git host; state stays in local SQLite; credentials in a 0600 .env; telemetry is on by default through two channels: server-side usage events with a closed documented allowlist, and browser-side PostHog autocapture, dead clicks, heatmaps, performance, exceptions and masked session replay of the app's own interface (a masked-surface guarantee the docs say is not a claim that replay cannot capture content); the one opt-out is telemetry.enabled false in config.yaml, with no onboarding prompt or Settings toggle; official builds forward the onboarding email to a hosted intake; the coder can send anything its commands send.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
Not separately cross-checked
  • See atomic answers for the unmet or unknown parts.
15 atomic answers
  • Code data [supported] Local worktrees; sent to the provider and git host. Sources: no-human:security.
  • Prompts [partial] Server-side events carry no prompts; browser session replay records the app's interface with operator-content blocks masked by hand-applied ph-no-capture, which the docs describe as a masked-surface guarantee, not proof it cannot capture content. Sources: no-human:telemetry, no-human:telem-web, no-human:telem-doc.
  • Credentials [supported] Stored in ~/.no_human/.env mode 0600, never in repo or config. Sources: no-human:security.
  • Logs [supported] Local. Sources: no-human:config.
  • Artifacts [supported] Local database and PRs. Sources: no-human:config.
  • Retention [supported] Ledger compaction after 90 days; memory archive after 45 days. Sources: no-human:config.
  • Deletion [partial] Delete learnings; task deletion not documented. Sources: no-human:api.
  • Training [unknown] Training use belongs to the model providers. Sources: no-human:security.
  • Residency [unknown] Local; provider residency unspecified. Sources: no-human:security.
  • Subprocessors [partial] PostHog and the registration endpoint are named; the model provider is the user's. Sources: no-human:telemetry, no-human:email.
  • Telemetry disclosure [partial] TELEMETRY.md lists every server event and the browser screen_viewed; docs/configuration.md separately describes browser autocapture and session replay and states the nine-event table does not cover them. Sources: no-human:telemetry, no-human:telem-doc.
  • Telemetry defaults [supported] On by default (opt-out). Sources: no-human:config.
  • Telemetry controls [supported] telemetry.enabled false and POST /api/telemetry/consent. Sources: no-human:config, no-human:api.
  • Provider separation [supported] Security doc separates telemetry from agent traffic. Sources: no-human:security.

Sources: no-human:telemetry, no-human:config, no-human:security, no-human:email, no-human:api, no-human:telem-web, no-human:telem-doc

Agent cross-checked partial

Free (Local) edition: $0 forever with no card and unlimited tasks, billed only by the user's model provider; Pro (flat per seat) and Max (cloud) are waitlist-only with prices to be announced; Enterprise is by contact.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free Local; paid tiers waitlisted · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
12 atomic answers
  • Currency [unknown] No price is published, so no currency. Sources: no-human:site.
  • Interval [unknown] Pro is described as flat per-seat subscription; interval not stated. Sources: no-human:site.
  • Seats [partial] Pro is per seat; Local has no seats. Sources: no-human:site.
  • Seat minimum [unknown] Not published. Sources: no-human:site.
  • Workspace fees [unknown] Not published. Sources: no-human:site.
  • Included usage [unsupported] Local includes no model usage; billed by the provider. Sources: no-human:site.
  • Credits [unsupported] No credits. Sources: no-human:site.
  • Trial [unsupported] Local is free forever; paid tiers are waitlisted. Sources: no-human:site.
  • Overages [unknown] Not published. Sources: no-human:site.
  • Taxes [unknown] Not published. Sources: no-human:site.
  • Model cost [supported] Billed by the user's provider, not through no_human. Sources: no-human:site.
  • Compute cost [supported] User's own machine for Local; Max cloud compute pricing unpublished. Sources: no-human:site.

Sources: no-human:site

Agent cross-checked partial

Platform cost is $0 for one, two or five developers on the Local edition (no collaboration features); model costs per task are estimated in-app but no scenario prices are published; Pro and Max prices are unannounced.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
11 atomic answers
  • One person [supported] $0 platform cost. Sources: no-human:site.
  • Two people [partial] $0 platform cost; each runs a separate local install without sharing. Sources: no-human:site.
  • Five people [partial] $0 platform cost; Pro team brain is unpriced. Sources: no-human:site.
  • Task assumptions [unknown] No scenarios published; none invented. Sources: no-human:site.
  • Concurrency [unknown] None published. Sources: no-human:site.
  • Tokens [unknown] Estimated per PR in demo screenshots only. Sources: no-human:readme.
  • Compute hours [unknown] Local hardware. Sources: no-human:site.
  • Fixed cost [supported] None for Local. Sources: no-human:site.
  • Variable cost [supported] Model tokens through the user's provider. Sources: no-human:site.
  • Included cost [unsupported] None. Sources: no-human:site.
  • Unknown cost [unknown] Pro and Max pricing unannounced. Sources: no-human:site.

Sources: no-human:site, no-human:readme

Agent cross-checked partial

Generally available free local edition (v0.2.4 on 2026-09-17, six releases since 2026-09-07); pre-1.0; macOS, Linux and Windows builds with Windows and Linux items marked unverified; waitlist-only paid tiers; Discord and GitHub issues; SECURITY.md; no response commitments or status page.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
8 atomic answers

Sources: no-human:release, no-human:site, no-human:changelog, no-human:windows, no-human:readme, no-human:security, no-human:repoapi, no-human:api

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

Free forever Local edition with no card; user pays model provider usage and own hardware; BYO Claude or ChatGPT subscriptions work; remote compute, phone and team collaboration are not in the free edition (paid tiers waitlisted).

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
10 atomic answers
  • Ongoing free [supported] Free (Local) forever. Sources: no-human:site.
  • Trial [unsupported] No separate trial. Sources: no-human:site.
  • Credits trial [unsupported] No credits. Sources: no-human:site.
  • Self host cost [supported] Local hardware and model provider spend. Sources: no-human:site.
  • Paid only [unsupported] Not paid-only. Sources: no-human:site.
  • Early access [partial] Pro and Max are gated by waitlist. Sources: no-human:site.
  • Free scenarios [partial] BYO subscriptions, issue intake and review work free; remote compute, mobile and team collaboration do not exist in Local. Sources: no-human:site, no-human:security.
  • Card required [unsupported] No card. Sources: no-human:site.
  • Usage caps [unsupported] Unlimited tasks, limited by model spend. Sources: no-human:site.
  • Paid evaluation [partial] A Claude or OpenAI credential is needed to evaluate. Sources: no-human:security.

Sources: no-human:site, no-human:security

Agent cross-checked partial

Partially specified: Local is free with stated terms; Pro is flat per seat and Max cloud have no price yet; Enterprise is quote-only; model costs pass through unmarked.

Scope
Surfaces: Web board on 127.0.0.1:8420 · Version: v0.2.4 (commit a00adde, released 2026-09-17) · Plan: Free local edition (MIT) · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-16 (6 days old)
Agent cross-check
2026-11-17
  • See atomic answers for the unmet or unknown parts.
9 atomic answers
  • Units [partial] Per seat for Pro; none for Local. Sources: no-human:site.
  • Included limits [partial] Local unlimited; Pro and Max limits unannounced. Sources: no-human:site.
  • Overages [unknown] Not published. Sources: no-human:site.
  • Compute markup [unknown] Max cloud compute pricing is unannounced. Sources: no-human:site.
  • Model markup [supported] Inference is billed by the user's provider, not through no_human. Sources: no-human:site.
  • Minimum commitment [unknown] Not published. Sources: no-human:site.
  • Cancellation [unknown] Not published. Sources: no-human:site.
  • Sales only unknowns [supported] Enterprise is by contact; Pro and Max are waitlist-only. Sources: no-human:site.
  • Transparency classification [supported] Partially specified: Local terms stated; paid tiers have named missing prices. Sources: no-human:site.

Sources: no-human:site

Sources

no-human:site

getnohuman.com

Free (Local) forever with no card, billed by the user's own model provider; Pro (team brain, per seat) and Max (cloud) are waitlist-only with prices to be announced; Enterprise adds SSO, SCIM, audit trail and budget policy by contact; desktop for macOS, Windows, Linux; no compliance certification claims.

Kind
documented
Locator
pricing section, platforms, waitlist tiers
Source date
Not stated
Retrieved
2026-11-16
no-human:release

no_human v0.2.4 release

Published 2026-09-17: macOS arm64 DMG and ZIP, Linux amd64 .deb and x86_64 AppImage, Windows UNSIGNED .exe and .zip, Python wheel, SHA-256 files.

Kind
documented
Locator
release notes and assets
Source date
Not stated
Retrieved
2026-11-16
no-human:readme

no_human README

Local factory from ticket to reviewed PR: plan, coder, independent reviewer, tamper guard, reproduction gate, honest stop; nh CLI, web board, desktop app; Jira, Linear, monday.com, GitHub, GitLab intake; Slack and Teams notices; GitHub Action reviewer gate.

Kind
documented
Locator
headline; the gates; Install; Product highlights; Run one task; Integrations; GitHub Action
Source date
Not stated
Retrieved
2026-11-16
no-human:config

Configuration reference

Defaults: subscription auth, claude-sonnet-5 implementer, claude-opus-4-8 reviewer, 3 attempts, 500 turns per attempt, concurrency off (2 workers when on), per-task worktrees, task priority, opt-out PostHog telemetry on by default.

Kind
documented
Locator
Settings at a glance; Isolation; Timeouts; Dispatch priority; Usage insights
Source date
Not stated
Retrieved
2026-11-16
no-human:windows

Windows app

Windows build and divergences from macOS with verified and unverified markers.

Kind
documented
Locator
status honesty markers
Source date
Not stated
Retrieved
2026-11-16
no-human:linux

Linux app

Linux .deb and AppImage build, divergences and unverified items.

Kind
documented
Locator
.deb and AppImage
Source date
Not stated
Retrieved
2026-11-16
no-human:adapters

Adapters

Intake (Jira, Linear, monday, GitHub, GitLab issues), VCS on GitHub or GitLab, CI via GitLab CI, GitHub Actions, Jenkins, CircleCI.

Kind
documented
Locator
Intake, context, VCS, CI backends
Source date
Not stated
Retrieved
2026-11-16
no-human:cli

nh CLI

Click-based nh CLI; approve lands the PR; merge-stack link/plan/run; mcp-serve stdio bridge.

Kind
source-inspected
Locator
click groups: task, repo, auth, rules, memories, playbook, merge-stack, skills, ci-gate; commands shell, init, status, review, diff, approve, reject, reply, wake, watch, mcp-serve
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human/cli/commands.py
no-human:api

Board API

Local HTTP API behind the board with task, approval, event stream, metrics and configuration routes.

Kind
source-inspected
Locator
/api/tasks, approve, send-back, pause, resume, cancel, events, metrics, config, integrations, telemetry/consent
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human/api/app.py
no-human:boundary

Loopback boundary

The board API is unauthenticated and protected by loopback Host and Origin checks against DNS rebinding and cross-site writes.

Kind
source-inspected
Locator
Host and Origin checks
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human/api/local_boundary.py
no-human:plugin

Claude Code plugin

Claude Code plugin offering task_add, task_status and nh gate without a server.

Kind
source-inspected
Locator
description, version 0.2.4
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
plugins/no-human/.claude-plugin/plugin.json
no-human:srch-cloud

Bounded search: vendor cloud and remote execution

No cloud runner or remote worker in the release; only the onboarding email intake is hosted; Max cloud is waitlist-only.

Kind
source-inspected
Locator
grep -Eni hosted|vendor cloud|remote worker|ssh|vps over src/no_human and docs
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human
no-human:srch-mobile

Bounded search: mobile and editor clients

No iOS, Android or editor extension; only Electron desktop, web board and the Claude Code plugin.

Kind
source-inspected
Locator
ls desktop web; grep -Eni ios app|android|vscode extension over desktop, web, plugins
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
desktop
no-human:backends

Coding backends

Three coder backends: claude (Agent SDK to claude CLI), codex (codex exec), local (claude CLI at your own server); planner, supervisor and intake stay on Claude; reviewer defaults to Claude and can be set per role.

Kind
documented
Locator
claude, codex, local table; Switching
Source date
Not stated
Retrieved
2026-11-16
no-human:claude

Claude backend

Coder session through the Claude Agent SDK with project settings and bypass permissions by default.

Kind
source-inspected
Locator
permission_mode bypassPermissions default; setting_sources project
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human/agent/claude_backend.py
no-human:security

Security model

Subscription or API-key billing path scrubbing; agent never merges (approve is human); coder runs bypassPermissions by default with acceptEdits option; network egress depends on agent commands.

Kind
documented
Locator
1 One billing path; 2 The agent never merges; 7 What leaves your machine
Source date
Not stated
Retrieved
2026-11-16
no-human:legal

Integrations legal position

Recorded legal and compliance position per third-party integration, including unresolved points.

Kind
documented
Locator
Codex auth and sourcing
Source date
Not stated
Retrieved
2026-11-16
no-human:email

Onboarding email registration

Official builds post the setup-wizard email to the hosted registration intake; self-compiled builds have no endpoint.

Kind
source-inspected
Locator
official builds forward email to a stamped endpoint
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human/email/register.py
no-human:quickstart

Quickstart

Five-minute path: install prerequisites, nh init, nh task add from title or issue URL, run in foreground, review and approve, parallel overnight drain with --until-empty.

Kind
documented
Locator
Install, nh init, add first task, review and approve, overnight drain
Source date
Not stated
Retrieved
2026-11-16
no-human:srch-spec

Bounded search: living specifications

No persistent product spec; acceptance criteria are per task plans and learnings are memory rules.

Kind
source-inspected
Locator
grep -Eni living spec|product spec|requirements doc|drift over docs and src
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
docs
no-human:changelog

Changelog

Shipped changes including onboarding email intake, review gate outside a server, wiring evidence and --follows.

Kind
documented
Locator
[0.2.4] - 2026-09-17
Source date
Not stated
Retrieved
2026-11-16
no-human:mcp-server

MCP registry manifest

MCP server manifest for the stdio bridge exposing task_add and task_status.

Kind
source-inspected
Locator
packages: pypi no-human, uvx mcp-serve, stdio
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
server.json
no-human:action

GitHub Action

Composite action that runs the reviewer and tamper guard as a PR check with a pass/fail checklist comment.

Kind
source-inspected
Locator
inputs credential, github_token
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
action.yml
no-human:verification

Verification

Plan, implement, review loop bounded by max attempts; reviewer is a fresh-context second model; tamper guard counts deleted tests before review; reproduction gate; merge-ready policy; limits section lists what it does not do.

Kind
documented
Locator
The pipeline; adversarial reviewer; tamper guard; reproduction gate; Merge-ready policy; Limits
Source date
Not stated
Retrieved
2026-11-16
no-human:distribution

Distribution

macOS DMG with frozen nh server via GitHub Releases and electron-updater; wheel on PyPI.

Kind
documented
Locator
artifacts and update path
Source date
Not stated
Retrieved
2026-11-16
no-human:desktop

Electron desktop shell

Electron shell attaches to a local nh server or spawns the frozen one; hide-on-close tray on macOS.

Kind
documented
Locator
attach or spawn local nh server
Source date
Not stated
Retrieved
2026-11-16
no-human:blockers

Blockers and wake conditions

Blocker taxonomy with wake conditions (for example DEPENDENCY_WAIT), escalation, nh reply and wake watcher.

Kind
documented
Locator
taxonomy table
Source date
Not stated
Retrieved
2026-11-16
no-human:srch-team

Bounded search: users, roles, SSO and presence

No multi-user accounts, roles, SSO or presence in the local product; SSO and SCIM are listed only for the waitlisted Enterprise tier.

Kind
source-inspected
Locator
grep -Eni saml|oidc|sso|rbac|organization|presence over src/no_human and docs
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human
no-human:telemetry

Telemetry contract

Nine event kinds with closed props sent to PostHog; documented opt-out via telemetry.enabled; no task ids, titles, repo names or paths.

Kind
documented
Locator
complete event list; closed value enums
Source date
Not stated
Retrieved
2026-11-16
no-human:srch-cost

Bounded search: cost and budget

Per-task token budgets, a usage ledger, per-task and window cost estimates and a Stats page exist; no billed-amount reconciliation.

Kind
source-inspected
Locator
grep -Eni budget|usage_ledger|cost over src/no_human and docs/COST_LEVERS.md
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human
no-human:sched-cpu

Scheduler pool sizing

The pool width is clamped to a CPU-derived ceiling (cpu_count // 3, minimum 2) when the server starts, and each task's pytest-xdist auto worker count is bounded to cpu // max_workers; Settings reports cpu_count and hardware_ceiling. No memory limit or live load check was found in these modules.

Kind
source-inspected
Locator
pool_width_ceiling, clamp_pool_width, bounded_xdist_workers; api/app.py _workers_payload
Source date
Not stated
Retrieved
2026-11-17
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human/core/scheduler.py
no-human:web-resp

Phone breakpoint in the web board

The web board has a phone layout keyed to a 640px media query shared between JavaScript and styles.css (pinned by useIsPhone.test.mjs); the board API stays unauthenticated and loopback-checked.

Kind
source-inspected
Locator
PHONE_QUERY (max-width: 640px), readIsPhone, subscribeIsPhone; styles.css @media rules
Source date
Not stated
Retrieved
2026-11-17
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
web/src/useIsPhone.js
no-human:web-kbd

Keyboard handling in the board

Task rows and cards open the task drawer with Enter or Space, dialogs trap Tab focus and Escape closes slide-overs; the UI audit documents keyboard fixes. No list of keyboard shortcuts or command palette was found.

Kind
source-inspected
Locator
onKeyDown on task rows (Enter and Space); docs/UI_AUDIT.md B2 and M13 rows
Source date
Not stated
Retrieved
2026-11-17
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
web/src/TaskTable.jsx
no-human:srch-ship

Bounded search: release, deploy, rollback, revert and delivery evidence

No release, deploy, rollback or revert command, endpoint or gate found. Matches are classifier vocabulary lists, commit-guard and scheduler comments about transaction rollback and reverted status writes, and a 'no automatic rollback' note on nh doctor --fix-walks. No live app preview or evidence gallery exists: 'preview' matches are text result previews of tool calls in the activity log, and 'recording' matches are the optional product telemetry's masked session replay, not delivery evidence.

Kind
source-inspected
Locator
grep -rniE 'gh release|create_release|git tag|deploy|rollback|revert|gallery|preview|recording' over src/no_human (Python) and web/src, plus the nh command list in cli/commands.py
Source date
Not stated
Retrieved
2026-11-17
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
src/no_human
no-human:repoapi

GitHub repository metadata

322 stars, MIT, default branch main, homepage getnohuman.com, pushed 2026-10-09, not archived.

Kind
documented
Locator
stargazers_count, license, default_branch, pushed_at
Source date
Not stated
Retrieved
2026-11-16
no-human:license

MIT License

MIT License for the repository.

Kind
source-inspected
Locator
header
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
LICENSE
no-human:pyproject

Python package manifest

Python package no-human with nh and no-human entry points; MIT.

Kind
source-inspected
Locator
project.scripts nh, license
Source date
Not stated
Retrieved
2026-11-16
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
pyproject.toml
no-human:updater

Security model: outbound traffic

The desktop app checks GitHub Releases at startup once a day without downloading; neither NH_NO_UPDATE_CHECK nor updates.enabled reaches that path, so the only way to stop it is not to run the desktop app (documented as a defect).

Kind
documented
Locator
One GET to pypi.org per day; The desktop app checks GitHub Releases at startup
Source date
Not stated
Retrieved
2026-11-17
no-human:telem-web

Browser telemetry and session replay

With telemetry.enabled true (the default) the browser board loads PostHog with autocapture, pageview, dead-click, heatmap, performance and exception capture and masked session replay of the app's own interface; inputs are masked and operator-content elements carry a hand-applied ph-no-capture block. config.py states the onboarding consent step and Settings pane were removed and config.yaml telemetry.enabled false is the one opt-out.

Kind
source-inspected
Locator
file header comment: ALL CHANNELS ON, MASKED REPLAY; config.py telemetry block and TELEMETRY_CONSENT_QUESTION
Source date
Not stated
Retrieved
2026-11-17
Commit
a00adde993bcf96a12b41b13b2b54c69f9feed92
Path
web/src/telemetry.js
no-human:telem-doc

Usage insights: session replay, honestly stated

The nine-event table covers only what the app sends via posthog.capture. Autocapture, dead clicks, heatmaps, web vitals and exceptions are collected alongside, and session replay is a masked-surface guarantee, not a claim that replay cannot capture content; it can capture pixels of anything not on the masked list. docs/security.md adds that the desktop update check cannot be disabled by NH_NO_UPDATE_CHECK or updates.enabled.

Kind
documented
Locator
Usage insights section: Session replay, honestly stated; docs/security.md Usage telemetry bullet
Source date
Not stated
Retrieved
2026-11-17

Comparisons with no_human

Compare no_human with any other product on adecomparison.com.