---
schema_version: 7
rubric_version: "0.3"
canonical_url: "https://podium.do/compare/agents/open-session-vs-podium/"
data_url: "https://podium.do/compare/agents/open-session-vs-podium/data.json"
generated_at: 2026-11-22
last_checked_at: 2026-11-16
last_cross_checked_at: 2026-11-21
oldest_checked_at: 2026-11-06
publisher: "Podium"
---

# Open Session vs Podium

> Podium publishes this catalog and sells an agent development environment. Podium chooses the products, criteria, sources and wording, so treat these pages as vendor-authored research. Check important claims against the linked primary sources. Sourced findings follow the same evidence rules for Podium and its competitors. Facts labeled Podium team research come from Podium's own team and have no linked source. None of this removes the conflict of interest.

> Based on data from adecomparison.com by Podium (https://adecomparison.com; source repository https://github.com/madeinorbit/ade-comparison, snapshot 4322f0c of 2026-11-22), used under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Source links and check dates are kept. Podium arranges the findings into pairs, applies its publication checks, and added its own research where marked "Podium team research". Data license terms: https://github.com/madeinorbit/ade-comparison/blob/4322f0c035f303791413639d1462a138443d8c1e/DATA-LICENSE.md

48 criteria sourced for both products; 35 criteria also agent cross-checked for both. 50 criteria with a sourced finding for at least one product. "Sourced" findings passed publication validation. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. Humans approve the rubric, templates and prototype; they do not review every finding. It does not declare a winner. A missing sourced finding is not evidence that a capability is absent.

Each row gives the finding's status, support, check date and answer. Scope, limitations, atomic answers and sources for every finding are in each product's document, under the criterion ID. Judgment rules are in the rubric.

- Open Session source checks: 2026-11-16. Details: https://podium.do/compare/agents/products/open-session/index.md
- Podium source checks: 2026-11-06. Details: https://podium.do/compare/agents/products/podium/index.md
- Rubric: https://podium.do/compare/agents/rubric/index.md
- Canonical HTML: https://podium.do/compare/agents/open-session-vs-podium/
- Machine-readable JSON: https://podium.do/compare/agents/open-session-vs-podium/data.json
- Methodology: https://podium.do/compare/agents/methodology/

## Access and agent choice

### ACC-01: Client access

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Self-hosted web UI and installed PWA (iOS push needs the installed PWA over HTTPS), macOS Electron shell, native SwiftUI app for iOS 26 and macOS 26 (TestFlight/Xcode), Chrome side-panel extension and the opensession admin CLI; no Android or Windows/Linux desktop client.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium ships desktop, CLI and browser clients, including phone-browser control. The native iPhone app is private beta; the complete download offering contains no native Android app.

### ACC-02: Agent and model choice

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. One embedded harness: the Pi engine runs every model turn in-process, with Anthropic, OpenAI/ChatGPT, xAI (SuperGrok) and OpenAI-compatible providers; no launching of other coding-agent CLIs as harnesses.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium launches the native Claude Code, Codex, Grok, OpenCode, Cursor and Pi CLIs in persistent terminals on machines you control. The 0.2.0 release calls Pi fully supported. Models come from each harness catalog, and capabilities differ per harness: Pi declares no quota, handoff or hooks. Mixed-harness operation was not exercised.

### ACC-03: Subscriptions, API keys and vendor credits

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Bring-your-own Claude subscriptions (setup tokens), ChatGPT sign-ins, SuperGrok sign-ins, OpenAI and other provider API keys, and any OpenAI-compatible endpoint; pooled with per-person assignment and automatic rotation. No vendor credits because there is no hosted service.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium supports native coding-agent logins and managed provider credentials. Claude subscriptions (via native login or a managed setup-token) and local ChatGPT/Codex login are supported paths, alongside Anthropic and OpenAI API keys. Docs list billing and hosted metering as not implemented product claims.

### ACC-04: Onboarding and project prerequisites

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. One-line install.sh to a running per-user service, then add a model account, pick a repository and prompt; scratch sessions need no repo, a server-only repository needs no remote, GitHub is via an App. No managed cloud; BYO host install is first class (installer flags, EC2 guide).
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Docs describe a first-run flow (install, podium, register a Git repository, confirm a detected logged-in harness) and a headless VPS installer with machine joining. Setup time and failure rate were not measured, and no self-serve managed cloud setup is documented. The current README and installation guide use podium.do/download and podium.do/install.sh as the canonical stable entrypoints.

### ACC-05: Programmable access

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Admin CLI, a Bearer/cookie-authenticated REST and WebSocket surface used by the clients, inbound webhooks and an MCP surface only for sessions the server starts; no published API reference, SDK or externally exposed MCP server.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The podium CLI covers issue create, show, update, claim, dependencies, artifacts, session send/status/read/stop and review actions, and the server exposes the same issue commands as a bearer-token MCP tool endpoint. No documented public HTTP API, SDK or webhooks were found.

### ACC-06: External tools and extensions

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. MCP client with stdio and HTTP/OAuth servers, per-user allowedUsers scoping, MCP feeds as projects, skills (SKILL.md), recipes and a data-only package format; Pi's own plugins/extensions stay off.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Podium gives agents its own issue tools over CLI and MCP, and agent profiles import and export Claude Code agent files. No Podium documentation for user-configured MCP clients, plugins or custom tools was found.

### ACC-07: Client implementation

- **Open Session**: Agent cross-checked (agent-cross-checked); support: supported. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Web UI (React, served by Bun server), Electron 43.2.0 macOS shell around the web UI, native SwiftUI app (iOS/macOS), Chrome MV3 extension; the shell renders the server frontend.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Desktop releases use a Tauri 2 shell that serves the Podium web UI; mobile source uses Expo and React Native. A native iPhone release is described as private beta.

## Planning and context

### PLAN-01: Intake and external tracker relationship

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Sessions start from the web UI prompt, Slack mentions, GitHub issue labels/Issues page, Linear agent assignments, Plain tickets, feeds from any MCP list tool, automations and Chrome page context; external trackers stay authoritative.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium issue records are native and authoritative with stable references, CLI creation and editing, and agent-driven filing from conversation. The in-product assistant has Linear search, create and move tools when a key is configured, but no import or two-way tracker sync was found.

### PLAN-02: Durable task plans

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Agents keep todos and a coordinator-summary.md asset; Linear has plan versus implement paths; no persistent plan editor with acceptance criteria or revision history.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Issue brief, acceptance criteria, state paragraph and todos persist on the durable issue record. Release 0.3.0 removed the separate design and notes fields and appended their text to the brief. On the human issue page the title, description and acceptance are editable and the brief is read-only; agents edit the brief and other fields through issue commands.

### PLAN-03: Hierarchy, dependencies and evolving scope

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Workspaces group sessions; a coordinator spawns child threads (spawn depth capped) shown by state; goals pursue one session over days; no epics, blockers or enforced dependencies.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium supports persistent parent and child issues, phases and typed dependency links, including reparenting an existing issue without replacing its identity. Since 0.3.0 issue types are task, phase and decision: epic and other kinds are retired, and any issue with children acts as a parent. Dependency types are fixed to blocked-by, related, discovered-from, supersedes and duplicates. Cycles are refused and docs list an open blocker as a reason an issue cannot start. No mandatory workflow preset applies in the baseline.

### PLAN-04: Shared context and memory

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. AGENTS.md and skills from the checkout, git-backed memory repositories (team, user, channel) with daily consolidation, session assets, per-session memory and search over history; repo lifecycle files provision workspaces.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. v0.3.0 routes Podium issue instructions and relay environment through terminal and engine session launch. Claude stream sessions use appended instructions and boundary callbacks; Codex server sessions use developer instructions, Grok ACP uses rules, and OpenCode uses the prompt system field. Claude and Codex boundary hooks can re-prime after compaction. Transcript mirroring is on by default; full-text indexing needs the command-palette flag, which defaults off. Agent profiles can carry markdown instructions. Curated memory, skills and memory correction or deletion controls remain unestablished. No instruction-delivery or compaction scenario was run.

### PLAN-05: Architecture and API awareness

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Agents use grep/find/read tools in worktrees, web_search/fetch_url tools, MCP feeds and history search; images and video attach to prompts; no vector index of the repository found.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Not established. Podium mirrors daemon transcripts by default, keeps a full-text index only when the command-palette flag is on, and stores session attachments. No repository code search, architecture awareness or API retrieval feature was found.

### PLAN-06: Native issue management and idea backlog

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Workspaces and sessions are the native work items, with lanes (needs input, in progress, ready to merge, backlog), drafts, snooze and a Desk todo list; GitHub issues are listed but not authored natively. No epics, labels or priorities on sessions.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium exposes native issue creation with an optional start flag, separate dispatch, editing, comments, labels, assignment, search, board filters, archive, sibling ordering and an issue tree. Issue records have their own identity separate from sessions and stages are durable. The idea-to-mission scenario was not run. v0.3.0 refuses an agent close or done update while issue sessions are computing unless --confirm-interrupt is supplied; guidance says to request review and close only on user instruction.

### PLAN-07: Agent-native issue operations

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Agents can list, read, create, cancel, message and review sessions through opensession-sessions tools with creator attribution; no agent-writable issue records with dependencies or claims.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. CLI and MCP address the same canonical issue records for reads, creation, edits, claims, state, dependencies and artifacts. Relayed agents have worker capability scoped to their issue subtree, with --outside-scope confirmation for other existing issues. attachSession is not subtree-gated, but direct rehoming from a real issue is refused and an agent attach naming a Proposed target is refused. That does not make every Proposed subtree inert: operator attachment or spawn-time cwd binding can leave a session attached to a Proposed issue; newSubissue without targetId then bypasses the proposed-parent guard, creates a human-audience backlog child and attaches the existing session. This path remains at v0.3.0 source and was not exercised live. Concurrent-edit handling remains unknown.

### PLAN-08: Living product specifications

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No living product specification: memory repositories, AGENTS.md and reports are persistent documents but are not requirement records linked to tasks with drift detection.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The spec CLI and service (living specs under pspec with stable SP IDs) are in v0.3.0. Specs is an experimental, default-off feature listed on the edge channel: the flag controls the Specs UI, the spec line in CLI help and whether agents are told about the spec CLI. The podium spec command itself is dispatched, and the server specs service has no flag check, so direct CLI use does not need the flag. This agrees with the docs, which call specs not baseline rather than blocked. Not run end to end.

## Coordination and automation

### COORD-01: Parallel work

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Many sessions and workspaces run concurrently as detached run hosts (default admission cap 128 active) with resource-aware admission; the sidebar shows running, needs input, ready to merge and backlog lanes.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Docs and release notes describe many sessions running as independent terminals, one worktree per issue, and several paired machines under one server, with session and issue state visible on the flight deck, board and CLI. Agent-initiated spawns are limited to 10 per target issue per UTC day. Achieved concurrency is unmeasured.

### COORD-02: Ownership and dispatch

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Workspace owner, collaborators and reviewers are human assignments; coordinator threads are assigned to child sessions by spawn_task; no queue-based claims, no enforced exclusive ownership of work items.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Issues carry an assignee, claim sets assignee and in_progress, a coordinator session can be set per issue, sessions have seats, and work can be placed on a chosen machine or agent profile. claim has no exclusivity check of its own, locks are advisory leases and Podium does not serialize agents editing one worktree, so exclusive ownership is not enforced.

### COORD-03: Inspectable delegation and communication

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Product-owned coordinator mode: the agent delegates with spawn_task to child sessions (own model, mode, repo, sandbox), polls with task_status/wait_for, messages with send_to_session, and the UI shows live thread cards; spawn depth is capped. Workflows fan out agents from scripts.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium orchestrates delegation itself: podium agent spawn starts a full child session on an issue with a chosen harness, model, effort or agent profile, mail carries messages, and bounded await reports the child result. Children are real sessions shown as seats on the flight deck. Agent-initiated spawns take a daily budget per issue. A complete delegated task with retained child findings was not run.

### COORD-04: Unattended triggers

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Automations (cron, one-off, external event triggers) and goals (self-paced wakes with a 5-minute floor and optional maxWakes) run on the server independent of clients; webhook automations default to one run at a time with a configurable cap.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The server owns a scheduler for cron and one-time automations that spawn agent sessions, skipping overlaps and not backfilling occurrences more than an hour late. The Automations UI is an edge-visibility feature that defaults off and docs list automations as non-baseline. Agents can subscribe to issue and session events.

### COORD-05: Intervention and attention

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Steer or queue prompts mid-turn, stop/cancel, resume, answer agent questions that park the session in the Needs input lane, web push and Live Activity notifications, and durable waits; terminal and chat parity is not a concept because agents have no terminal.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Chat and native CLI views share a session. v0.3.0 defaults human controller chat to steer and immediately types it into running Claude Code, Codex, Grok and OpenCode TUIs that declare native busy-input queuing; undeclared harnesses wait for a boundary, and compaction waits. Mail and automation keep when-ready delivery. Stop, resume, questions, decision issues and offers remain available. This is inspected implementation, not a cross-harness runtime parity result.

### COORD-06: Fleet and epic management UI

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Sidebar lanes across workspaces (needs input, in progress, ready to merge, backlog), thread cards and a Threads tab grouped by blocked/ready/working/idle/shipped, PR list and a Feed; no dependency graph or epic board.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Release 0.3.0 ships a flight deck showing a whole mission in one view: phases, every task and its state, who works on what, what is blocked and by what, and proposals. Done work stays visible. The CLI prints the same snapshot. The waterfall source is dormant and the Timeline view was deleted, so per-task timeline history is not shown. The shared 12-task UX scenario has not been run.

### COORD-07: Workflow flexibility and orchestration visibility

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No mandatory preset: sessions start from a prompt with optional mode/model, natural-language coordinator and workflow authoring, per-child model choice and live thread cards; coordinator relationships persist in the sidebar.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. A quick task can be an interactive session or an issue; an issue can grow into a mission by gaining children while keeping its identity; no mandatory workflow preset applies in the baseline. Per-agent harness, model and effort are chosen at spawn or through agent profiles, and the deck shows seats. The coordinator-with-two-reviewers scenario was not run.

## Execution and reliability

### RUN-01: Laptop-independent execution

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Always self-hosted: the server runs on your computer or any Linux/macOS/WSL2 host; sessions run on that host, on attached Runners (command delegation), or in per-session Sandboxes from your Daytona, Boat, use.computer, Mac VM or Modal account. No vendor cloud.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The published Podium execution choices are local user machines and a user-owned VPS or paired machine. No vendor-operated agent host is in the complete download offering.

### RUN-02: Workspace and process isolation

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Git worktrees per code workspace (isolated branch and index), read-only ask checkouts, shared-checkout exception, optional per-session VM sandboxes (Daytona/Boat/Mac VM/Modal), command policy and minimal environment; containers started by agents are labelled but not used as the isolation boundary.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium separates issue files with Git branches and worktrees, but its released daemon launches native host processes without product-managed container or VM provisioning.

### RUN-03: Recovery, expiry and continuity

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Session kernel with durable state; Linux system-scope run hosts survive gateway restart and reattach; per-user installs run turns in-process and do not survive restart; sandboxes sleep/wake; transcripts, queues and goals persist across days.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Closing a browser tab does not stop the agent process on a running Podium host. Idle sessions may hibernate under configurable policies; a stopped session keeps its transcript, branch and resume reference. Release 0.2.0 says a failed update rolls back and running sessions keep running through the upgrade; database rollback remains a manual restore. Terminal reattachment goes through the driver adopt contract with process-identity and observation-lease checks. Worker-crash and multi-day behavior were not tested.

### RUN-04: Development environment reliability

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Worktree creation seeds a warm template then runs .agents/setup or depsInstall (bun install by default); repo lifecycle files expose app Portals; sandbox project snapshots; sccache is used; ports via Portals.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Only machine setup is documented: the installer installs missing runtime tools and pairs a host, and the state directory holds server-managed secrets. Dependency caching, services, ports and automatic repair for project environments were not found.

### RUN-05: Limits and failure handling

- **Open Session**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. Setup timeout per repo, default 2-hour wait timeout, goal wake floor and maxWakes, workflow concurrency/call/timeout limits, workflow nested-session token and cost budgets, run-host admission timeout and model-account limit sidelining with fallback; no token or spend cap for ordinary sessions.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium exposes retryable errors, optional auto-continue with backoff, bounded waits and provider quota. Claude stream and hosted headless drivers enforce a supplied turn deadline, with no deadline when timeoutMs is absent. The one-shot headless server runner supplies its budget, default ten minutes. Agent spawns have a daily per-issue budget. Operator-configurable task-wide turn, token and spend caps remain unestablished; quota display is not enforcement.

### RUN-06: Truthful status and operational statistics

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Audit log JSONL, per-request usage by session/day/model, Analytics view (turns, durations, errors, PRs), transcripts with run durations, doctor/status/logs commands; derived session states; no export of usage in documented formats other than database CSV.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Podium offers local logs and crash export, structured session status, issue stats, a usage and analytics sheet with hourly list-price cost, per-task costs and host load panels. The 0.3.0 notes report a vendor benchmark of about 330 MB server memory against about 1.2 GB for an earlier Podium build, and 8 to 52 percent faster start; the method is published in the repository and was not reproduced here. Usage export and cross-reconnect consistency were not established.

### RUN-07: Per-task API and compute cost

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Per-request tokens and list-price cost recorded per session and shown in the composer ($ per session), plus Analytics; subscription usage and reset windows are displayed per account; no per-epic aggregation or budget alerts.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Since 0.2.0 Podium shows what each task costs, on the task header and the usage sheet, with per-session rows and descendant rollups. The 0.3.0 deck adds a mission cost chip. Figures are token estimates at public model list prices, not subscription invoices or provider bills.

### RUN-08: Compute-aware scheduling and verification

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Linux run-host admission checks active host count, MemAvailable and CPU pressure with bounded backoff and a visible timeout; cgroup slices with CPU weights keep control-plane responsive; documented concurrency settings; no shared check reuse.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium reports host memory, load and disk, auto-hibernates idle sessions under pressure, and provides named advisory resource leases. The merge-queue panel was removed; a shipping queue remains behind the Shipping flag. Concurrency limits and bounded test queuing were not established.

## Human collaboration and control

### TEAM-01: Live human collaboration

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Workspaces are shared with collaborators; people can prompt the same session (messages attributed by name), comment on messages, react, and join voice huddles; live presence and typing indicators exist in the web client. Default install has no authentication, so attribution is a self-selected display name unless GitHub sign-in is on.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The issue UI displays owner and visibility read-only and deliberately omits sharing controls. Backend share handlers and a Members settings section with invites and admin or member roles exist; they do not establish a finished human collaboration workflow. Docs say small teams can share an instance but the interface prioritizes one operator.

### TEAM-02: Roles and access boundaries

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Team roster in identity.team and an admin gate for control tools; opt-in GitHub sign-in admits any verified GitHub account that can reach the instance; per-user MCP scoping; no SAML/SCIM SSO or named organization roles.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium defines member/admin instance roles and admin-only membership management. The released client authentication uses password-backed sessions and paired-device tokens without enterprise SSO.

### TEAM-03: Approvals and temporary access

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Interactive runs rely on the human as authority; unattended runs use command policy with deny/allow/require_approval, MCP allowlists and hard-denied tools; money-moving and credential actions need human approval cards; force merge needs the signed-in driver to confirm and is pinned to the head SHA.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Agent-session management requests go through an operator approval broker with approve and deny; the privacy docs say lifecycle commands and automation requests may require operator approval. Harness permission prompts appear as a Permission needed state; credential copying during pairing is a per-grant opt-in. Command-level policy enforcement beyond the harness own modes was not established.

### TEAM-04: Decision and activity history

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Structured audit log (JSONL per day) records run, tool and approval events; sessions record creators and timelines; transcripts persist across users; history lives in local files that an operator can alter, with no stated integrity model.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Issue actions, approval steps, comments and mail are recorded server-side. Issue activity events, including approval steps, are pruned by the server's janitor once they are older than 14 days or fall outside the newest 50,000 rows. That policy does not define all content retention, export or tamper-evident audit guarantees.

### TEAM-05: Review experience and guidance

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Needs review band and review requests, PR review view with split diff, checks and merge action, AI review guide that groups a diff into story-first sections, per-file viewed state, OS review with severity findings and merge-risk; mobile PWA available.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Review is a documented loop: issue stage review, diff and checks, artifacts, offers with merge or send-back buttons, and a Tray of review-ready work. Release 0.3.0 adds quoting text from a reply or review finding into the next message and a full-height reading view with an outline. The board has a key map with a help sheet. Guided-review quality and narrow-screen use were not measured.

### TEAM-06: Colleague takeover and continuity

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Collaborators can open the same workspace, read the full transcript and steer the session while the server keeps running; model/engine can be migrated with a transcript handoff; ownership transfer is not a distinct feature.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The durable issue, session transcript, artifacts and mail persist for any later agent, and a live session can be handed to another machine in an edge feature. Colleague takeover by a second person was not established.

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Per-turn diffs, session assets (files, images, charts, HTML artifacts, reports, databases), screenshots and recordings via Portals/desktop tools and walkthroughs, PR review guide and OS review output; assets persist in the session store.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Artifact commands store immutable server-side copies of issue-linked files, including images, video, HTML and documents, which render in the issue sidebar and offers and stay readable after the worktree is gone. Each task has an artifacts page grouped into screens, documents and reports, with filters and search. Revision linking remains untested.

### SHIP-02: Verification and spec gates

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Checks are repository and GitHub policy: agents may run tests/lint; pr_checks waits wake the session on failure; an optional OS approval gate check run reads CODEOWNERS and OS review; .os-review.json adds secret scan and test-on-base; no spec checks.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. In the experimental Shipping path a configured validation profile runs before landing (default argv bun run test with a 10 minute timeout) and a failed validation holds the order. Lint, type, CI and spec conformance gates and independent review requirements were not found as product-enforced policy.

### SHIP-03: Git and pull request workflow

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Worktrees, commits and branch handling, PR creation via GitHub App or gh, review comments, PR agent responding to review comments in an integration worktree, CI waits, stacked PR support, conflict-refusing force merge; code.storage branches act as reviews.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Issues own branches and worktrees, and issue actions rebase, open a pull request with gh (pr create --fill) and merge, subject to a merge-style setting (ff-only by default, with auto-rebase before merge). Podium does not resolve branch conflicts, and PR review comments and CI response were not established.

### SHIP-04: Merge and deployment authority

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Merge actions use the signed-in person's GitHub token so GitHub decides authority; force-merge is pinned to the head SHA; deploy_self advances the pinned runtime for self-hosting; durable deploys publish apps; no separate release management.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The operator accepts work through offers and runs the merge action under a branch merge-lock; in the experimental Shipping path approval is frozen to an exact head and delivery lands on a local target branch by default. Release and deployment are not product features found in the sources.

### SHIP-05: Completion evidence and rollback

- **Open Session**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. Sessions link to commits (by transcript sha), PRs, CI runs and rollout statuses through GitHub webhooks; delivery lanes show ready to merge and shipped; agent-published internal apps can be rolled back to a retained version, but there is no rollback for repository changes or PRs; approvals can be required on the current head.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Shipping orders record approved base and head SHAs, tested integration SHA, landed ref and validation result in a durable delivery receipt, and stale approvals hold the order. Shipping is experimental. The pr action records a PR URL on the issue. Build and deployment links and rollback were not found.

### SHIP-06: Batch review and high-volume shipping

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Pull requests list and Needs review band across workspaces, merge-risk scoring, AI review guide per PR, review requests, stacked PR view; no batch approval or dependency-aware merge queue.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. The shipping service records revision-specific approval, configured validation and delivery receipts. The Shipping panel is an experimental edge toggle, off by default; the separate Queues panel was removed.

## Ownership, privacy and economics

### OWN-01: Source and license

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. MIT licensed repository (client, server, protocol, native apps and website in one repository); no closed or hosted extension; code published at release tag v0.4.82.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The public repository is licensed Apache 2.0, and the website presents Podium as an open-source agent development environment. Hosted extensions and hosted-service terms are not established.

### OWN-02: Hosting and exit

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Fully self-hosted; no vendor service is required beyond model providers and optional GitHub/Slack/Linear apps and sandbox providers; state is local files and git repositories; no import/export tooling beyond files, memory repos and session databases.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Local desktop and self-hosted installs run on user-controlled machines with a documented state directory. The docs describe stopped full-state backup and automatic pre-migration database-only snapshots retaining three copies. Those snapshots omit artifacts, transcripts, uploads, configuration and secrets; no portable structured export/import contract was established.

### OWN-03: Data handling and telemetry

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Code, prompts, credentials, logs and artifacts stay on the operator's host; prompts go to the chosen model providers; Sandboxes send repository clones to the provider; no first-party telemetry was found in the server code; privacy terms for providers are theirs.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-21. Docs state repositories and native harness credentials stay on machines you control and server state lives in a documented directory. Since 0.2.0 a daily usage report is on by default and can be turned off; crash reports stay opt-in. Usage reports carry an install id, schema version, Podium version, OS, architecture, bucketed install age and machine count, session counts per harness and whether issues were used. Crash reports carry the same install id, versions, OS and architecture, a fixed error type and up to 20 stack frames, each with a Podium source file path, line and function when there is one; error messages and frames outside Podium are dropped. Neither tier sends prompts, transcripts, your code or paths outside the Podium source tree. Model-provider handling is the harness own. Hosted analytics and website analytics are separate paths.

### OWN-04: Price and included usage

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Free: MIT software with no plans, seats, credits or trials; costs are your hosting, model accounts or API usage and optional sandbox provider charges.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. No Podium price is published: podium.do/pricing returns 404 and the docs list billing as not implemented. The software is open source and free to download; model and compute costs are the user's own.

### OWN-05: Scenario cost and controls

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Software cost is zero for one, two or five developers; total cost depends on model subscriptions or API usage and hosting, which this catalog does not price.
- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### OWN-06: Availability and support

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Active pre-1.0 releases (v0.4.80 to v0.4.82 within two days) with binaries and checksums; support through GitHub issues; contributions as written requests; no response commitments or status page.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium is pre-1.0. Stable v0.3.1 (2026-11-06), an update fix, follows v0.3.0 (2026-11-05), v0.2.0 (2026-10-11) and v0.1.0 (2026-08-21), with edge and dev prerelease channels. Windows and Linux desktop are Experimental, the native iPhone app is in private beta and hosted Podium is unconfirmed. Support runs through GitHub issues, Discord and private vulnerability reporting.

### OWN-07: Enterprise assurance

- **Open Session**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### OWN-08: Useful free tier and evaluation access

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Open-source self-hosting is the free path; every shared scenario works free apart from model and hosting costs; no card, caps or sales gate.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium is open-source Apache-2.0 software, and the download page calls it free and open source. Download links for macOS, Linux and Windows redirect to GitHub release assets without a login (observed by HTTP requests; not installed). No Podium charge is documented for self-hosting; agent provider usage is separate. The native iPhone app is private beta and hosted access is unconfirmed.

### OWN-09: Pricing transparency

- **Open Session**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Transparent: the software is free; no units, limits, markup or minimum commitment exist.
- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
