A source-linked comparison across the complete Podium ADE rubric. 48 criteria sourced for both products; 37 criteria also agent cross-checked for both. 51 rows have at least one sourced finding, including 47 with an agent-cross-checked finding. No score or winner is inferred.
Each row shows a finding's verification status, support, check date and answer. Its scope, limitations, atomic answers and sources are on the product's page. 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.
The complete current application repository lists macOS Electron/Tauri shells, web clients, a daemon and CLI. It has no native Windows/Linux desktop shell or iOS/Android app. User-host daemons can use other operating systems, and phone browsers can create, watch and message sessions.
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.
HumanLayer integrates Claude Code, Codex, OpenCode and Pi. The closed schema lists those families and product-specific CodeLayer/Fold paths, with a stricter daemon-launchable subset; other supported terminal sessions can be mirrored. Model gateways do not add another coding harness.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The pricing FAQ explicitly permits existing Claude/Codex subscriptions or API keys. Codex sign-in and custom API configuration are separate paths. The FAQ says HumanLayer has no separate per-token bill; provider and compute charges remain the user’s responsibility. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-10. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The tutorial names macOS, an account, signed-in Claude Code and Git, then creates an inline task/session. It is a documented procedure, with no elapsed-time measurement. The tutorial can clone a GitHub repository; GitHub App issue intake is separately documented. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Sourcedpartial
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.
Product CLI/RPC routes create/list tasks and launch/list sessions; automation run uses a checkout and PAT. Full operation parity and API stability were not tested. Interactive login stores host credentials; automations use expiring personal access tokens and separate provider credentials.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The current repository includes Claude Code, OpenCode and Pi session plugins and built-in HumanLayer/RPI skills. Workspace docs load repository skills/instructions across repos. MCP and Claude settings are inherited according to the launch directory, not universally merged by the ADE. No external-tool call was tested. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Scope and sources
The current pinned monorepo identifies a shared web UI inside macOS Electron and Tauri shells. This does not measure responsiveness or imply native platform widgets.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Users create inline tasks with a name/slug; CLI examples expose persistent task IDs and optional ticket fields. GitHub issues, Linear issues and Jira Cloud tickets can seed HumanLayer tasks. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Guided workflows save research/design/outline/plan artifacts and allow comments and in-place iteration before implementation. Artifacts drive later phases; attributable revision semantics and in-run tests remain unverified. Task artifacts and files sync across sessions/workstations. Restart durability was not tested.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources
/hl:orchestrate breaks work into tasks; workflow checkpoints hold design and outline handoffs; Linear states can follow phases. Native epics, arbitrary hierarchy and blockers were not established.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Repository skills/instructions and shared task documents supply context. Task files are distinct from managed cross-task memory or a living product specification. Saved phase artifacts can be iterated and later artifacts take precedence. This is document correction, not verified stale-memory repair. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
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.
Release notes document image attachments in task intake. The requested architecture-conflict scenario was not run.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
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.
Inline persistent task containers group multiple independent sessions, so a ticket in an external tracker is optional. A native backlog with issue-state semantics is not established. The recent minimalist UI allows task renaming; full native issue-field editing remains unverified. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The bundled orchestration skill calls product CLI task/session routes with the same durable task IDs shown in the application. Shared issue fields, claims and conflict handling are not established. The skill can inspect PRs and manage task artifacts, which provides retained outputs without proving a native blocker/result issue model.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
PRD and TDD artifacts persist in task files with approval checkpoints, version comparison and Slack/public-link review; describe-pr compares the diff with the plan. Cross-release requirement tracking is not established.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
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.
The vendor states local daemons run many sessions in parallel; the bundled skill launches separate task worktrees. No concurrent fixture was observed. The CLI status reference distinguishes running, needs approval, usage-limit waits and failed/lost sessions. Task status is separate and absent in that reference.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-10. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Each task picks its coding agent and host; work queued on an offline host waits for its daemon. Task listing can filter by owning user; exclusive ownership is not established.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
RPI provides named harness-native research/implementation children; a separate bundled orchestration skill launches/inspects product tasks/sessions through the CLI. Harness-specific model/effort rules apply. Recent release notes show nested Claude subagent calls in the stream. No live child-identity fixture was observed. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
User-run CI/cron can invoke automation run with a PAT; schedules, concurrency groups and no-op guards are external workflow configuration. This is documented automation integration, not a hosted scheduler. Automation exits with the session result; inactivity or stop controls the daemon shutdown. No automation was executed.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Sourcedpartial
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.
Release notes document shared-session queue/interrupt, Pi stop/reply and attention notifications. These controls were documented, not exercised in chat and terminal fixtures. Usage-limit waits can resume after reset. Host loss, failed sessions and approval waits have explicit CLI status labels; their observed consistency is unknown. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The UI has attention notifications and a task board, with grouped session history and nested subagents under their parent. Advanced Metrics splits token spend or cost by agent, model, stage, person and mode. No configured runtime fixture was run.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources
Oneshot handles small changes; Freeform omits fixed phases, while RPI/PRD provide guided checkpoints. Users choose agent/model/effort and can amend saved artifacts. A documented skill/CLI route supports orchestration; natural-language discovery and two-reviewer usability were not observed.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Daemons run on the workstation or user-selected VM/server near the code and private services. The user supplies and supervises that compute; a hosted UI does not imply managed agent compute. The pinned README says Cloud runs the same code, its devstack runs the whole stack locally and self-hosting guides are in progress. No self-hosted install was performed. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
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.
Worktree timing allows task-specific branches/worktrees or direct checkout use. Multi-repo tasks create a worktree per repository. No two-change collision fixture was run. The daemon gives agents the file/network access of its OS user. Worktrees separate code and do not prove hostile-code containment.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
Podium separates issue files with Git branches and worktrees, but its released daemon launches native host processes without product-managed container or VM provisioning.
Remote-host sessions and task files are accessible across clients; exact reload/recovery behavior was not tested. After about two minutes of lost host response running/approval sessions fail; a new message is possible when the host returns. Persisted host ID/auth and Claude history are required for a suspended host.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Workspace configuration supplies setup commands and copied local files per repo; remote hosts need checkout, tools and provider credentials. User setup remains required. The current CLI launch reference exposes materialization errors and explicit retries. Some copy/setup errors do not block launching, so automatic repair is not established.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Release notes document Claude usage-limit warnings, waiting states and resumption after reset. Other safe-budget and controlled-failure behavior was not tested.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The status reference documents approval, provider-limit and failed/lost states, and daemon supervisor logs. Advanced Metrics ranks tasks by token spend or cost and splits usage by agent, model, stage, person and mode; metric exports remain unestablished. No induced-fault or performance test was run.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources
Advanced Metrics ranks every task by token spend or cost with six splits including agent and model; per-host Claude limit alerts exist. Provider-billed versus estimated charges and child/epic aggregation are not established.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
External automation workflows can configure concurrency/no-op guards. These are user-owned CI controls, not a verified shared ADE scheduling policy. An opt-in host-load view shows CPU, memory, load and disk. This does not prove resource-aware dispatch or backpressure.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Task sharing gives editors session/file access and reviewers document comments. No two-account permission fixture was run. Release notes describe live shared drafts with named cursors/presence and authors on queued messages; the October beta UI includes multiplayer prompting. Input conflicts were not tested. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Official integration guides reserve connection setup to organization admins; task-level edit and review access are documented. Full role matrix and revocation enforcement were not tested. Editors can add sessions and change task files; reviewers can comment on documents. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
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.
The product launch reference lists default, accept_edits, auto and bypass permission modes. Automation runs explicitly bypass prompts. Safe allow/deny/revoke behavior was not tested.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
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.
Shared task files/comments remain with related sessions and can be read by later agents. Audit retention and tamper resistance are not established.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
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.
Documented diff review includes changed-file navigation, comments and viewed markers, with artifact comments retained across UI reloads. Review effort, narrow screens and missed-evidence rates were not measured.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Shared task access allows another editor to add sessions and continue task files/history. Ongoing process/ownership transfer after owner disconnect was not tested. Claude/Codex handoff continues on the same task/worktree with transcript per release notes. This is separate from verified human takeover.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Task files sync into an artifact view, including text, HTML, images and PDFs, with task/session grouping. No cross-task gallery or exact-revision retrieval fixture was run. Workflow PR output can save a description and walkthrough. Retrieval of a full completed reviewer child was not tested.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Scope and sources
Guided implementation documents checks/manual review between phases; PR follow-up can respond to CI. These are workflow instructions, not verified enforced delivery gates. PR skills compare branch changes with the task plan. Persistent-spec conflict enforcement is not established.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Workspace setup creates task branches/worktrees; implementation skills commit checked phases. No fixture change was delivered. An opt-in GitHub PR tab exposes PR actions/review threads/checks, and PR skills create/update descriptions and follow up on checks.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The opt-in GitHub PR tab documents merge and auto-merge actions. Exact-revision authority enforcement, release and deployment were not tested.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Release notes document session/PR links through a commit ledger; task artifacts retain PR descriptions. This does not establish delivery status or rollback.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Per-task diff/artifact comments, PR controls and workflow next actions exist. A six-task batch review queue, dependency ordering and stale-approval invalidation remain unverified.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Scope and sources
The current application monorepo at the cited revision is Apache-2.0, with separately licensed vendored MIT folders. It includes desktop/web, daemon, API and sync proxy. The pinned README says HumanLayer Cloud runs this code. Independent production parity and any hosted-only operations were not audited.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-11. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Current core is open source and can be built and run; 0.202.0 adds a reference self-host copy that HumanLayer calls unsupported, with WorkOS login required. The Factory transition notice offers data-export, migration or self-hosting support and refunds; an actual full history export/import was not tested.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources
Agents execute on user hosts while events/task artifacts sync through HumanLayer APIs/storage; model traffic can use configured provider gateways. Retention, residency and training policies were not audited. Saved daemon login includes a refresh token; host credentials/history volumes require persistence and limited access. Further scoped facts are recorded in the atomic answers.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-21. Scope and sources
Public pricing lists Pro at USD 100/user/month with unlimited tasks/sessions and BYO agent subscriptions/API keys; Starter is free up to three members and 200 sessions/month. Provider/compute costs remain separate. Agents use user-provided local/remote compute; no universal compute bill is established.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-10. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
One or two users can fit the advertised free Starter seat allowance if they remain within 200 sessions/month. Provider subscriptions, workload costs and compute remain unknown; this is not a priced measured workload.
Official notes reach 0.202.0 on November 14, 2026; production and beta environments both run. Release documentation is not a hands-on reliability result. The November 4 Factory notice sets at least 30 days of transition operation and offers export/migration/self-hosting support. No exact hosted end date is announced.
Checked 2026-11-22 (checked today); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The vendor homepage asserts SOC 2 Type II and Vanta monitoring. No report, audit period or independent scope verification was accessed in this November 7 pass.
Starter is an ongoing free plan for up to three members and 200 sessions/month, currently offered during the announced transition. The homepage includes Pro capabilities; model and host costs remain separate. Apache-2.0 self-builds have no application licence charge; compute, model and third-party service costs remain. Self-hosting setup was not executed.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-10. Scope and sources
Podium
Agent cross-checkedpartial
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.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Pricing is partially specified: per-user monthly Pro price and Starter caps are public; Enterprise is custom, while taxes, overages and minimum commitments are not resolved.