A source-linked comparison across the complete Podium ADE rubric. 48 criteria sourced for both products; 37 criteria also agent cross-checked for both. 50 rows have at least one sourced finding, including 50 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.
Terminal client on macOS, Linux, Windows (PowerShell, WSL), Android terminals and BSDs via package managers and binaries; crush run for headless use; crush server exposes an HTTP API that other clients can attach to. No native desktop app, mobile app, browser UI or editor extension ships in this release.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
Podium
Sourcedpartial
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.
Crush embeds its own agent loop (via the fantasy provider layer) rather than launching other agent CLIs. Model providers are broad: Hyper, Anthropic, OpenAI, Gemini, Bedrock, Vertex, Azure, OpenRouter, Groq, xAI and others plus custom OpenAI- or Anthropic-compatible endpoints and local servers. Mixed-harness operation does not exist; subagents can use a different model but not a different harness.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Routes: API keys for many providers, vendor model service Hyper (subscription and prepaid), ChatGPT subscription via OAuth against the Codex backend, GitHub Copilot and Grok account logins, and local models. Anthropic subscription login is not offered; Anthropic access is by API key. Account switching is by model or provider selection mid-session; no multi-account manager for one provider was found.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Install via package manager, run crush, pick a model in the picker (Hyper login or API key) and start prompting; works in any directory with no Git requirement. Git features are only prompts to the model. No managed cloud or BYO-VPS installer exists.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
CLI: run (headless prompt), session list/show/last/delete/rename (json output), stats, logs, models. HTTP API from crush server with OpenAPI 3.1 docs covers workspaces, sessions, messages, agent run/cancel/queue/summarize, permissions, questions, MCP and config over unix socket or TCP; the handler has no authentication. No SDK, no webhook ingress and no MCP server exposing Crush to other agents.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
MCP client over http, stdio and sse with OAuth flow (including pre-registered clients), resources and prompts; Agent Skills from many directories (including .claude/skills and .cursor/skills); context files from AGENTS.md, CLAUDE.md, GEMINI.md, .cursorrules and Copilot instructions; hooks for tool control; LSP integration. No plugin marketplace or custom Go tool plugin API.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Single client implementation: a Go terminal UI built with Bubble Tea v2, Lip Gloss and Glamour. No desktop, mobile, Electron or web client.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Intake is prompts typed in the TUI, piped stdin to crush run, API posts, and MCP channel pushes. No issue import, no tracker sync and no native chat or Git triggers.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Crush has a plan agent and a todos tool that keep an in-session task list persisted on the session record; there are no acceptance criteria, plan editor or revision history.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No epics or dependency graph. Parent-child exists only between a session and its subagent task sessions; blockers and readiness are not modelled.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Instruction files (AGENTS.md, CRUSH.md, CLAUDE.md and others, plus global CRUSH.md/AGENTS.md), Agent Skills, .crushignore and /init-generated context files. Cross-session memory is limited to those files and persisted sessions; there is no managed memory store.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
Code navigation uses grep, glob, ls, view, Sourcegraph search and LSP tools (definitions, references, symbols, call hierarchy, diagnostics); web fetch and web search tools; image input depends on the model. No repository index, citations or architectural-conflict checks.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
No issue tracker. Sessions with titles and todos are listed and searchable in the session picker; there are no labels, assignees, priorities, archives or boards.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No shared issue records exist for agents to operate on; agents see only their todos tool and subagent tools.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No living product specification features; context files are static Markdown the user maintains.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
Multiple sessions per project and multiple clients on one server workspace are supported; subagents can run concurrently; background shell jobs up to max_background_jobs (default 50). No documented quota on subagents. The server marks sessions IsBusy and counts attached clients.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No assignment, claims or queues for work. Prompts queue per session; routing exists only for MCP channel messages to a session.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Product-owned delegation: the main agent can dispatch named subagents with read or write access and a chosen model, provider and reasoning effort, message them, stop them, check status, and receive their reports as later turns; subagents are persisted as sessions and reconciled after restart. In headless run mode delegation blocks. Cross-harness teams are not possible.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No scheduler or recurring tasks. MCP servers opted in as channels can push events that start a turn in a session of a running server or TUI; there are no completion conditions or retries.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
Cancel (esc/ctrl+c, API cancel), queued prompts as steering, permission prompts and question tool for decisions, stop of subagents, session resume. Pause is not offered distinct from cancel. Notifications for permission and turn end when unfocused.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No fleet or epic management view; the session picker lists sessions and busy/attached signals.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Free-form prompting with no mandatory workflow; subagent model and reasoning configurable per dispatch in natural language; roles and results visible in the transcript; no presets or epics.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Executes on the machine running crush (or its server). A headless crush server on a user host can serve clients, but work does not move to a vendor cloud, and a closed terminal ends a TUI session while a server keeps running agents. No managed cloud.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
Agents run on the user checkout with the user permissions; no worktree, branch, container, VM or OS sandbox is created by Crush. Isolation is the permission prompt system and tool allow/deny lists; the bash tool runs in a built-in shell interpreter on the host.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
State persists in SQLite so transcripts, usage and todos survive crashes and restarts; subagents unanswered at shutdown are reported as interrupted; sessions resume via --continue; there is no process re-attachment or automatic task resumption.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Crush does not manage dependencies, caches, services, ports or secrets for workspaces; it uses the host environment and relies on LSP servers the user installs. Config supports env expansion.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Per-request inactivity timeout (default 60s, configurable), loop detection (repeated tool-call signature), auto-summarize on context pressure, background job cap. No turn, token or spend caps were found.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Logs (crush logs, ./.crush/logs), session cost/token tracking, crush stats with usage by day, model, hour and tool, tool call timers. No traces, per-agent or per-project dashboards beyond stats --all, and no performance measurement.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Session cost in USD is shown in the sidebar and stored per session using catalog pricing or provider-reported cost (OpenRouter), with token counts and an estimated-usage flag; subagent task sessions are separate sessions. No epic aggregation, budgets or alerts; subscription logins do not report marginal cost.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No compute-aware scheduling. Background shell jobs are capped (max_background_jobs); prompts queue per session; no CPU/RAM awareness or check deduplication.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Several clients with the same --cwd join one server workspace and share session list, history, permission queue, LSP and MCP state, and a session mirrors live in all attached clients, but there are no accounts, comments or presence beyond an attached-client count. Co-prompting is possible in the same session through any attached client without attribution.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No organization, project or task roles, membership, SSO or provisioning; the server has no authentication.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
Per-tool-call permission prompts with allow once, allow for session and deny; persistent allow/deny lists by tool name in config; bash read-only commands auto-allowed after parsing; yolo mode skips prompts but refuses dangerous commands; PreToolUse hooks can allow/deny or rewrite. These are product-enforced in the tool layer.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
Messages, tool calls, usage and file versions are stored per session in SQLite and persist across sessions; no user attribution, approvals log or export beyond JSON session output; records are local and mutable.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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.
Edits show diffs in the permission dialog and modified-file counts (+/-) in the sidebar; there is no review queue, comment or request-changes flow.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
A second client can join the same workspace and open the same session with its history, but there is no identity, ownership transfer or cross-harness transfer.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Retained outputs are the transcript, tool results, file version history and modified-file list per session; no gallery, screenshots, recordings or previews.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No required checks or gates. The agent may run tests or linters through bash and LSP diagnostics are available as a tool; hooks can be configured by the user to block actions.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Git is done by the model through the bash tool with a prompt for commits (with attribution trailers) and gh pr create; branch name is shown from git; no worktrees, rebase handling or CI response in product state.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Merge, release and deploy authority is the user running or approving shell commands; no product-level approval or exact-revision checks.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
No task-to-commit, PR, build or deployment links or rollback features; commits carry an attribution trailer naming the model.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Single public repository under FSL-1.1-MIT (Functional Source License with MIT future license): free use, copying and modification for any purpose except a Competing Use, converting to MIT after the license period. Source-available rather than a standard open-source license today. Provider catalog (Catwalk) and Hyper service are separate.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Fully local: runs without any vendor service, with sessions in a local SQLite DB and config in crushrc/JSON files; provider catalog auto-updates from Catwalk unless disabled. Export is limited to session JSON output; no import. Cancelling Hyper does not affect local use.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Code and prompts go to the model provider you choose; local storage in SQLite and logs in .crush; pseudonymous usage metrics (device hash, usage metadata, never prompts or responses per README) go to PostHog, disabled by CRUSH_DISABLE_METRICS=1, DO_NOT_TRACK=1 or options.disable_metrics; metrics are on by default and no first-run consent dialog was found. Hyper policies are separate and not captured.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Crush itself is free; model costs are separate. Hyper is the first-party model provider with subscription and prepaid options per the README, but its prices were not readable and are a separate service.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Scenario costs for one, two and five developers cannot be priced from public sources beyond software cost zero; model spend depends on provider and usage and is unpublished.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Public GitHub project from Charmbracelet, Inc.; weekly tagged releases (v0.101.0 on 2026-11-12, v0.100.0 on 2026-11-05), nightly builds, community Slack, Discord and issues. No stated response commitments.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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
Ongoing free software: the ADE is free to download and use with your own API keys, subscription logins or local models; Hyper offers subscription and prepaid options for models. No card needed for the ADE.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. 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