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.
Browser cockpit (npx cezar-run, localhost:4321; responsive on phones, with mobile task list/session/review) is the primary client; Tauri desktop app for macOS 12+ (aarch64/x86_64), Linux (x86_64 AppImage/deb/pkg) and Windows x86_64; cezar/cez CLI for headless runs and server install; no native phone app or editor extension.
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.
Cezar launches the user's logged-in agent CLIs through one AgentRunner seam: Claude Code, Codex (app-server), Junie, OpenCode, Cursor Agent, pi (experimental ones noted) with README adding Copilot, Antigravity, Gemini, Kimi and OMP; models are discovered from each CLI; backend per task or per workflow step enables mixed-agent chains.
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
Uses the user's own claude/codex/etc. login ("your subscription, no API key"); multiple agent accounts and an automatic fallback order across up to ten provider/account pairs; no vendor credits or models from Cezar; local models only through agents that support them; Gemini CLI requires an API key, Vertex or Workspace licence.
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
npx cezar-run in a repo opens the cockpit; type a task and Start; Node 20+ and one logged-in agent CLI required, git and gh optional; non-Git directories degrade to one task at a time; server-install sets up a VPS with HTTPS and login; macOS+ngrok guide; CEZ_DRY_RUN mock mode.
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 (cez runs/task/automation/tracker, headless cezar run), a versioned HTTP API under /api/v1 with zod schemas (typed contract and a private api-client package), webhooks (opt-in), and health discovery; no MCP server found; cockpit binds 127.0.0.1 with no built-in auth.
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 and tools are inherited from each agent CLI; Cezar adds Markdown skills (project, team repo, org repos), workflow nodes (agent, check, gate, dispatch, github, notify), skills catalog with provisioning into workspaces, Settings > Agent config editing and Open Mercato skills installs.
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
Web cockpit is a React app (Vite) served pre-built from the Node package; the desktop app is a Tauri 2 shell around the same UI; responsive layout for phones; no React Native or native UI.
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
Tasks are created from the cockpit composer, a prompt, GitHub issues/PRs (via gh, including Enterprise), Jira Cloud and Linear issue browsers, bookmarklets, headless cezar run, automations (schedule, GitHub and tracker events) and manager agents; tasks are local records that link to issues and PRs.
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
Plan first lets the planner draft a chain for review; workflows are YAML with steps, checks and retry rules; attachments and notes journal per task; no acceptance-criteria object or revision history beyond files/git.
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
Dispatch lets a task start child tasks (four in flight, each in its own worktree forked from the parent branch, budget carved from the parent) that report back; dispatch trees are visible nested under the parent; workflow graphs support loops, gates and sub-workflows; no epics, blockers or readiness model.
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
Skills (Markdown playbooks from project, team repo and org repos), custom system prompt and prompt templates per project, task Notes handoff journal, optional follow-up inbox, resumed agent sessions and per-task attachments; no managed cross-session 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.
Git tab shows diffs, history and a repository file browser; ⌘P finds task files; GitHub issues/PRs are read; no code indexing, external knowledge base, citations or review-time architecture enforcement; attachments include images, PDFs, text.
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.
Tasks are persistent runs (queued, running, review, done, failed, cancelled) with titles, tags per project, pin/archive/read marks, search and filters, All tasks grouping by tag, project, status or workflow, parent/child dispatch and PR/issue links; ideas can be left queued or in the opt-in Inbox; no discussion threads, priorities or assignees.
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
Running tasks can create child tasks, report results, and (for tracker-launched tasks) read, comment and transition their own Jira/Linear issue through cez tracker with a per-session capability; managers start and steer tasks; cez runs/automation list read state; changes appear in the cockpit.
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: skills, notes and workflows are not maintained requirements with drift detection (internal .ai/specs are the maintainers' own).
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.
Up to maxParallel tasks (default 2, configurable) run concurrently across every project in separate worktrees with extra tasks held in a visible FIFO queue (#1, #2); non-git projects run one at a time; the cockpit dashboard shows Needs you, running and finished work.
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
FIFO queue with Run First promotion, per-project parallel ceilings, worktree and repository locks preventing two writers in one checkout, trunk-based write tasks taking turns, and dispatch assigning child tasks to runners; no human assignees or routing rules.
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-supplied delegation: a running task can dispatch up to four child tasks (own worktree and budget, any runner, kind review verdicts) and receive reports via cez task report; Manager agents are global chat agents that watch projects and start/steer tasks with approval for merges; workflow graph nodes dispatch and run sub-workflows; children show nested live.
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
Automations (on by default) start ordinary tasks on calendar schedules, GitHub PR/issue events and Jira/Linear events; the list shows next runs, outcomes and pause; the coordinator reconciles retained run records after restarts; schedules run on the cockpit host so the server must be running.
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 (queued or running), Continue, follow-up messages into live sessions, memory-ceiling pause that resumes on demand, human gates and ask-user nodes in workflows, Needs-you navigation and notifications; approvals in Claude Code are not actionable in the cockpit (unapproved tools denied).
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
Dashboard Overview shows attention, completed/failed outcomes, median cycle time, project comparisons, live work, enabled automations and recent results; All tasks groups by tag/project/status/workflow with PR/issue refs, cost and live CPU/memory; dispatch trees nest children; Needs-you navigation.
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
No mandatory preset: quick-task runs with zero setup; Plan first drafts chains in natural language; workflows are optional YAML/graphs with per-step runner and model; Autonomous toggle; in-run messages; the UI shows nodes, children and results live; managers add chat-driven control.
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
Runs on the machine hosting the cockpit: local laptop, or your own VPS/server via server-install (nginx+HTTPS+systemd) or macOS+ngrok, so work continues when your laptop is closed and is reachable from phones; a separate Open Mercato cloud sandbox is offered (closed); no vendor-run execution in the open-source product.
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.
Every task runs in its own git worktree (branch cez/<id8>) with a repository lock, per-task temp dir and least-privilege agent environment; trunk-based mode works in the checkout; no container, VM or OS sandbox: the zero-config Claude tool list grants unrestricted Bash in the worktree and Codex/Junie/OpenCode ignore allowedTools.
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.
Queue and run records are re-enqueued after a cockpit restart; runs resume the agent session or start a fresh one when a conversation is pruned; auto-resume at provider reset; leftover processes are reaped; scheduled-start recovery reconciles retained records; worktrees are retained then reclaimed with branches kept.
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
Worktree lifecycle scripts run ordered setup/cleanup commands with variables (root, worktree path, id) such as copying .env or docker compose per worktree; Preview Start app runs services in terminal tabs; per-task TMPDIR; encrypted Secrets assigned to checks; no automatic dependency/cache sharing or port allocation.
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-task budgets (child dispatch and graph nodes carry budgetUsd carved from the parent), per-task memory ceiling, parallel cap, 30-minute default timeout for lifecycle commands, retry loops with max counts, automatic fallback on usage exhaustion and reset-time auto-resume; enforcement varies (budgets stop, some limits warn).
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
Live event stream (agent text, tool calls, results), token and backend-reported cost per step, Usage & cost by project, dashboard outcomes and median cycle time, per-task peak memory and CPU, failure kinds, cez impact reports and HTML artifacts; NDJSON logs; state kept consistent via SSE and persistence.
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
Cost and token counts are shown per step and task from backend-reported usage, aggregated by project and in the dashboard, with separate hide-cost and hide-token flags; subscription usage appears as tokens with cost when the backend reports it; no budgets alerts or CSV export beyond API.
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
Global maxParallel cap with FIFO queue and Run First, per-project ceilings, per-task memory ceiling with pause, process-tree CPU/RSS sampling, repository lock, worktree retention and Reclaim, cancellation of queued tasks; no cross-task 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
A hosted cockpit can be opened by anyone behind its login and shows the same tasks live; there are no user identities, comments, presence or per-user prompting; sharing is a single basic-auth credential.
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/task roles, membership, SSO or provisioning; access is basic auth at the proxy or none on localhost.
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.
Autonomous toggle and per-backend tool lists: Claude denies unapproved tools without prompting (dontAsk) and zero-config allows unrestricted Bash; there is no cockpit permission response channel; human gates, ask-user and review gates exist in workflows; secrets can be granted per task; tracker capability per session.
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.
Per-task append-only NDJSON transcripts record messages, tool calls and results; telemetry audit is separate and opt-in; no user attribution; local files can be edited; webhooks give lifecycle events.
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.
Review gate parks a finished run with changes; diff view with inline comments that go back to the agent session, side-by-side variant comparison, Draft PR, Git tab commit patches, keyboard shortcuts and mobile diff review; reviewer children can issue verdicts.
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
Anyone with access to a hosted cockpit can open the same task, history, diffs and terminal and continue it, and continue with another agent via fallback; there is no identity, ownership transfer or permission model.
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 per-task diffs, transcripts, attachments (screenshots, PDFs), HTML artifacts and impact reports under .ai/cezar/artifacts/<runId>, preview tab with Design Mode, e2e verification outputs and variants; browsable per task and task list.
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
Workflow check steps (exit 0 = pass) with onFail retry loops feed failures back to the agent; requiredChecks for trunk landing; github.wait-ci node; e2e verification gate; optional review gate and independent review children; no persistent-spec conformance.
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
Branch and worktree per task, autosave and landing commits with generated subjects, Draft PR via gh, GitHub issues/PRs views, CI wait node, trunk-based Finish that commits, rebases, runs required checks and pushes, and failed rebases returned to the agent.
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
"You stay the merge button": agents never merge on their own; managers propose merges that require chat approval; trunk-based tasks can land (push to base branch) after required checks; no release or deploy features.
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
Tasks link to branches, PRs and issues; landing records commits; cez impact reports and artifacts retain evidence; branches are kept when worktrees are reclaimed so work stays recoverable; no deployment links or built-in rollback/revert.
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
Dashboard, All tasks filters and Needs-you navigation list finished tasks and reviews; variants compare diffs; managers summarise; Review open PRs template and review children produce verdicts; no risk/size filters, stale approval invalidation or dependency-aware merge queues.
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
MIT license for the whole repository (server, web cockpit, desktop shell, docs) at v0.20.0; the Open Mercato cloud sandbox is a separate hosted service; Windows installer signing uses SignPath.
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
Self-hostable by design: npx cezar-run or server-install; state is plain files (.ai/cezar, ~/.cezar) with no database; usable without any Cezar account; projects can be removed without touching repos; export is files/git; telemetry is opt-in.
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, prompts and transcripts stay on the host and go only to the chosen agent providers; credentials in an encrypted store (AES-256-GCM, keychain) with secret scrubbing of on-disk state; telemetry is opt-in with documented events and DO_NOT_TRACK/CEZ_TELEMETRY=0 blocks; no training use by Cezar.
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
Cezar itself is free and open source with no price; separate costs are agent subscriptions or API keys and the user's host; the Open Mercato cloud sandbox (README banner "Start for free") has its own undisclosed pricing.
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
Platform cost is zero for one, two or five developers when self-hosted; agent subscription and VPS costs depend on workload and are not modeled by Cezar; cloud sandbox cost unknown.
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.
Open-source project from Open Mercato with frequent releases (npm weekly-ish, v0.20.0 on 2026-11-15; desktop v0.1.11), GitHub issues and nightly/preview channels; no response commitments or status page found.
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
Free and open source with no account, trial or caps; a mock dry-run mode lets you evaluate without any agent login; cloud sandbox offers "Start for free" separately.
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