A source-linked comparison across the complete Podium ADE rubric. 48 criteria sourced for both products; 34 criteria also agent cross-checked for both. 50 rows have at least one sourced finding, including 46 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.
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.
Electron desktop app for macOS (Apple Silicon only) and Linux (x64 and arm64) with a local backend; the `sculpt` CLI for agents and scripts; no Windows, Intel Mac or editor-extension client. The user docs and SECURITY.md describe local use only, but the repository also ships a web build (installable PWA) that the backend serves in an OpenHost self-hosted deployment; the two first-party sources are not reconciled.
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
Sculptor
Agent cross-checkedpartial
Integrated harnesses for Claude Code (default) and Pi, plus any terminal-based agent as a terminal agent; Claude model families via the Claude CLI, Pi models from its own providers. Adding a first-class harness needs code.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Uses the Claude CLI's own login (subscription or API) and Pi's provider connections and keys; fast mode on Claude subscriptions draws on usage credits. No Imbue credits or accounts; local models only via Pi providers.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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.
Documented path: download the app, run the wizard (name/email, Claude CLI and git check, add a repository), create a workspace and prompt an agent, review changes and create a PR with gh. Requires a Git repository; no remote needed for worktrees; GitHub features need gh. Container or remote backend is experimental.
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
Sculptor
Agent cross-checkedpartial
A local REST/WebSocket backend (default port 5050) with an OpenAPI-generated Python client powers the `sculpt` CLI, which can create, inspect, message and interrupt agents and workspaces; session-token auth for local use; no public hosted API, SDK package, MCP server or webhooks; the API is experimental.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Claude CLI MCP and plugin configuration is inherited; Sculptor adds bundled skills and slash-command plugins, an extension system for UI panels (Linear bundled), custom saved actions and the sculpt skill. Sculptor itself documents no MCP client UI.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Electron desktop app (React/TypeScript frontend, Electron Forge) with a separate Python backend process; no mobile client.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Intake is prompts and starter prompts per workspace; the bundled Linear extension shows issues linked to the current branch/PR and a board-style home of assigned issues (read-only link view); no issue import into the product's own data.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Plan mode makes the agent write a plan and wait for approval (plan opens in the editor pane for Claude, inline for Pi); agent todo lists track steps; workflow skills write spec, architecture and plan files into the repo; no separate plan database or revision UI beyond Git.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Agents break work into todo lists; Claude is told to record which tasks block which and Sculptor draws a dependency graph; skills create plan folders of task files; workspaces can be stacked on a branch; no epics or enforced dependencies.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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.
Context is per agent conversation with /compact, /clear and a context % footer; repo `.sculptor/code.md`, `testing.md` and `docs.md` guidance via `/sculptor-workflow:setup-repo`; skills and CLAUDE.md/AGENTS.md read by the harness; handoff skills carry summaries to a fresh agent. No managed cross-session memory store.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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 code index or retrieval of its own; @ mentions attach files and folders, images can be attached, and the browse tab shows the tree. Retrieval is the agent's.
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
Sculptor
Agent cross-checkedpartial
No native issue or backlog; units are workspaces and agents (with tabs, names, auto-naming and a sidebar list); bundled Linear extension displays assigned issues.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Agents can use the `sculpt` CLI (with their own agent/workspace identity) to create, list, message, inspect and interrupt agents and workspaces, but there are no issues or fields; Linear data is read through the extension.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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.
No living product specification; the workflow skills write per-feature spec, mocks, architecture and plan files into the repo, which are ordinary files without drift checks.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Sourcedpartial
Multiple agents per workspace and multiple workspaces run at once; tabs and a sidebar list show state; no documented concurrency limit.
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
Sculptor
Agent cross-checkedpartial
The user decides which workspace and agent does what; agents in one workspace share files and may conflict; agents with the sculpt skill can create and message other agents. No queues, claims or enforcement.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Agents can create, message, inspect and interrupt other agents with the bundled sculpt CLI skill (handoff, stack, batch-style skills), and Claude's own subagents/batch skills run inside the harness; delegation is skill-driven and experimental, not a coordinator UI.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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.
No product scheduler or event triggers; the experimental CI Babysitter reacts to PR check failures and merge conflicts by prompting an agent; Claude's `/loop` skill is the harness's. Runs only while the app runs.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Interrupt a turn, edit or delete queued messages, answer persistent pending questions in native panels, plan approval, steer by sending corrections; an interrupted turn survives a quit or crash; notifications from substituted tools; no pause control.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Sidebar lists workspaces and agents with status; top bar shows repo, branch, target and change summary with PR status; Linear extension offers a board view of issues; no multi-epic dependency, workload or attention dashboard.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
No mandatory workflow: any prompt works, optional sculptor-workflow pipeline (spec → mock → architect → plan → build → review), per-agent model/effort/fast, saved actions and handoff; configuration is in the UI and files.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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 execute on the user's machine by default; remote options are an experimental custom backend command (Docker, VM or SSH recipe) and an OpenHost self-hosted deployment in the repository that runs the backend and agents in a container behind a web UI. SECURITY.md says Sculptor is for local use and not for network exposure or hosted use, which conflicts with the OpenHost files. No managed cloud.
Podium separates issue files with Git branches and worktrees, but its released daemon launches native host processes without product-managed container or VM provisioning.
Default isolation is a git worktree per workspace (clone and in-place are experimental modes); agents in one workspace share the working copy; Claude is launched with permissions skipped and IS_SANDBOX=1 while the integrated-harness doc says it "runs sandboxed" — bounded search found no sandbox launcher; the Docker backend is an experimental recipe.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Agent processes are independent of the app, so an interrupted turn survives a quit or Sculptor crash; message queue and pending questions persist across reloads and harness restarts; conversations persist in the local database; no remote compute to replace.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
A per-repo setup command runs when a workspace is created (e.g. npm install); env files load from `~/.sculptor/.env` and `.sculptor/.env`; a built-in terminal helps; no cache sharing, port allocation or snapshots.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
No time, token or spend limits; context % shown and compaction available; CI Babysitter has a retry cap; provider limits are the harness's.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Tool-call cards with timing, task list progress, context % with a token breakdown, PR/CI status polling and a `trace`/`debug` CLI for development; no cost or usage statistics, exports or per-project stats.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Only a per-turn context percentage and token breakdown; fast mode notes higher per-token price and credit use; no dollar costs, aggregation or export.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Sourcedpartial
No compute-aware scheduling or resource limits; CI Babysitter waits for an idle workspace and avoids duplicate fixes for one failing run; message queues are per agent.
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
Sculptor
Agent cross-checkedpartial
Single-user local app (name and email in the wizard); no sharing, presence, comments or multi-user steering; SECURITY.md says not to expose it to a network.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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.
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.
Claude runs with `--dangerously-skip-permissions` and permissions routed through a stdio permission-prompt tool that Sculptor auto-approves ("tool permissions auto-approved"); Ask-User-Question and plan approval are replaced by native panels; no command, network or secret approval policy.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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 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
Sculptor
Agent cross-checkedpartial
Files panel (Browse, Changes, Commits) with unified or split diffs, per-file discard, commit button, PR button with status, review skill and keyboard shortcuts with a command palette; no review queue, comments or request-changes workflow.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
No second person: local single user; a `handoff` skill moves work to a fresh agent in the same or a new workspace with a summary, and machine state does not transfer to another machine.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Retained outputs are Git diffs and commits, conversations with tool cards, agent-produced images in chat and files in the workspace (spec, mocks.html, review.md); no gallery, recordings or test artifact store.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Sourcedpartial
No product-run test or lint gates; the workflow skills write failing tests first (fix-bug) and run a review skill; CI Babysitter reacts to red CI; nothing blocks delivery.
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
Sculptor
Agent cross-checkedpartial
Integrated Git: worktree branches with patterns and target branch, live diff, commit via the agent, push and PR creation through gh with editable prompts, PR status, babysitter that rebases and force-pushes to resolve conflicts; stacked workspaces.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
The product can push and open a PR on user click; it does not merge, release or deploy (the babysitter never merges or closes a PR).
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Top-bar PR status (open/merged/closed, approvals, comments, CI), commits on the workspace branch and branch cleanup policy; no build/deployment links, rollback or revert feature beyond per-file discard.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
No batch review or shipping queue; per-workspace PR buttons and the CI Babysitter help "leave a batch of PRs to sort themselves out"; no grouping, filters or merge queue.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedsupported
MIT license for the whole monorepo (Electron frontend, Python backend, sculpt CLI, bundled skills and extensions) at v0.50.0; released installers are built from it; no closed or hosted components were found.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Local-only application with data under ~/.sculptor and Git branches; no vendor service needed beyond the harness providers and optional Linear/PostHog; no export or import features; experimental custom backend for containers.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Code, prompts and credentials stay local apart from the harness providers; telemetry is frontend-only PostHog (structure-only autocapture, text masked, session recording off) behind a binary consent with a Settings > Privacy toggle and defaults of false in the config model; backend reports nothing to PostHog or Sentry; the wizard's email is shown in Privacy and a signup event fires from the frontend.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Free and open source (MIT) in a research preview with no prices or paid plan published; Claude/Pi provider costs are separate; fast mode draws additional Claude usage credits.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Experimental research preview with rapid releases (0.49.0 on 2026-10-21, 0.50.0rc2 on 2026-11-13, 0.50.0 on 2026-11-16); support through GitHub issues, limited external contribution bandwidth, private vulnerability reporting; no response commitments or status page.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources
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
Sculptor
Agent cross-checkedpartial
Free MIT download with no trial or caps; BYO Claude/Pi accounts; no remote compute, mobile, two-person collaboration or native issues; Linear extension requires a Linear account.
Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scope and sources