---
schema_version: 7
rubric_version: "0.3"
canonical_url: "https://podium.do/compare/agents/podium-vs-rove/"
data_url: "https://podium.do/compare/agents/podium-vs-rove/data.json"
generated_at: 2026-11-22
last_checked_at: 2026-11-17
last_cross_checked_at: 2026-11-21
oldest_checked_at: 2026-11-06
publisher: "Podium"
---

# Podium vs Rove

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

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

48 criteria sourced for both products; 31 criteria also agent cross-checked for both. 50 criteria with a sourced finding for at least one product. "Sourced" findings passed publication validation. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. Humans approve the rubric, templates and prototype; they do not review every finding. It does not declare a winner. A missing sourced finding is not evidence that a capability is absent.

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

- Podium source checks: 2026-11-06. Details: https://podium.do/compare/agents/products/podium/index.md
- Rove source checks: 2026-11-17. Details: https://podium.do/compare/agents/products/rove/index.md
- Rubric: https://podium.do/compare/agents/rubric/index.md
- Canonical HTML: https://podium.do/compare/agents/podium-vs-rove/
- Machine-readable JSON: https://podium.do/compare/agents/podium-vs-rove/data.json
- Methodology: https://podium.do/compare/agents/methodology/

## Access and agent choice

### ACC-01: Client access

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium ships desktop, CLI and browser clients, including phone-browser control. The native iPhone app is private beta; the complete download offering contains no native Android app.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Terminal UI on macOS, Linux, WSL and native Windows; browser client (rove --web); Electron desktop window (macOS, Windows x64, Linux AppImage); SwiftUI iOS and Kotlin Android remote controls built from source; WeChat bridge. No editor extension.

### ACC-02: Agent and model choice

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium launches the native Claude Code, Codex, Grok, OpenCode, Cursor and Pi CLIs in persistent terminals on machines you control. The 0.2.0 release calls Pi fully supported. Models come from each harness catalog, and capabilities differ per harness: Pi declares no quota, handoff or hooks. Mixed-harness operation was not exercised.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Runs the real interactive CLIs: built-in Claude Code, Codex, GitHub Copilot, Kimi Code, Pi, OMP and IBM Bob; 15 more launch-and-badge contrib engines; custom commands and plugin engines. Mixed engines per task and per fan-out round.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium supports native coding-agent logins and managed provider credentials. Claude subscriptions (via native login or a managed setup-token) and local ChatGPT/Codex login are supported paths, alongside Anthropic and OpenAI API keys. Docs list billing and hosted metering as not implemented product claims.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Uses each engine CLI's own login, so existing Claude, Codex and Copilot subscriptions or API keys work; Rove shows Claude and Codex subscription windows. No vendor credits.

### ACC-04: Onboarding and project prerequisites

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Docs describe a first-run flow (install, podium, register a Git repository, confirm a detected logged-in harness) and a headless VPS installer with machine joining. Setup time and failure rate were not measured, and no self-serve managed cloud setup is documented. The current README and installation guide use podium.do/download and podium.do/install.sh as the canonical stable entrypoints.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. curl or npm install, then rove in a repo and press n; needs git and one engine CLI. Directory tasks work without Git; local repos without a remote work; GitHub needs gh for PRs and issues. BYO SSH machines via rove machine add; no managed cloud.

### ACC-05: Programmable access

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The podium CLI covers issue create, show, update, claim, dependencies, artifacts, session send/status/read/stop and review actions, and the server exposes the same issue commands as a bearer-token MCP tool endpoint. No documented public HTTP API, SDK or webhooks were found.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. rove api exposes create, read, steer, stop, land and publish verbs over CLI, daemon socket and bridge WebSocket with a versioned envelope; inbound signed webhooks fire routines; TypeScript plugin SDK. No MCP server for task control.

### ACC-06: External tools and extensions

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Podium gives agents its own issue tools over CLI and MCP, and agent profiles import and export Claude Code agent files. No Podium documentation for user-configured MCP clients, plugins or custom tools was found.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. MCP use is inherited from each engine CLI. Rove has first-party and third-party plugins (rove-plugin.toml) adding panes, events, commands, engines and mods, plus a bundled agent skill. Plugins are unsandboxed.

### ACC-07: Client implementation

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Desktop releases use a Tauri 2 shell that serves the Podium web UI; mobile source uses Expo and React Native. A native iPhone release is described as private beta.
- **Rove**: Agent cross-checked (agent-cross-checked); support: supported. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. TUI is Bun with OpenTUI React; web client is React and xterm.js; desktop is Electron wrapping the web client; iOS is SwiftUI; Android is Kotlin Jetpack Compose.

## Planning and context

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium issue records are native and authoritative with stable references, CLI creation and editing, and agent-driven filing from conversation. The in-product assistant has Linear search, create and move tools when a key is configured, but no import or two-way tracker sync was found.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Tasks are created from a prompt in the TUI, web, phone apps, rove api or routines. GitHub Issues can start a task read-only; a first-party Issues/Kanban mod holds a local backlog. The local issue store is authoritative for backlog; no two-way external sync.

### PLAN-02: Durable task plans

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Issue brief, acceptance criteria, state paragraph and todos persist on the durable issue record. Release 0.3.0 removed the separate design and notes fields and appended their text to the brief. On the human issue page the title, description and acceptance are editable and the brief is read-only; agents edit the brief and other fields through issue commands.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. No durable task plan object; each task is a workspace with an engine conversation. Plan mode and plans live inside the engine CLI. Diff-review notes persist per task.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium supports persistent parent and child issues, phases and typed dependency links, including reparenting an existing issue without replacing its identity. Since 0.3.0 issue types are task, phase and decision: epic and other kinds are retired, and any issue with children acts as a parent. Dependency types are fixed to blocked-by, related, discovered-from, supersedes and duplicates. Cycles are refused and docs list an open blocker as a reason an issue cannot start. No mandatory workflow preset applies in the baseline.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Tasks nest as parent and child tasks (shared directory or own worktree) with fan-out groups; there are no epics, blockers or readiness gates. Status is a user-set label.

### PLAN-04: Shared context and memory

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. v0.3.0 routes Podium issue instructions and relay environment through terminal and engine session launch. Claude stream sessions use appended instructions and boundary callbacks; Codex server sessions use developer instructions, Grok ACP uses rules, and OpenCode uses the prompt system field. Claude and Codex boundary hooks can re-prime after compaction. Transcript mirroring is on by default; full-text indexing needs the command-palette flag, which defaults off. Agent profiles can carry markdown instructions. Curated memory, skills and memory correction or deletion controls remain unestablished. No instruction-delivery or compaction scenario was run.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Repository instructions (AGENTS.md, CLAUDE.md) and skills are the engine's own. Rove adds per-repo init prompts, PR instructions, a bundled skill and experimental field notes filed by agents that start every later session in the repo.

### PLAN-05: Architecture and API awareness

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Not established. Podium mirrors daemon transcripts by default, keeps a full-text index only when the command-palette flag is on, and stores session attachments. No repository code search, architecture awareness or API retrieval feature was found.
- **Rove**: Sourced (sourced); support: partial. Checked 2026-11-17 (5 days old); not separately cross-checked. No Rove-owned code search, indexing or knowledge layer; the engine does retrieval. Rove reads images and PDFs as attachments to the first prompt.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium exposes native issue creation with an optional start flag, separate dispatch, editing, comments, labels, assignment, search, board filters, archive, sibling ordering and an issue tree. Issue records have their own identity separate from sessions and stages are durable. The idea-to-mission scenario was not run. v0.3.0 refuses an agent close or done update while issue sessions are computing unless --confirm-interrupt is supplied; guidance says to request review and close only on user instruction.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Local issue store with a Kanban board (Backlog, In progress, Parked, Done), edit in a drawer, start a session from a card, and agent issue-* verbs. No labels, assignment, priority, comments or search.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. CLI and MCP address the same canonical issue records for reads, creation, edits, claims, state, dependencies and artifacts. Relayed agents have worker capability scoped to their issue subtree, with --outside-scope confirmation for other existing issues. attachSession is not subtree-gated, but direct rehoming from a real issue is refused and an agent attach naming a Proposed target is refused. That does not make every Proposed subtree inert: operator attachment or spawn-time cwd binding can leave a session attached to a Proposed issue; newSubissue without targetId then bypasses the proposed-parent guard, creates a human-audience backlog child and attaches the existing session. This path remains at v0.3.0 source and was not exercised live. Concurrent-edit handling remains unknown.
- **Rove**: Sourced (sourced); support: partial. Checked 2026-11-17 (5 days old); not separately cross-checked. Agents and scripts use rove api issue-list/create/update/delete on the same daemon store that the board shows; board refreshes every few seconds. No attribution, assignment or dependencies.

### PLAN-08: Living product specifications

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The spec CLI and service (living specs under pspec with stable SP IDs) are in v0.3.0. Specs is an experimental, default-off feature listed on the edge channel: the flag controls the Specs UI, the spec line in CLI help and whether agents are told about the spec CLI. The podium spec command itself is dispatched, and the server specs service has no flag check, so direct CLI use does not need the flag. This agrees with the docs, which call specs not baseline rather than blocked. Not run end to end.
- **Rove**: Agent cross-checked (agent-cross-checked); support: unsupported. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. No living product specification.

## Coordination and automation

### COORD-01: Parallel work

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Docs and release notes describe many sessions running as independent terminals, one worktree per issue, and several paired machines under one server, with session and issue state visible on the flight deck, board and CLI. Agent-initiated spawns are limited to 10 per target issue per UTC day. Achieved concurrency is unmeasured.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Many tasks and tabs run concurrently, each in its own PTY under the PTY host; fan-out caps at 10 attempts from a shell and 5 in the TUI composer. Sidebar and Inbox show running, waiting, errored and finished states.

### COORD-02: Ownership and dispatch

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Issues carry an assignee, claim sets assignee and in_progress, a coordinator session can be set per issue, sessions have seats, and work can be placed on a chosen machine or agent profile. claim has no exclusivity check of its own, locks are advisory leases and Podium does not serialize agents editing one worktree, so exclusive ownership is not enforced.
- **Rove**: Sourced (sourced); support: partial. Checked 2026-11-17 (5 days old); not separately cross-checked. Work is assigned by creating a task with an engine; a dispatcher records who spawned a child; routing is manual or experimental auto-routing tiers. No claims, queues or exclusive ownership.

### COORD-03: Inspectable delegation and communication

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium orchestrates delegation itself: podium agent spawn starts a full child session on an issue with a chosen harness, model, effort or agent profile, mail carries messages, and bounded await reports the child result. Children are real sessions shown as seats on the flight deck. Agent-initiated spawns take a daily budget per issue. A complete delegated task with retained child findings was not run.
- **Rove**: Agent cross-checked (agent-cross-checked); support: supported. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Product-supplied delegation: an agent or script runs rove api add (children, fan-out, other engines), send (peer messages with provenance), report and collect, and read-output; replies route to the dispatcher tab. A bundled skill teaches this.

### COORD-04: Unattended triggers

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The server owns a scheduler for cron and one-time automations that spawn agent sessions, skipping overlaps and not backfilling occurrences more than an hour late. The Automations UI is an edge-visibility feature that defaults off and docs list automations as non-baseline. Agents can subscribe to issue and session events.
- **Rove**: Sourced (sourced); support: partial. Checked 2026-11-17 (5 days old); not separately cross-checked. Daemon-owned Routines run cron prompts that create tasks or deliver into an existing tab, with prechecks, script routines, a signed webhook and run history. The enabled routine keeps the daemon alive; no timezone field.

### COORD-05: Intervention and attention

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Chat and native CLI views share a session. v0.3.0 defaults human controller chat to steer and immediately types it into running Claude Code, Codex, Grok and OpenCode TUIs that declare native busy-input queuing; undeclared harnesses wait for a boundary, and compaction waits. Mail and automation keep when-ready delivery. Stop, resume, questions, decision issues and offers remain available. This is inspected implementation, not a cross-harness runtime parity result.
- **Rove**: Sourced (sourced); support: partial. Checked 2026-11-17 (5 days old); not separately cross-checked. Typing into the real engine session steers it; Inbox surfaces permission prompts, questions, rate limits, errors, dead engines and missing reports; decision gates ask the owner; closing the tab or deleting the task stops it.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Release 0.3.0 ships a flight deck showing a whole mission in one view: phases, every task and its state, who works on what, what is blocked and by what, and proposals. Done work stays visible. The CLI prints the same snapshot. The waterfall source is dormant and the Timeline view was deleted, so per-task timeline history is not shown. The shared 12-task UX scenario has not been run.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Sidebar tree and Inbox across projects with status marks; Kanban per project with needs-you, ready-to-land, working badges; context read lists groups. No dependency or epic views.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. A quick task can be an interactive session or an issue; an issue can grow into a mission by gaining children while keeping its identity; no mandatory workflow preset applies in the baseline. Per-agent harness, model and effort are chosen at spawn or through agent profiles, and the deck shows seats. The coordinator-with-two-reviewers scenario was not run.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. No mandatory workflow: pick engine, model and effort per task, optionally auto-routing tiers; fan-out rounds, child tasks and routines shape orchestration; the sidebar shows coordinator/worker relationships.

## Execution and reliability

### RUN-01: Laptop-independent execution

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The published Podium execution choices are local user machines and a user-owned VPS or paired machine. No vendor-operated agent host is in the complete download offering.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Execution is on the machine running the daemon and PTY host: your laptop, any registered SSH machine or a server running a resident daemon. No vendor cloud. Quitting the TUI or dropping SSH keeps work running on an awake host.

### RUN-02: Workspace and process isolation

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium separates issue files with Git branches and worktrees, but its released daemon launches native host processes without product-managed container or VM provisioning.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Each managed task gets its own git worktree and branch; directory tasks and shared children share the checkout. An experimental LayerFS backend (Linux, docker) isolates files. No container or VM for ordinary tasks and no network or secret boundary.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Closing a browser tab does not stop the agent process on a running Podium host. Idle sessions may hibernate under configurable policies; a stopped session keeps its transcript, branch and resume reference. Release 0.2.0 says a failed update rolls back and running sessions keep running through the upgrade; database rollback remains a manual restore. Terminal reattachment goes through the driver adopt contract with process-identity and observation-lease checks. Worker-crash and multi-day behavior were not tested.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Quit, SSH drop and daemon restart keep processes; reboot or PTY-host death relaunches commands with restored scrollback (up to 64MB) and engine resume; checkpoints per turn allow rewind; a restored screen is not proof of completion.

### RUN-04: Development environment reliability

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Only machine setup is documented: the installer installs missing runtime tools and pairs a host, and the state directory holds server-managed secrets. Dependency caching, services, ports and automatic repair for project environments were not found.
- **Rove**: Sourced (sourced); support: partial. Checked 2026-11-17 (5 days old); not separately cross-checked. Per-repo .rove/init.sh and init-prompt run in new worktrees, with copy-on-write cloning of ignored directories (node_modules, build output) on APFS; no port allocation, service management or secret injection.

### RUN-05: Limits and failure handling

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium exposes retryable errors, optional auto-continue with backoff, bounded waits and provider quota. Claude stream and hosted headless drivers enforce a supplied turn deadline, with no deadline when timeoutMs is absent. The one-shot headless server runner supplies its budget, default ten minutes. Agent spawns have a daily per-issue budget. Operator-configurable task-wide turn, token and spend caps remain unestablished; quota display is not enforcement.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. No turn, token or spend limits. Rate limits trigger an automatic resume for Claude when the window resets; fan-out is capped; routines have documented limits.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Podium offers local logs and crash export, structured session status, issue stats, a usage and analytics sheet with hourly list-price cost, per-task costs and host load panels. The 0.3.0 notes report a vendor benchmark of about 330 MB server memory against about 1.2 GB for an earlier Podium build, and 8 to 52 percent faster start; the method is published in the repository and was not reproduced here. Usage export and cross-reconnect consistency were not established.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Activity states, failure reasons and events per tab; daemon and bridge logs; Settings usage dashboard for Claude and Codex quota; no per-task statistics or export.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Since 0.2.0 Podium shows what each task costs, on the task header and the usage sheet, with per-session rows and descendant rollups. The 0.3.0 deck adds a mission cost chip. Figures are token estimates at public model list prices, not subscription invoices or provider bills.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. No cost or spend visibility. Per-task token sums come from vendor transcripts and Claude/Codex subscription windows are shown.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium reports host memory, load and disk, auto-hibernates idle sessions under pressure, and provides named advisory resource leases. The merge-queue panel was removed; a shipping queue remains behind the Shipping flag. Concurrency limits and bounded test queuing were not established.
- **Rove**: Sourced (sourced); support: partial. Checked 2026-11-17 (5 days old); not separately cross-checked. No CPU or RAM limits, task queue or backpressure; concurrency is bounded only by the fan-out cap and user hardware. --machine auto places work on the registered machine with the lowest reported load per core. Worktree probes use bounded concurrency.

## Human collaboration and control

### TEAM-01: Live human collaboration

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The issue UI displays owner and visibility read-only and deliberately omits sharing controls. Backend share handlers and a Members settings section with invites and admin or member roles exist; they do not establish a finished human collaboration workflow. Docs say small teams can share an instance but the interface prioritizes one operator.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Single-user tool. Several clients of one person can watch and type in the same session; there are no teammates, comments, presence or attributed co-prompting.

### TEAM-02: Roles and access boundaries

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium defines member/admin instance roles and admin-only membership management. The released client authentication uses password-backed sessions and paired-device tokens without enterprise SSO.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. No organizations, roles or user provisioning. Access is a shared token, per-device tokens, a password or Cloudflare Access SSO at the edge.

### TEAM-03: Approvals and temporary access

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Agent-session management requests go through an operator approval broker with approve and deny; the privacy docs say lifecycle commands and automation requests may require operator approval. Harness permission prompts appear as a Permission needed state; credential copying during pairing is a per-grant opt-in. Command-level policy enforcement beyond the harness own modes was not established.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Approvals are the engine CLI's own permission prompts, surfaced in the Inbox and answerable from any client; Rove adds no policy, scoped grants or revocation. Decision gates ask the owner free-form questions.

### TEAM-04: Decision and activity history

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Issue actions, approval steps, comments and mail are recorded server-side. Issue activity events, including approval steps, are pruned by the server's janitor once they are older than 14 days or fall outside the newest 50,000 rows. That policy does not define all content retention, export or tamper-evident audit guarantees.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. No attributed activity history. The daemon audits task deletions and the bridge logs destructive actions with device and time to stderr; engine transcripts are engine-owned and mutable.

### TEAM-05: Review experience and guidance

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Review is a documented loop: issue stage review, diff and checks, artifacts, offers with merge or send-back buttons, and a Tray of review-ready work. Release 0.3.0 adds quoting text from a reply or review finding into the next message and a full-height reading view with an outline. The board has a key map with a help sheet. Guided-review quality and narrow-screen use were not measured.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Inbox lists what needs you; files pane and diff view with line notes sent as one prompt; branch and working-tree scopes; keyboard-first and narrow-terminal layouts. No request-changes or approval workflow beyond notes and PR links.

### TEAM-06: Colleague takeover and continuity

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The durable issue, session transcript, artifacts and mail persist for any later agent, and a live session can be handed to another machine in an edge feature. Colleague takeover by a second person was not established.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Another person can attach to the same daemon only through the owner's tokens and sees the same tasks and sessions; there is no account-based takeover or ownership transfer.

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Artifact commands store immutable server-side copies of issue-linked files, including images, video, HTML and documents, which render in the issue sidebar and offers and stay readable after the worktree is gone. Each task has an artifacts page grouped into screens, documents and reports, with filters and search. Revision linking remains untested.
- **Rove**: Sourced (sourced); support: partial. Checked 2026-11-17 (5 days old); not separately cross-checked. Diffs and files are browsable per task; engine transcripts and scrollback persist; run output reads through read-output. No artifact gallery, recordings or previews beyond the planned web side panel browser.

### SHIP-02: Verification and spec gates

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. In the experimental Shipping path a configured validation profile runs before landing (default argv bun run test with a 10 minute timeout) and a failed validation holds the order. Lint, type, CI and spec conformance gates and independent review requirements were not found as product-enforced policy.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. No product-enforced verification gates: PR check state (CI) is shown, land refuses a dirty base or empty branch, and the repo's own checks are run by the agent. Independent review is a separate task the user starts.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Issues own branches and worktrees, and issue actions rebase, open a pull request with gh (pr create --fill) and merge, subject to a merge-style setting (ff-only by default, with auto-rebase before merge). Podium does not resolve branch conflicts, and PR review comments and CI response were not established.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Integrated branch and worktree per task, commits by the agent, publish pushes and opens a PR with gh, land merges or squashes locally with conflict abort, PR and CI status shown, sync for drift. Review comments and CI fixes are driven through prompts.

### SHIP-04: Merge and deployment authority

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The operator accepts work through offers and runs the merge action under a branch merge-lock; in the experimental Shipping path approval is frozen to an exact head and delivery lands on a local target branch by default. Release and deployment are not product features found in the sources.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. The local user lands and publishes; merge and deployment authority is GitHub's. No approvals, release or deploy features.

### SHIP-05: Completion evidence and rollback

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Shipping orders record approved base and head SHAs, tested integration SHA, landed ref and validation result in a durable delivery receipt, and stale approvals hold the order. Shipping is experimental. The pr action records a PR URL on the issue. Build and deployment links and rollback were not found.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Tasks link to their branch, worktree and PR with state and checks; per-turn checkpoints with rewind provide undo; no build or deployment links.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. The shipping service records revision-specific approval, configured validation and delivery receipts. The Shipping panel is an experimental edge toggle, off by default; the separate Queues panel was removed.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. The Inbox, Kanban badges and context/collect reads support a queue of finished tasks; land and publish act per task. No summaries, risk filters or dependency-aware merge queues.

## Ownership, privacy and economics

### OWN-01: Source and license

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The public repository is licensed Apache 2.0, and the website presents Podium as an open-source agent development environment. Hosted extensions and hosted-service terms are not established.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. MIT license for the whole monorepo (CLI, daemon, bridge, web, desktop, iOS, Android, plugin SDK); no hosted or closed extension.

### OWN-02: Hosting and exit

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Local desktop and self-hosted installs run on user-controlled machines with a documented state directory. The docs describe stopped full-state backup and automatic pre-migration database-only snapshots retaining three copies. Those snapshots omit artifacts, transcripts, uploads, configuration and secrets; no portable structured export/import contract was established.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Everything is self-hosted; state lives under ~/.rove and ~/.config/rove in JSON files; no vendor account or service is required. Engine conversations remain in each engine's store.

### OWN-03: Data handling and telemetry

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-21. Docs state repositories and native harness credentials stay on machines you control and server state lives in a documented directory. Since 0.2.0 a daily usage report is on by default and can be turned off; crash reports stay opt-in. Usage reports carry an install id, schema version, Podium version, OS, architecture, bucketed install age and machine count, session counts per harness and whether issues were used. Crash reports carry the same install id, versions, OS and architecture, a fixed error type and up to 20 stack frames, each with a Podium source file path, line and function when there is one; error messages and frames outside Podium are dropped. Neither tier sends prompts, transcripts, your code or paths outside the Podium source tree. Model-provider handling is the harness own. Hosted analytics and website analytics are separate paths.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Data stays on the user's machine; engine CLIs send prompts to their providers. The CLI contacts only npm and GitHub for updates and, for Claude subscribers, Anthropic's OAuth usage endpoint; mobile apps have no analytics. No analytics SDK found.

### OWN-04: Price and included usage

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. No Podium price is published: podium.do/pricing returns 404 and the docs list billing as not implemented. The software is open source and free to download; model and compute costs are the user's own.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Free open-source software (MIT); Rove charges nothing; engine subscriptions or API usage are paid to the vendors and hardware is the user's own.

### OWN-05: Scenario cost and controls

- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Rove platform fee is zero for any team size; model and compute costs depend on the engines and hardware and are not estimated.

### OWN-06: Availability and support

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium is pre-1.0. Stable v0.3.1 (2026-11-06), an update fix, follows v0.3.0 (2026-11-05), v0.2.0 (2026-10-11) and v0.1.0 (2026-08-21), with edge and dev prerelease channels. Windows and Linux desktop are Experimental, the native iPhone app is in private beta and hosted Podium is unconfirmed. Support runs through GitHub issues, Discord and private vulnerability reporting.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Generally available stable releases with very frequent -next prereleases; GitHub issues as the support channel; no response commitments; iOS and Android are source-only.

### OWN-07: Enterprise assurance

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

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium is open-source Apache-2.0 software, and the download page calls it free and open source. Download links for macOS, Linux and Windows redirect to GitHub release assets without a login (observed by HTTP requests; not installed). No Podium charge is documented for self-hosting; agent provider usage is separate. The native iPhone app is private beta and hosted access is unconfirmed.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. Entirely free: MIT open source with no card, caps or paid evaluation; engines may need their own paid subscriptions.

### OWN-09: Pricing transparency

- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
- **Rove**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-17 (5 days old); agent cross-checked 2026-11-17. No pricing exists: free open source with no units, limits, markups or minimums.
