---
schema_version: 7
rubric_version: "0.3"
canonical_url: "https://podium.do/compare/agents/dev-3-0-vs-podium/"
data_url: "https://podium.do/compare/agents/dev-3-0-vs-podium/data.json"
generated_at: 2026-11-22
last_checked_at: 2026-11-16
last_cross_checked_at: 2026-11-21
oldest_checked_at: 2026-11-06
publisher: "Podium"
---

# dev-3.0 vs Podium

> 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; 33 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.

- dev-3.0 source checks: 2026-11-16. Details: https://podium.do/compare/agents/products/dev-3-0/index.md
- Podium source checks: 2026-11-06. Details: https://podium.do/compare/agents/products/podium/index.md
- Rubric: https://podium.do/compare/agents/rubric/index.md
- Canonical HTML: https://podium.do/compare/agents/dev-3-0-vs-podium/
- Machine-readable JSON: https://podium.do/compare/agents/dev-3-0-vs-podium/data.json
- Methodology: https://podium.do/compare/agents/methodology/

## Access and agent choice

### ACC-01: Client access

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Desktop app for macOS (Apple Silicon and Intel) and Windows x64 (new, unsigned zip); headless Linux x64/arm64 and macOS dev3 server that serves the full UI to any browser including a phone (remote); dev3 CLI. No native iOS or Android app and no editor extension.
- **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.

### ACC-02: Agent and model choice

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Launches installed coding-agent CLIs in each task terminal: Claude Code, Codex, Gemini CLI, Cursor Agent, GitHub Copilot CLI, OpenCode, Pi, Oh My Pi, or any configured CLI; models come from the agent. Claude Code and Codex can run on Bedrock.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Subscriptions and API accounts are whatever each agent CLI is signed in with; dev-3.0 never resells, marks up or proxies them. Managed account profiles can be switched per agent; Bedrock supported for Claude Code and Codex; local models depend on the agent CLI.
- **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.

### ACC-04: Onboarding and project prerequisites

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Install by Homebrew, DMG, Windows zip or CLI tarball (or let an agent follow ai-install.txt), add a project pointing at a git repo, press Cmd+N, describe a task, choose an agent and Run. Works with local git repos with or without a remote; virtual Operations boards need no git repo. Headless installer for a VPS; no managed cloud.
- **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.

### ACC-05: Programmable access

- **dev-3.0**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. dev3 CLI controls tasks, epics, labels, notes, review comments, messages, automations, PRs, config, stats and remote; commands use a local socket with documented exit codes. No MCP server, REST API, SDK or inbound webhook triggers; outbound notification webhooks and exec transports can be configured in notifications.json; external senders can message tasks.
- **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.

### ACC-06: External tools and extensions

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No MCP client of its own: MCP and plugins come from the underlying agents; dev-3.0 installs dev3 skills into each agent, supports board-view extensions (unsandboxed) and a secret-run command for credentials. Instructions and skills are agent-owned.
- **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.

### ACC-07: Client implementation

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Desktop shell is Electrobun (native webview, Bun main process) with React 19 and Tailwind UI, ghostty-web terminals and tmux underneath; the browser UI is the same renderer served over WebSocket. No mobile client.
- **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.

## Planning and context

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Tasks are created locally (Cmd+N, CLI, agents creating peer tasks), from PRs or branches (pr-review type), by importing running Claude Code or Codex conversations, and by schedules. No built-in Linear, Jira or GitHub Issues import: the board is authoritative.
- **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.

### PLAN-02: Durable task plans

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Per-task description and agent-written overview, durable notes surfaced to future agents, and a board copy exported into the project; no structured acceptance criteria or plan revision history. Descriptions can be updated but a running agent does not see them until messaged.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Global epics group tasks across projects (tasks created by a task inherit its epic), start-after conditions (finish or PR merge) hold To Do tasks until prerequisites finish, coordinator-type tasks manage tasks, and variants run sibling attempts. No arbitrary parent/child tree beyond created-by parent.
- **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.

### PLAN-04: Shared context and memory

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Per-task notes (durable, newest five delivered to new sessions), agent-written overview, project config in .dev3, dev3 skills injected into each agent, search over past conversations, and the agent's own AGENTS.md and memory. No cross-project shared memory store of its own.
- **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.

### PLAN-05: Architecture and API awareness

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No code index or architecture awareness of its own: agents search the worktree; conversations search covers prior tasks; screenshots and images can be dropped into prompts and shown with show-image; no external knowledge connectors.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. The board is the native task system: cards with seq IDs, title, description, priority P0-P4, labels, type, epic, custom columns, full-text search, filters, archive/completed lists and per-task overview and notes. Agents work on cards; multiple agent panes and variants per task.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Agents use the dev3 CLI on the same task records humans use: create tasks, set overview, add notes, change status, label, set start-after and epics, message peers, read review comments and watch PRs; the UI reflects it with created-by attribution and approvals for sensitive moves.
- **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.

### PLAN-08: Living product specifications

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: unsupported. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No living product specification: board copy, notes and project config persist but there are no requirements, revisions, drift detection or review integration.
- **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.

## Coordination and automation

### COORD-01: Parallel work

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Many agents run at once, each task in its own worktree, terminal and tmux session; the board shows To Do, Agent is Working, Has Questions, AI Review, Your Review and PR Review lanes with live terminal hover preview and memory use. No fixed quota; memory pressure drives hibernation.
- **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.

### COORD-02: Ownership and dispatch

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Each task has one main agent and optional extra panes; agents can start others only with user approval; file-claim hooks keep Claude Code edits exclusive in shared folders; no human assignment or queue.
- **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.

### COORD-03: Inspectable delegation and communication

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Coordinator-type tasks manage the board with the dev3 CLI: create tasks, message live agents (now or scheduled), peek at peers' terminals read-only, spawn agent panes, read results. Agents may be different CLIs, and sender identity is attached. Product-owned role presets exist; delegation tooling is the CLI and skills.
- **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.

### COORD-04: Unattended triggers

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Project automations create real tasks on RFC 5545-style schedules (hourly, daily, weekly, monthly) with catch-up skip or run-once; messages can be scheduled to an agent; start-after chains and PR watch fire on events. The scheduler runs inside the app or headless server, so it stops when that process stops.
- **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.

### COORD-05: Intervention and attention

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Stop, pause, resume and hibernate tasks, move cards, answer agent questions (Has Questions lane), steer by typing into the live terminal or scheduled messages, approval dialogs list, bell and red badge notifications, and keep-alive for crashed agents; terminals are tmux so CLI and UI share state.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Kanban board per project with six default lanes plus custom columns, Table view, Spaces dashboard grouping projects, Activity dashboard with live agent status across projects, epic filters, PR/CI badges and productivity stats. Dependencies and blockers appear through start-after flags.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No mandatory workflow: columns are user-defined and can start agents on drop; per-task agent, preset, model, effort and system prompt; split panes with different agents or variants; changes mid-run by messaging or adding panes; agent traffic view shows who messaged whom.
- **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.

## Execution and reliability

### RUN-01: Laptop-independent execution

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Agents run on the machine hosting dev-3.0: the laptop (desktop app) or a headless Linux or macOS server reached with dev3 remote from a browser or phone. There is no vendor cloud. tmux sessions survive the client closing, so work continues on a remote host while the laptop sleeps.
- **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.

### RUN-02: Workspace and process isolation

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Each task gets its own git worktree and branch from the base branch, its own tmux session, reserved ports and per-project setup script, with copy-on-write clones of heavy directories. Not a security sandbox: agents run as the user with full permissions of their CLI; worktrees isolate files only.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Hibernate and wake save and resume the agent's exact session for Claude Code, Codex, Copilot, Pi and OMP (OpenCode most recent only); keep-alive relaunches crashed agents; tmux sessions survive app restarts; hourly state backups for projects and tasks; dev3 doctor repairs install and worktrees.
- **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.

### RUN-04: Development environment reliability

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Per-project setup script, copy-on-write cloning of node_modules/.venv, sparse checkout for monorepos, free-port pool per task, one-click dev servers with logs and verified stop, and detection of port conflicts; no shared package cache or container images.
- **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.

### RUN-05: Limits and failure handling

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No product-wide time, token or spend limit. Agents with budget flags receive them via adapters (max budget) and usage and rate-limit readings are shown; provider errors move cards to Has Questions and keep-alive retries with bounds.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Task transcripts parsed from agent logs, dev server and diagnostic logs (local, redacted), productivity and usage stats (tokens and API-equivalent cost per agent per day or per task, rate-limit windows, memory) and agent status through hooks. Status states are consistent across UI and CLI. Speed and memory benchmarks come only from ADEMark, which has no dev-3.0 entry.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Tokens and API-equivalent cost per agent per day or per task are computed from local agent transcripts and refreshed model prices (USD per 1M tokens); subscription allowance shown as rate-limit windows; no billed amounts, compute fees or budget alerts.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Memory pressure and headroom are measured and surfaced (Stats memory, card memory use) with hibernate to free memory and a PTY backpressure layer; no CPU/RAM quotas, queues or check deduplication; start-after serialises work manually.
- **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.

## Human collaboration and control

### TEAM-01: Live human collaboration

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Single-user by design: README says the unit is the individual. Anyone holding the remote URL or QR session can drive the same UI and terminals, but there are no accounts, presence, attribution or co-prompt ordering.
- **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.

### TEAM-02: Roles and access boundaries

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: unsupported. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No organization, project or task roles, SSO or provisioning: a single local user; remote access is capability-token based.
- **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.

### TEAM-03: Approvals and temporary access

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Approval dialogs for sensitive CLI moves (complete, cancel, reset, launch of other tasks, secret run) with timeouts; agent tool approvals follow each agent's own permission mode; no network or secret policy enforcement beyond those dialogs.
- **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.

### TEAM-04: Decision and activity history

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Local-only history: conversations parsed from agent transcripts, task events feed, notes, review comments with status and replies, agent traffic view, diagnostic logs with redaction, hourly state backups. No integrity guarantees or multi-user attribution.
- **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.

### TEAM-05: Review experience and guidance

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Built-in review panel: full branch diff with syntax highlighting, per-file read state, inline comments on line ranges and rendered Markdown/Mermaid/images, review exported back to the agent terminal, agent resolve/reply to comments, AI Review and Your Review lanes, bug-hunter packs, keyboard shortcuts and a PR badge flow.
- **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.

### TEAM-06: Colleague takeover and continuity

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Not a multi-person product, but a second person with the access URL can continue the same task, terminal and history from a browser since the server holds the runtime; no ownership transfer or attribution. Agent session handoff between agents exists (conversation handoff).
- **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.

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Diffs, agent-authored interactive HTML artifacts (ZIP download), images and media with captions, task overview and notes, review comments, terminal scrollback and dev-server logs; stored on the task after the session; no cross-task gallery or screenshots by the product itself.
- **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.

### SHIP-02: Verification and spec gates

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. dev-3.0 itself does not run tests or CI; agents do. AI Review lanes run reviewer agents on moved cards, bug hunters review diffs, CI badges report GitHub checks and the dev-3.0 repository enforces its own verification gates. No product-enforced required checks on delivered work.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Integrated: base-branch worktree and branch per task, agents commit, dev3 pr create pushes and opens the PR, auto-merge, CI and PR badges on cards, pr-watch messages the agent on CI or merge, PR review tasks check out PR heads including forks, git operation panes for rebase. gh is required.
- **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.

### SHIP-04: Merge and deployment authority

- **dev-3.0**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. The user approves completion in the app; dev3 pr auto-merge asks GitHub to merge when checks pass; releases and deployments are outside the product. A merged PR can complete the task.
- **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.

### SHIP-05: Completion evidence and rollback

- **dev-3.0**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. Cards link task, branch, PR and CI; start-after --until merged and merge detection can suggest completion; worktrees can be pruned or reset; no rollback or revert feature; no approval invalidation on changed revisions.
- **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.

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

- **dev-3.0**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. The board is the batch queue (AI Review, Your Review, PR Review lanes) with agent summaries, PR/CI badges, productivity stats and a reviewer agent per column; no risk filters, dependency-aware merge queue or stale-approval invalidation.
- **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.

## Ownership, privacy and economics

### OWN-01: Source and license

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Apache License 2.0 for the whole repository (desktop app, CLI, headless server); one public repository, no closed hosted component. Pinned v1.65.0.
- **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.

### OWN-02: Hosting and exit

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Everything is local or user-hosted: state lives in ~/.dev3.0 (JSON) with hourly backups, board copy can be exported into the project, conversations dump to JSON; no vendor account or service is needed; headless mode self-hosts the UI.
- **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.

### OWN-03: Data handling and telemetry

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Code, prompts, logs and artifacts stay on the machine except what the chosen agent CLIs send to their providers. Release builds send anonymous analytics to Google Analytics 4 and PostHog (no names, paths, prompts or diffs) with one switch, DEV3_TELEMETRY=off or DO_NOT_TRACK=1; a build from source has no PostHog key.
- **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.

### OWN-04: Price and included usage

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Free and open source with one edition, no paid tier, no per-seat license and no account; users pay agent subscriptions or API usage and their own hardware.
- **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.

### OWN-05: Scenario cost and controls

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Platform cost is $0 for one, two or five developers (single-user tool, no seats); model and hardware costs are the user's and not published.
- **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.

### OWN-06: Availability and support

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Generally available open-source desktop and headless software with several releases a week (v1.65.0 on 2026-11-12), a canary channel, issue tracker and no documented support SLA or status page. Windows support is explicitly labelled brand new.
- **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.

### OWN-07: Enterprise assurance

- **dev-3.0**: 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.
- **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.

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

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Fully free ongoing: whole app free with no trial, card, seat or usage cap; costs are the agent subscriptions and hardware. Two-person collaboration is not a feature; BYO subscriptions, remote (own server), phone browser, issue management (board) and review all work free.
- **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.

### OWN-09: Pricing transparency

- **dev-3.0**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Transparent: the product is free with no tiers; agent costs are billed by providers without markup; no minimum commitment, overage or cancellation terms apply.
- **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.
