podium

nodeterm
vs Podium

A source-linked comparison across the complete Podium ADE rubric. 48 criteria sourced for both products; 37 criteria also agent cross-checked for both. 51 rows have at least one sourced finding, including 50 with an agent-cross-checked finding. No score or winner is inferred.

Each row shows a finding's verification status, support, check date and answer. Its scope, limitations, atomic answers and sources are on the product's page. Humans approve the rubric, templates and prototype; they do not review every finding. An agent source cross-check is not a hands-on product test. A missing sourced finding is not evidence that a capability is absent.

Rubric
0.3 · 51 criteria
Last source check
2026-11-12
Oldest source check
2026-11-06 (16 days old)
Agent cross-checked for both
37 criteria
nodeterm source checks
2026-11-12
Podium source checks
2026-11-06

Access and agent choice

ACC-01

Client access

nodeterm

Sourced partial

Desktop Electron app on macOS 12+ (Apple Silicon/Intel, auto-update + Homebrew), Linux x64 (AppImage self-updating, .deb/.rpm manual), Windows x64 beta (unsigned exe/zip, manual updates, session continuity landing). Server Edition runs the same canvas in any browser. iOS App Store + Android Play companions attach to live sessions (no canvas on phone). In-app palette + ⌘K creates/starts/steers; OS + push notifications; phone continues desktop sessions. Unresolved contradiction (checked 2026-11-13): the live FAQ denies Windows support while README v0.5.1 and the releases page ship Windows x64 beta installers.

Checked 2026-11-12 (10 days old). Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

Runs real coding-agent CLIs as node startup commands with hook-driven status: built-ins Claude Code, Codex, Antigravity, Gemini, opencode, Grok, Copilot, Cursor plus user-defined custom agents (any CLI, process/title status only). Underlying CLIs keep their own providers; mixed agents share one canvas with cross-agent context links.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium launches the native Claude Code, Codex, Grok, OpenCode, Cursor and Pi CLIs in persistent terminals on machines you control. The 0.2.0 release calls Pi fully supported. Models come from each harness catalog, and capabilities differ per harness: Pi declares no quota, handoff or hooks. Mixed-harness operation was not exercised.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Bring your own everything: existing Claude subscriptions via managed accounts (Max/Org side by side) or system login; other agents via their own CLI logins/API keys. No vendor credits or model markup. On-device Whisper for dictation only. No nodeterm account exists; local work needs nothing.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium supports native coding-agent logins and managed provider credentials. Claude subscriptions (via native login or a managed setup-token) and local ChatGPT/Codex login are supported paths, alongside Anthropic and OpenAI API keys. Docs list billing and hosted metering as not implemented product claims.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Install the app, open a folder, right-click for terminal/agent: five-minute path. Plain folders work without Git; local Git without remote works with git panel; GitHub-backed adds gh sign-in + Issues lane. Prerequisites (tmux, Node, agent CLIs) documented. No managed cloud; BYO VPS via Server Edition Docker/checkout/one-line install.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

No public user API; programmatic surfaces are scoped: server-admin team CLI over admin socket, agent-facing canvas-control verbs (cards/issues/triggers), Claude Agent SDK-driven chat nodes, internal push-webhook management routes. GUI/palette is the user interface.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

The podium CLI covers issue create, show, update, claim, dependencies, artifacts, session send/status/read/stop and review actions, and the server exposes the same issue commands as a bearer-token MCP tool endpoint. No documented public HTTP API, SDK or webhooks were found.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Product-managed connections: GitHub (gh/PAT), hook installers per agent CLI, agent skills (canvas-control, linked-context), trigger/canvas verbs; inherits MCP/plugins from underlying CLIs (⌘M lists enabled plugin skills). No product MCP client; approvals via hooks + permission modes + host-enforced roles.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium gives agents its own issue tools over CLI and MCP, and agent profiles import and export Claude Code agent files. No Podium documentation for user-configured MCP clients, plugins or custom tools was found.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Scope and sources

nodeterm

Agent cross-checked partial

Desktop is Electron (main/preload/React renderer/xterm, CorePlatform seam abstracting Electron vs Server shells). iOS companion is SwiftUI; Android app exists (implementation not established). Same renderer served over WebSocket-RPC in Server Edition.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Desktop releases use a Tauri 2 shell that serves the Podium web UI; mobile source uses Expo and React Native. A native iPhone release is described as private beta.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

Planning and context

nodeterm

Agent cross-checked partial

Cards are live sessions; GitHub Issues attach as an opt-in lane (exact label↔column mapping, two-way move/close/reopen sync, GitHub stays source of truth, PRs excluded). Prompt intake via triggers/palette; project.json adopted from git shares layouts.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium issue records are native and authoritative with stable references, CLI creation and editing, and agent-driven filing from conversation. The in-product assistant has Linear search, create and move tools when a key is configured, but no import or two-way tracker sync was found.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Cards + sticky notes + editor carry task context on a durable board: live-session cards with metadata, amendable mid-run (drag while agent keeps running), revision via project.json hot-reload + conflict bar and layout undo. No explicit acceptance-criteria field.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Issue brief, acceptance criteria, state paragraph and todos persist on the durable issue record. Release 0.3.0 removed the separate design and notes fields and appended their text to the brief. On the human issue page the title, description and acceptance are editable and the brief is read-only; agents edit the brief and other fields through issue commands.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources

nodeterm

Agent cross-checked partial

Hierarchy is spatial, not enforced: group frames (optionally worktree-bound) hold nodes; subagent fan-out is display-only; blockers surface as NEEDS YOU badges, never gates. Cards graduate across columns keeping identity/sessions/outputs.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium supports persistent parent and child issues, phases and typed dependency links, including reparenting an existing issue without replacing its identity. Since 0.3.0 issue types are task, phase and decision: epic and other kinds are retired, and any issue with children acts as a parent. Dependency types are fixed to blocked-by, related, discovered-from, supersedes and duplicates. Cycles are refused and docs list an open blocker as a reason an issue cannot start. No mandatory workflow preset applies in the baseline.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Instructions (AGENTS.md notes, stickies), skills (Claude skill + canvas verbs + harness plugins), project docs (Explorer/monaco/markdown) and pull-on-demand context links. No managed cross-session memory; recall is transcripts + snapshots + mirror, surviving handover via git-shared project files.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

Retrieval is terminal-and-file centric: lazy Explorer, ⌘K file + terminal-output search, file links, web/video nodes, image paste. Freshness/index scope unstated; no citations, no review-time enforcement; conflicts converge rather than resolve.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

Trello-style board where cards are live sessions: create/edit/discuss (comments)/prioritize/label/assign/search/filter, All/GitHub/Sessions views, idea parking via Ungrouped/stickies, explicit human dispatch (done stays human), durable column states with RUNNING chips. GitHub lane optional; issue content editing planned.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium exposes native issue creation with an optional start flag, separate dispatch, editing, comments, labels, assignment, search, board filters, archive, sibling ordering and an issue tree. Issue records have their own identity separate from sessions and stages are durable. The idea-to-mission scenario was not run. v0.3.0 refuses an agent close or done update while issue sessions are computing unless --confirm-interrupt is supplied; guidance says to request review and close only on user instruction.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Agents operate the same cards humans see: read linked transcripts, move own session cards (assign), spawn teams, report outcomes — with human-visible typing/activity and done-stays-human guardrails. GitHub lane is read-only for agents; dependencies/claims unsupported.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

CLI and MCP address the same canonical issue records for reads, creation, edits, claims, state, dependencies and artifacts. Relayed agents have worker capability scoped to their issue subtree, with --outside-scope confirmation for other existing issues. attachSession is not subtree-gated, but direct rehoming from a real issue is refused and an agent attach naming a Proposed target is refused. That does not make every Proposed subtree inert: operator attachment or spawn-time cwd binding can leave a session attached to a Proposed issue; newSubissue without targetId then bypasses the proposed-parent guard, creates a human-audience backlog child and attaches the existing session. This path remains at v0.3.0 source and was not exercised live. Concurrent-edit handling remains unknown.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked unsupported

No living product specification exists: sticky notes, editor docs and project files are unreferenced working material with no requirement linking, retrieval, drift detection or review integration. Bounded pass found no spec entity.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

Coordination and automation

COORD-01

Parallel work

nodeterm

Agent cross-checked partial

Many live tmux sessions run concurrently on one canvas (95 Claude processes measured on one host), all visible with RUNNING/NEEDS YOU states via badges, board chips, notch and minimap. Reaping only under memory pressure; no documented concurrency quota.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Docs and release notes describe many sessions running as independent terminals, one worktree per issue, and several paired machines under one server, with session and issue state visible on the flight deck, board and CLI. Agent-initiated spawns are limited to 10 per target issue per UTC day. Achieved concurrency is unmeasured.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Humans assign via card members + Team Access seats; agents move own cards via assign verb. Ownership is advisory (typing badges, activity) except host-core role enforcement on team canvases. No queues, routing, or duplicate-prevention beyond conflict guards.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Issues carry an assignee, claim sets assignee and in_progress, a coordinator session can be set per issue, sessions have seats, and work can be placed on a chosen machine or agent profile. claim has no exclusivity check of its own, locks are advisory leases and Podium does not serialize agents editing one worktree, so exclusive ownership is not enforced.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

User is the coordinator on a shared canvas; agents coordinate via product verbs (spawn teams, assign own cards, message via cursor chat/context reads, report outcomes) plus harness-native subagents (display-only fan-out). Cross-harness reads across all four built-ins; live progress everywhere; results retained as transcripts/reports.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium orchestrates delegation itself: podium agent spawn starts a full child session on an issue with a chosen harness, model, effort or agent profile, mail carries messages, and bounded await reports the child result. Children are real sessions shown as seats on the flight deck. Agent-initiated spawns take a daily budget per issue. A complete delegated task with retained child findings was not run.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Canvas-owned trigger nodes (cron/interval/once) with local arming consent, 30s sweep, no catch-up, idle-gated delivery; recurring /loop + /schedule + /cron cards. Server Edition fires headless; desktop closed fires nothing. No external event sources or OS schedulers yet.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

Steer by typing (canvas/phone/Control link/cursor chat); stop via node × (kills tmux), Esc interrupt in chat, trigger disarm; resume via warm reattach/--resume/chat session id. NEEDS YOU + Approve/Deny + push covers pending decisions. No general pause; errors surface via badges, missed-rings and troubleshooting.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Chat and native CLI views share a session. v0.3.0 defaults human controller chat to steer and immediately types it into running Claude Code, Codex, Grok and OpenCode TUIs that declare native busy-input queuing; undeclared harnesses wait for a boundary, and compaction waits. Mail and automation keep when-ready delivery. Stop, resume, questions, decision issues and offers remain available. This is inspected implementation, not a cross-harness runtime parity result.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Kanban board is the fleet view: To Do/In Progress/Done columns with counts, RUNNING/progress/priority/due chips, member avatars, GitHub lane, workload hints via RAM pill. Blockers/dependencies/history-navigation beyond activity feed were not established as board features.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Release 0.3.0 ships a flight deck showing a whole mission in one view: phases, every task and its state, who works on what, what is blocked and by what, and proposals. Done work stays visible. The CLI prints the same snapshot. The waterfall source is dormant and the Timeline view was deleted, so per-task timeline history is not shown. The shared 12-task UX scenario has not been run.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources

nodeterm

Agent cross-checked partial

No mandatory workflow: any terminal/agent/note/editor/diff/chat from menus, palette or dock; context links and triggers configured in plain UI with confirm dialogs; per-node agent/account/permission choice; changes mid-run allowed; canvas + board + mirror expose what ran (coordinator/subagent roles, relationships, results).

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

A quick task can be an interactive session or an issue; an issue can grow into a mission by gaining children while keeping its identity; no mandatory workflow preset applies in the baseline. Per-agent harness, model and effort are chosen at spawn or through agent profiles, and the deck shows seats. The coordinator-with-two-reviewers scenario was not run.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

Execution and reliability

nodeterm

Agent cross-checked partial

Local tmux execution; BYO remote over SSH projects or self-hosted Server Edition (VPS/homelab/Docker); no vendor cloud. Server/SSH hosts keep running detached from the client; phone/browser reach them from anywhere via relay. Closed laptop sleeps (no lid-closed execution); overnight runs belong on a non-sleeping box.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

Isolation is Git-level, not security-level: main checkout or bound worktree per scope, branch per group, tmux session per node, secrets in keychains/0600 files, team roles + E2EE relay. No containers/VMs/OS sandboxes per task; no hostile-code containment claim.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

Podium separates issue files with Git branches and worktrees, but its released daemon launches native host processes without product-managed container or VM provisioning.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

Quit/detach warm-reattaches; reboot cold-restores via 256KB scrollback snapshots + per-agent --resume relaunch; offline SSH cache reconciles newer-wins; missed trigger fires logged honestly. Container redeploys and Windows-beta restarts lose running processes; subagent cards clear.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Closing a browser tab does not stop the agent process on a running Podium host. Idle sessions may hibernate under configurable policies; a stopped session keeps its transcript, branch and resume reference. Release 0.2.0 says a failed update rolls back and running sessions keep running through the upgrade; database rollback remains a manual restore. Terminal reattachment goes through the driver adopt contract with process-identity and observation-lease checks. Worker-crash and multi-day behavior were not tested.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Dependency setup is documented BYO (tmux, Node, git, agent CLIs) with degraded fallbacks; secrets handled via keychains; single-port + ControlMaster + install script simplify remotes. No snapshot services, port management, collision handling or auto-repair beyond reconnect/reconcile.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Only machine setup is documented: the installer installs missing runtime tools and pairs a host, and the state directory holds server-managed secrets. Dependency caching, services, ports and automatic repair for project environments were not found.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Budgets are about resources, not spend: memory-pressure session reaping, trigger TTLs, fetch/probe timeouts, delivery queues. Usage/context meters inform; no time/turn/token/spend caps or provider-failure policy beyond degraded fallbacks.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium exposes retryable errors, optional auto-continue with backoff, bounded waits and provider quota. Claude stream and hosted headless drivers enforce a supplied turn deadline, with no deadline when timeoutMs is absent. The one-shot headless server runner supplies its budget, default ten minutes. Agent spawns have a daily per-issue budget. Operator-configurable task-wide turn, token and spend caps remain unestablished; quota display is not enforcement.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Truth comes from hooks, not scraping: normalized working/waiting/blocked/done states on badges/cards/notch/mirror/inbox, typing attribution, missed/failed rings, troubleshooting causes. Stats are live-state + resource/usage displays; no exports, no measured speed claims.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium offers local logs and crash export, structured session status, issue stats, a usage and analytics sheet with hourly list-price cost, per-task costs and host load panels. The 0.3.0 notes report a vendor benchmark of about 330 MB server memory against about 1.2 GB for an earlier Podium build, and 8 to 52 percent faster start; the method is published in the repository and was not reproduced here. Usage export and cross-reconnect consistency were not established.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources

nodeterm

Agent cross-checked partial

Cost visibility is conversational, not accounting: chat cost chip (running total), context meters, subagent token/duration cards, per-account provider usage in inbox. No billed-vs-estimated reconciliation, compute costing, alerts, export or drill-down.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Since 0.2.0 Podium shows what each task costs, on the task header and the usage sheet, with per-session rows and descendant rollups. The 0.3.0 deck adds a mission cost chip. Figures are token estimates at public model list prices, not subscription invoices or provider bills.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Scheduling exists for triggers (30s sweep, exactly-once slots, TTL queues, gradual budget reaping) and backpressure for co-attach (8MB drop-and-redraw). No fleet concurrency limits, fairness, host-aware scheduling, or check dedup.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium reports host memory, load and disk, auto-hibernates idle sessions under pressure, and provides named advisory resource leases. The merge-queue panel was removed; a shipping queue remains behind the Shipping flag. Concurrency limits and bounded test queuing were not established.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

Human collaboration and control

nodeterm

Agent cross-checked partial

Small-team multiplayer on one canvas: live cursors + cursor chat, facepile, per-node who-is-here chips, terminal co-attach with typing attribution (no locking), shared issues/cards. Team Access is Pro by seat; owner laptop must be awake unless a standing hosted relay is used.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

The issue UI displays owner and visibility read-only and deliberately omits sharing controls. Backend share handlers and a Members settings section with invites and admin or member roles exist; they do not establish a finished human collaboration workflow. Docs say small teams can share an instance but the interface prioritizes one operator.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

No organizations, no SSO, no SCIM: identity is the device, trust is per-invite SAS + approval. Project roles (Viewer/Commenter/Editor/Owner) enforced in host core on hosted teams; membership pinned in team.json with immediate revocation. Pro scopes seats.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

Approvals ride the agent hooks: Claude permission modes (manual/auto/acceptEdits/plan/bypass), deterministic hook Approve/Deny incl. phone, in-chat tool cards, read-only AI-commit flow. Defaults are permissive (auto); safer modes available; enforcement is hook-level for Claude, advisory elsewhere.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

Attribution is live and lightweight: typing badges, assign/move activity in card modal, hook account labels, canvas sync of edits. History persists in transcripts/snapshots/project files. No audit log with retention/integrity model; no history export. The word audit is not used.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Sourced partial

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.

Checked 2026-11-06 (16 days old). Scope and sources

nodeterm

Agent cross-checked partial

Review starts at NEEDS YOU: badges/unread/notch/notification jump straight to the node; card modal opens the live session with members/due/comments/activity; diff nodes + file links + recent commits supply evidence; ⌘K/shortcuts throughout. No guided batch-review flow; narrow-screen/keyboard completeness unverified without fixture.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Review is a documented loop: issue stage review, diff and checks, artifacts, offers with merge or send-back buttons, and a Tray of review-ready work. Release 0.3.0 adds quoting text from a reply or review finding into the next message and a full-height reading view with an outline. The board has a key map with a help sheet. Guided-review quality and narrow-screen use were not measured.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Takeover is a first-class flow: equal-peer Team Access (same canvas/sessions/history), phone attach to live sessions, hosted relay surviving owner disconnect, per-host accounts + runtime intact. Harness transfer (hand thread to another model) not established.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

The durable issue, session transcript, artifacts and mail persist for any later agent, and a live session can be handed to another machine in an edge feature. Colleague takeover by a second person was not established.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

Verification and delivery

nodeterm

Agent cross-checked partial

Artifacts live where work happens: diff nodes, Monaco files, pasted/dropped images, markdown previews, live terminal output, subagent transcripts, chat cost/thread, recent commits. No gallery, no recordings, no revision-linked artifact store; subagent cards are ephemeral by design.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Artifact commands store immutable server-side copies of issue-linked files, including images, video, HTML and documents, which render in the issue sidebar and offers and stay readable after the worktree is gone. Each task has an artifacts page grouped into screens, documents and reports, with filters and search. Revision linking remains untested.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Scope and sources

nodeterm

Agent cross-checked unsupported

No verification or spec gates: no required tests/lint/types/CI/independent review, no blocking on failure or spec conflict. Agents can run checks ad hoc in terminals; merge/push dialogs confirm but enforce no policy.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

In the experimental Shipping path a configured validation profile runs before landing (default argv bun run test with a 10 minute timeout) and a failed validation holds the order. Lint, type, CI and spec conformance gates and independent review requirements were not found as product-enforced policy.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Git-native delivery via panel + worktrees: branch switch/create, worktree-per-group, stage/commit/push/sync/publish, gh sign-in, merge-back with confirm. PRs are read-only for agents and terminal-driven for humans; no product PR creation, CI response, or rebase.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-17. Scope and sources

Podium

Agent cross-checked partial

Issues own branches and worktrees, and issue actions rebase, open a pull request with gh (pr create --fill) and merge, subject to a merge-style setting (ff-only by default, with auto-rebase before merge). Podium does not resolve branch conflicts, and PR review comments and CI response were not established.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Authority is human and local: merge confirm dialogs, push opt-in, done-stays-human, per-project GitHub approval, host-core team roles. No release/deploy flow, no exact-revision approval, no policy engine beyond hooks + roles.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

The operator accepts work through offers and runs the merge action under a branch merge-lock; in the experimental Shipping path approval is frozen to an exact head and delivery lands on a local target branch by default. Release and deployment are not product features found in the sources.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Delivery status reads off the board (columns, RUNNING chips, progress %) with retained transcripts/snapshots/commits; undo + discard + unbind-keep-branch soften mistakes. No task→PR/build/deployment links, no rollback/revert, no stale-approval invalidation beyond per-turn hooks and content-bound trigger consent.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Shipping orders record approved base and head SHAs, tested integration SHA, landed ref and validation result in a durable delivery receipt, and stale approvals hold the order. Shipping is experimental. The pr action records a PR URL on the issue. Build and deployment links and rollback were not found.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

The kanban board doubles as the review queue (columns, filters, RUNNING/priority/due chips, card modal with live session + comments + activity, diff nodes). No batch summaries, risk filters, retained reviewer findings, exact-revision approvals, merge queues or check dedup.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

The shipping service records revision-specific approval, configured validation and delivery receipts. The Shipping panel is an experimental edge toggle, off by default; the separate Queues panel was removed.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Scope and sources

Ownership, privacy and economics

nodeterm

Agent cross-checked partial

Single BUSL-1.1 codebase (Licensor Enes Kirca): desktop, server, hosted extensions share the license; source fully visible on GitHub at pinned v0.5.1; each release converts to MIT 4 years after publication. Server Edition is same-core but Phase-2 scoped (no assign verb), so hosted parity is partial.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

The public repository is licensed Apache 2.0, and the website presents Podium as an open-source agent development environment. Hosted extensions and hosted-service terms are not established.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Self-host everything: desktop local, Server Edition on own box (data in ~/.nodeterm-server volume), SSH hosts user-controlled. Vendor services (relay, push, update/check feeds) are optional assists; offline works. History travels via git-shared project.json; transcripts stay machine-local; uninstall script inventories removal.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Local desktop and self-hosted installs run on user-controlled machines with a documented state directory. The docs describe stopped full-state backup and automatic pre-migration database-only snapshots retaining three copies. Those snapshots omit artifacts, transcripts, uploads, configuration and secrets; no portable structured export/import contract was established.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources

nodeterm

Agent cross-checked partial

Content stays on user machines (code/prompts/credentials/logs/artifacts never collected; only in-transit notification text passes the push server, unstored). Anonymous telemetry ON by default with Settings/env off-switch; update/check calls always on; relay E2EE with metadata visible; subprocessors: Stripe, GitHub CDN, Android FCM/ML Kit, OS speech services.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Docs state repositories and native harness credentials stay on machines you control and server state lives in a documented directory. Since 0.2.0 a daily usage report is on by default and can be turned off; crash reports stay opt-in. Usage reports carry an install id, schema version, Podium version, OS, architecture, bucketed install age and machine count, session counts per harness and whether issues were used. Crash reports carry the same install id, versions, OS and architecture, a fixed error type and up to 20 stack frames, each with a Podium source file path, line and function when there is one; error messages and frames outside Podium are dropped. Neither tier sends prompts, transcripts, your code or paths outside the Podium source tree. Model-provider handling is the harness own. Hosted analytics and website analytics are separate paths.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-21. Scope and sources

nodeterm

Agent cross-checked partial

Core free, no trial, no credits. Paid surface: Team Access seats $5/seat/month; Pro (unlimited relay + teams) priced at purchase (desktop Stripe; iOS App Store monthly/yearly/lifetime, Apple terms incl. 24h-advance renewal/cancel). Base desktop Pro price and iOS price points are not public on first-party pages. Model/compute spend is BYO and excluded.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

No Podium price is published: podium.do/pricing returns 404 and the docs list billing as not implemented. The software is open source and free to download; model and compute costs are the user's own.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Workload scenarios are seat-arithmetic plus BYO unknowns: 1 dev free (core + 5 relay bridges/mo); 2 devs collaborate via Team Access seats ($5/seat/mo → $10/mo vendor) + own models/compute; 5 devs → seats ×5. No fixed task/token/compute-hour assumptions published; base Pro price, iOS prices, model and compute costs unknown.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

nodeterm

Agent cross-checked partial

Early access v0.5.1 (2026-11-06; pushed 2026-11-12; frequent updates, auto on macOS/AppImage, manual on deb/Windows). No gated access. Support: support@nodeterm.dev (1-2 business days) + GitHub Issues + troubleshooting docs; no SLA, no status page, no deprecation/export program beyond uninstall inventory.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium is pre-1.0. Stable v0.3.1 (2026-11-06), an update fix, follows v0.3.0 (2026-11-05), v0.2.0 (2026-10-11) and v0.1.0 (2026-08-21), with edge and dev prerelease channels. Windows and Linux desktop are Experimental, the native iPhone app is in private beta and hosted Podium is unconfirmed. Support runs through GitHub issues, Discord and private vulnerability reporting.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked unsupported

No enterprise assurance claims: bounded pass over the public repo (v0.5.1), docs site, privacy policy and terms found no ISO certification, SOC 2 attestation, certificate access, or audit report. Security posture is described (E2EE, keychains, 0600 files) without third-party certification.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

nodeterm

Agent cross-checked partial

Ongoing free core (no account, no card): desktop + Server Edition + phone attach, 5 relay bridges/mo, LAN/pairing always free. No trial/credits/paid-only gate. Dormant project-allowance design (FREE 5 when cutoff set) does not bind today. Two-person collaboration needs paid Pro seats; evaluation needs no purchase or sales call.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

Agent cross-checked partial

Podium is open-source Apache-2.0 software, and the download page calls it free and open source. Download links for macOS, Linux and Windows redirect to GitHub release assets without a login (observed by HTTP requests; not installed). No Podium charge is documented for self-hosting; agent provider usage is separate. The native iPhone app is private beta and hosted access is unconfirmed.

Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources

nodeterm

Agent cross-checked partial

Partially specified: units are seats, relay bridges, open projects, live links; seat price and free quotas public; no overage billing (decline, not charge), no compute/model markup (BYO), cancel via Stripe/Apple; base Pro + iOS prices and commitment/tax details live behind checkout. No quote-only enterprise tier.

Checked 2026-11-12 (10 days old); agent cross-checked 2026-11-13. Scope and sources

Podium

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.