---
schema_version: 7
rubric_version: "0.3"
canonical_url: "https://podium.do/compare/agents/podium-vs-termic/"
data_url: "https://podium.do/compare/agents/podium-vs-termic/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"
---

# Podium vs Termic

> 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; 32 criteria also agent cross-checked for both. 50 criteria with a sourced finding for at least one product. "Sourced" findings passed publication validation. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. Humans approve the rubric, templates and prototype; they do not review every finding. It does not declare a winner. A missing sourced finding is not evidence that a capability is absent.

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

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

## Access and agent choice

### ACC-01: Client access

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium ships desktop, CLI and browser clients, including phone-browser control. The native iPhone app is private beta; the complete download offering contains no native Android app.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Desktop app: macOS 12+ (universal), Linux x86_64 AppImage, Windows 11 x64 (experimental). The termic CLI and an MCP endpoint drive the running app; a phone companion is planned only. No browser client and no editor extension.

### ACC-02: Agent and model choice

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium launches the native Claude Code, Codex, Grok, OpenCode, Cursor and Pi CLIs in persistent terminals on machines you control. The 0.2.0 release calls Pi fully supported. Models come from each harness catalog, and capabilities differ per harness: Pi declares no quota, handoff or hooks. Mixed-harness operation was not exercised.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Spawns the real agent CLIs in PTYs: claude, codex, antigravity (agy), copilot, grok, opencode, pi, omp, Muse Code, Devin and Cursor CLI built in, with an editable registry for aider, local models or scripts; models and effort selectable per tab. No embedded harness or SDK.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium supports native coding-agent logins and managed provider credentials. Claude subscriptions (via native login or a managed setup-token) and local ChatGPT/Codex login are supported paths, alongside Anthropic and OpenAI API keys. Docs list billing and hosted metering as not implemented product claims.
- **Termic**: 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 user's own Claude Pro/Max, Codex or other CLI login; several logins per agent can be switched per task; Termic never sees credentials, adds no markup, and has no account. API keys and local models depend on the agent CLI.

### ACC-04: Onboarding and project prerequisites

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Docs describe a first-run flow (install, podium, register a Git repository, confirm a detected logged-in harness) and a headless VPS installer with machine joining. Setup time and failure rate were not measured, and no self-serve managed cloud setup is documented. The current README and installation guide use podium.do/download and podium.do/install.sh as the canonical stable entrypoints.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Install by Homebrew cask, DMG, AppImage script or Windows installer, add a project (pick a folder, clone a URL, or turn a plain folder into a repo), press Cmd+N and choose an agent. Works with local repos without a remote, plain folders (converted to git) and GitHub, GitLab and Azure DevOps repos. No managed cloud and no VPS installer.

### ACC-05: Programmable access

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The podium CLI covers issue create, show, update, claim, dependencies, artifacts, session send/status/read/stop and review actions, and the server exposes the same issue commands as a bearer-token MCP tool endpoint. No documented public HTTP API, SDK or webhooks were found.
- **Termic**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. termic CLI (new, tab, send, status, wait, result, review and more, JSON/NDJSON output and exit codes) and an MCP server with matching tools and bearer-token auth, reachable from another device when allowed; no public HTTP API, SDK or webhooks.

### ACC-06: External tools and extensions

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Podium gives agents its own issue tools over CLI and MCP, and agent profiles import and export Claude Code agent files. No Podium documentation for user-configured MCP clients, plugins or custom tools was found.
- **Termic**: 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: the agents bring MCP; Termic keeps skills, MCP servers and personas once per profile and adds them to claude, codex and .agents-reading agents. Own MCP endpoint is an inbound server. Secrets roles let caged agents use credentials without holding them.

### ACC-07: Client implementation

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Desktop releases use a Tauri 2 shell that serves the Podium web UI; mobile source uses Expo and React Native. A native iPhone release is described as private beta.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Tauri 2 desktop shell (Rust, native webview) with a React and xterm.js (WebGL) UI; no mobile client yet.

## Planning and context

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium issue records are native and authoritative with stable references, CLI creation and editing, and agent-driven filing from conversation. The in-product assistant has Linear search, create and move tools when a key is configured, but no import or two-way tracker sync was found.
- **Termic**: 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 from a fresh or existing branch, an issue, a pull request or an existing worktree; GitHub and GitLab issues and PRs arrive as a composed prompt the user reads first; Todos lists issues and PRs across projects. Linear is planned. The forge stays authoritative for issues.

### PLAN-02: Durable task plans

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Issue brief, acceptance criteria, state paragraph and todos persist on the durable issue record. Release 0.3.0 removed the separate design and notes fields and appended their text to the brief. On the human issue page the title, description and acceptance are editable and the brief is read-only; agents edit the brief and other fields through issue commands.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No structured plans: Markdown plan files render as a reader/review surface with inline comments, scratchpads hold agent plans and reports, and the agent's own plan mode applies. Review comments batch into one message to the agent.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium supports persistent parent and child issues, phases and typed dependency links, including reparenting an existing issue without replacing its identity. Since 0.3.0 issue types are task, phase and decision: epic and other kinds are retired, and any issue with children acts as a parent. Dependency types are fixed to blocked-by, related, discovered-from, supersedes and duplicates. Cycles are refused and docs list an open blocker as a reason an issue cannot start. No mandatory workflow preset applies in the baseline.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Tasks started by an agent gather under it as a named coloured group; schedules produce grouped runs; multi-repo tasks group several repos under one task; no epics, blockers, readiness or dependency enforcement.

### PLAN-04: Shared context and memory

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. v0.3.0 routes Podium issue instructions and relay environment through terminal and engine session launch. Claude stream sessions use appended instructions and boundary callbacks; Codex server sessions use developer instructions, Grok ACP uses rules, and OpenCode uses the prompt system field. Claude and Codex boundary hooks can re-prime after compaction. Transcript mirroring is on by default; full-text indexing needs the command-palette flag, which defaults off. Agent profiles can carry markdown instructions. Curated memory, skills and memory correction or deletion controls remain unestablished. No instruction-delivery or compaction scenario was run.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Per-profile skills, MCP servers and personas applied to tasks, .termic.yaml config as code, scratchpads shared per task, project, profile or global, a prompt library and the agents' own memory. Archived tasks keep history searchable by PR number.

### PLAN-05: Architecture and API awareness

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Not established. Podium mirrors daemon transcripts by default, keeps a full-text index only when the command-palette flag is on, and stores session attachments. No repository code search, architecture awareness or API retrieval feature was found.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Fuzzy file finder, find-in-files over ripgrep or git grep, CodeMirror with language servers for eight toolchains and inline git blame; no repository index or external knowledge connectors; images render inline in terminals.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium exposes native issue creation with an optional start flag, separate dispatch, editing, comments, labels, assignment, search, board filters, archive, sibling ordering and an issue tree. Issue records have their own identity separate from sessions and stages are durable. The idea-to-mission scenario was not run. v0.3.0 refuses an agent close or done update while issue sessions are computing unless --confirm-interrupt is supplied; guidance says to request review and close only on user instruction.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Tasks are persistent worktree records with name, branch, agent tabs, PR, group, archive and history; the sidebar filters by project, agent, status and PR; a Kanban board derives columns from live terminal state. No priority, labels or assignment; idea backlog not provided; Todos list external issues and PRs.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. CLI and MCP address the same canonical issue records for reads, creation, edits, claims, state, dependencies and artifacts. Relayed agents have worker capability scoped to their issue subtree, with --outside-scope confirmation for other existing issues. attachSession is not subtree-gated, but direct rehoming from a real issue is refused and an agent attach naming a Proposed target is refused. That does not make every Proposed subtree inert: operator attachment or spawn-time cwd binding can leave a session attached to a Proposed issue; newSubissue without targetId then bypasses the proposed-parent guard, creates a human-audience backlog child and attaches the existing session. This path remains at v0.3.0 source and was not exercised live. Concurrent-edit handling remains unknown.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Agents operate on tasks through the termic CLI or MCP: create tasks, prompt peers, wait and read results, review, archive, rename and group; shared task IDs and group membership are visible in the UI. No issue fields or dependencies exist to write.

### PLAN-08: Living product specifications

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The spec CLI and service (living specs under pspec with stable SP IDs) are in v0.3.0. Specs is an experimental, default-off feature listed on the edge channel: the flag controls the Specs UI, the spec line in CLI help and whether agents are told about the spec CLI. The podium spec command itself is dispatched, and the server specs service has no flag check, so direct CLI use does not need the flag. This agrees with the docs, which call specs not baseline rather than blocked. Not run end to end.
- **Termic**: 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: docs/plans and docs/ideas are Termic's own repository docs, not a feature; no requirements, revisions, drift detection or review integration.

## Coordination and automation

### COORD-01: Parallel work

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Docs and release notes describe many sessions running as independent terminals, one worktree per issue, and several paired machines under one server, with session and issue state visible on the flight deck, board and CLI. Agent-initiated spawns are limited to 10 per target issue per UTC day. Achieved concurrency is unmeasured.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Many agents run in parallel, each task in its own worktree with several tabs; the sidebar and Kanban board show working, needs-you, in-review and settled counts; the Activity view lists CPU and memory per agent. No documented concurrency quota.

### COORD-02: Ownership and dispatch

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Issues carry an assignee, claim sets assignee and in_progress, a coordinator session can be set per issue, sessions have seats, and work can be placed on a chosen machine or agent profile. claim has no exclusivity check of its own, locks are advisory leases and Podium does not serialize agents editing one worktree, so exclusive ownership is not enforced.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. A task belongs to one worktree with one or more agent tabs; spawned tasks are grouped under their creator; no queues, claims or routing, and duplicate work is not prevented beyond separate worktrees.

### COORD-03: Inspectable delegation and communication

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium orchestrates delegation itself: podium agent spawn starts a full child session on an issue with a chosen harness, model, effort or agent profile, mail carries messages, and bounded await reports the child result. Children are real sessions shown as seats on the flight deck. Agent-initiated spawns take a daily budget per issue. A complete delegated task with retained child findings was not run.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. The CLI and MCP let an agent inside a task create other tasks (joining its group), send prompts, wait, read results and diffs; inter-agent messages are signed; the agent chooses agent, model and reasoning arguments. Dedicated coordinator roles and orchestration shapes are an idea, not shipped.

### COORD-04: Unattended triggers

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The server owns a scheduler for cron and one-time automations that spawn agent sessions, skipping overlaps and not backfilling occurrences more than an hour late. The Automations UI is an edge-visibility feature that defaults off and docs list automations as non-baseline. Agents can subscribe to issue and session events.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Scheduled tasks run daily, on weekdays, weekly or once with a report per run and catch-up for missed slots; manageable from CLI and MCP. They run inside the desktop app, so a closed or sleeping computer misses them (keep-awake can help).

### COORD-05: Intervention and attention

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Chat and native CLI views share a session. v0.3.0 defaults human controller chat to steer and immediately types it into running Claude Code, Codex, Grok and OpenCode TUIs that declare native busy-input queuing; undeclared harnesses wait for a boundary, and compaction waits. Mail and automation keep when-ready delivery. Stop, resume, questions, decision issues and offers remain available. This is inspected implementation, not a cross-harness runtime parity result.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Interrupt (Escape/Ctrl-C), queue, send now or later, broadcast, answer permission prompts in the terminal; bell notifications when an agent needs you or ends a turn; attention tracked until answered; Escape-interrupt tracked; chat and terminal are the same PTY.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Release 0.3.0 ships a flight deck showing a whole mission in one view: phases, every task and its state, who works on what, what is blocked and by what, and proposals. Done work stays visible. The CLI prints the same snapshot. The waterfall source is dormant and the Timeline view was deleted, so per-task timeline history is not shown. The shared 12-task UX scenario has not been run.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Sidebar groups projects and tasks with status chips and filters, a Kanban board of columns derived from terminal activity, a Todos view across projects, PR/check badges, and Activity with CPU, memory and output rate. No epics, dependencies or workload graph.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. A quick task can be an interactive session or an issue; an issue can grow into a mission by gaining children while keeping its identity; no mandatory workflow preset applies in the baseline. Per-agent harness, model and effort are chosen at spawn or through agent profiles, and the deck shows seats. The coordinator-with-two-reviewers scenario was not run.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No mandatory workflow: any agent, model and effort per tab, broadcast and agent races, prompt library, task-scoped scheduling; agents can message and group peers; the sidebar shows groups and delegated-work states; discoverability through guided tour and tips.

## Execution and reliability

### RUN-01: Laptop-independent execution

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The published Podium execution choices are local user machines and a user-owned VPS or paired machine. No vendor-operated agent host is in the complete download offering.
- **Termic**: 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 where Termic runs, in a local worktree and PTY, optionally inside a Docker container. There is no vendor cloud, no headless server (planned idea) and no remote execution mode; LAN pairing lets agents drive another computer's Termic.

### RUN-02: Workspace and process isolation

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium separates issue files with Git branches and worktrees, but its released daemon launches native host processes without product-managed container or VM provisioning.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Each task is a git worktree (or attached to the repo root) with its own PTY tabs. Optional per-task macOS Seatbelt cage restricts writes and network through an allowlist proxy; Docker mode runs the agent in a container as the host user with capabilities dropped (experimental, egress not restricted); Secrets let a caged agent use credentials without holding them. Cages are off by default.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Closing a browser tab does not stop the agent process on a running Podium host. Idle sessions may hibernate under configurable policies; a stopped session keeps its transcript, branch and resume reference. Release 0.2.0 says a failed update rolls back and running sessions keep running through the upgrade; database rollback remains a manual restore. Terminal reattachment goes through the driver adopt contract with process-identity and observation-lease checks. Worker-crash and multi-day behavior were not tested.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Relaunch resumes every agent tab on its own conversation (agents that can resume), hooks track states, tasks and panic logs persist locally, crash logs are easy to send; closing Termic ends PTYs. No managed recovery or worker replacement.

### RUN-04: Development environment reliability

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Only machine setup is documented: the installer installs missing runtime tools and pairs a host, and the state directory holds server-managed secrets. Dependency caching, services, ports and automatic repair for project environments were not found.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Per-project setup and run scripts, preview URLs and sandbox allowlists in a committed .termic.yaml; per-member dev-server ports for multi-repo tasks; Spotlight mirrors a worktree into the repo root; no dependency caching or snapshots, and a worktree does not clone node_modules.

### RUN-05: Limits and failure handling

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium exposes retryable errors, optional auto-continue with backoff, bounded waits and provider quota. Claude stream and hosted headless drivers enforce a supplied turn deadline, with no deadline when timeoutMs is absent. The one-shot headless server runner supplies its budget, default ten minutes. Agent spawns have a daily per-issue budget. Operator-configurable task-wide turn, token and spend caps remain unestablished; quota display is not enforcement.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No time, turn, token or spend limits in Termic. Plan usage windows and context fill are shown; the user can move a task to another login past 95 percent; agents' own limits apply and a hit usage limit is a visible state.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Podium offers local logs and crash export, structured session status, issue stats, a usage and analytics sheet with hourly list-price cost, per-task costs and host load panels. The 0.3.0 notes report a vendor benchmark of about 330 MB server memory against about 1.2 GB for an earlier Podium build, and 8 to 52 percent faster start; the method is published in the repository and was not reproduced here. Usage export and cross-reconnect consistency were not established.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Agent state from hooks and PTY signals, local panic and diagnostic logs, plan usage windows and context fill in the footer, Activity process monitor, PR checks; no usage export, per-task cost or analytics. Speed and memory figures come only from ADEMark, which has no Termic entry.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Since 0.2.0 Podium shows what each task costs, on the task header and the usage sheet, with per-session rows and descendant rollups. The 0.3.0 deck adds a mission cost chip. Figures are token estimates at public model list prices, not subscription invoices or provider bills.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. No dollar or per-task cost: the footer shows provider plan usage windows (session and weekly, daily and weekly for Devin, monthly for copilot) and context fill; no budget alerts or export.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium reports host memory, load and disk, auto-hibernates idle sessions under pressure, and provides named advisory resource leases. The merge-queue panel was removed; a shipping queue remains behind the Shipping flag. Concurrency limits and bounded test queuing were not established.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. An Activity process monitor shows CPU, memory, output rate and uptime per agent, shell and run script; Docker caps PIDs; no queues, CPU/RAM limits, backpressure or check deduplication; a message queue serialises prompts per agent.

## Human collaboration and control

### TEAM-01: Live human collaboration

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The issue UI displays owner and visibility read-only and deliberately omits sharing controls. Backend share handlers and a Members settings section with invites and admin or member roles exist; they do not establish a finished human collaboration workflow. Docs say small teams can share an instance but the interface prioritizes one operator.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Single-user local app: no sharing, comments, presence or co-prompting; LAN pairing links one person's computers and sealed messages between agents are signed, not human collaboration. Config can sync through a private git repo.

### TEAM-02: Roles and access boundaries

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium defines member/admin instance roles and admin-only membership management. The released client authentication uses password-backed sessions and paired-device tokens without enterprise SSO.
- **Termic**: 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; pairing grants and profiles separate work and personal instances on one machine.

### TEAM-03: Approvals and temporary access

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Agent-session management requests go through an operator approval broker with approve and deny; the privacy docs say lifecycle commands and automation requests may require operator approval. Harness permission prompts appear as a Permission needed state; credential copying during pairing is a per-grant opt-in. Command-level policy enforcement beyond the harness own modes was not established.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Agents ask permission in their own terminal; Termic can auto-enable YOLO only inside a cage and shows a red lightning icon when YOLO is on without a sandbox; Seatbelt and Docker enforce file and network policy (network only for Seatbelt); no Termic-level approval queue or ledger; pairing grants are scoped per machine.

### TEAM-04: Decision and activity history

- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Issue actions, approval steps, comments and mail are recorded server-side. Issue activity events, including approval steps, are pruned by the server's janitor once they are older than 14 days or fall outside the newest 50,000 rows. That policy does not define all content retention, export or tamper-evident audit guarantees.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Local-only history: archived tasks with branch and PR, terminal transcripts in each agent, signed inter-agent messages, crash and panic logs, scratchpads; config can sync to a private git repo; no audit retention or integrity model.

### TEAM-05: Review experience and guidance

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Review is a documented loop: issue stage review, diff and checks, artifacts, offers with merge or send-back buttons, and a Tray of review-ready work. Release 0.3.0 adds quoting text from a reply or review finding into the next message and a full-height reading view with an outline. The board has a key map with a help sheet. Guided-review quality and narrow-screen use were not measured.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Side-by-side or unified diffs with syntax highlighting, inline GitHub-style comments on diffs, files and rendered Markdown that batch into one message to the agent, a deep review of eight focused reviewers, PR review tasks, PR and checks in the panel, keyboard-first navigation, Git panel with stage, commit, push.

### TEAM-06: Colleague takeover and continuity

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The durable issue, session transcript, artifacts and mail persist for any later agent, and a live session can be handed to another machine in an edge feature. Colleague takeover by a second person was not established.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Single-user: no colleague takeover. LAN pairing lets an agent or the same person drive tasks on another computer; conversations can move to another login mid-conversation; hand-off to another agent is a built-in prompt.

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Artifact commands store immutable server-side copies of issue-linked files, including images, video, HTML and documents, which render in the issue sidebar and offers and stay readable after the worktree is gone. Each task has an artifacts page grouped into screens, documents and reports, with filters and search. Revision linking remains untested.
- **Termic**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. Diffs, Markdown and HTML/SVG previews (sandboxed), scratchpads where agents write findings, plans and reports, scheduled-run reports, terminal scrollback; no screenshots, recordings or gallery of its own; retained with the task.

### SHIP-02: Verification and spec gates

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. In the experimental Shipping path a configured validation profile runs before landing (default argv bun run test with a 10 minute timeout) and a failed validation holds the order. Lint, type, CI and spec conformance gates and independent review requirements were not found as product-enforced policy.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Termic itself runs no tests or CI; agents and setup scripts do; PR checks and reviews are shown; Review and Deep review prompts run independent agents; no required checks or gates.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Issues own branches and worktrees, and issue actions rebase, open a pull request with gh (pr create --fill) and merge, subject to a merge-style setting (ff-only by default, with auto-rebase before merge). Podium does not resolve branch conflicts, and PR review comments and CI response were not established.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Integrated Git: branches and worktrees, Git panel with stage, commit and push, GitHub PR, GitLab MR and Azure DevOps PR creation, checks and reviews watched in the right panel, PR review tasks fetch the PR into a worktree, Send to main, duplicate worktree for parallel attempts; conflict handling is by the agent.

### SHIP-04: Merge and deployment authority

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The operator accepts work through offers and runs the merge action under a branch merge-lock; in the experimental Shipping path approval is frozen to an exact head and delivery lands on a local target branch by default. Release and deployment are not product features found in the sources.
- **Termic**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. The user opens PRs from the app or via agents; merge, release and deployment are done on the forge or by agents; Send to main applies a task to the main branch; no authority enforcement beyond forge permissions.

### SHIP-05: Completion evidence and rollback

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Shipping orders record approved base and head SHAs, tested integration SHA, landed ref and validation result in a durable delivery receipt, and stale approvals hold the order. Shipping is experimental. The pr action records a PR URL on the issue. Build and deployment links and rollback were not found.
- **Termic**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. Task rows link branch and PR with status and a tick when approved; history restores tasks by PR number; no build or deployment links, rollback or stale-approval invalidation.

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. The shipping service records revision-specific approval, configured validation and delivery receipts. The Shipping panel is an experimental edge toggle, off by default; the separate Queues panel was removed.
- **Termic**: Sourced (sourced); support: partial. Checked 2026-11-16 (6 days old); not separately cross-checked. Kanban and sidebar group tasks by state with PR badges and change size, a Todos view for PRs needing review, Deep review for bulk checking; no risk filters, merge queues or approval invalidation.

## Ownership, privacy and economics

### OWN-01: Source and license

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The public repository is licensed Apache 2.0, and the website presents Podium as an open-source agent development environment. Hosted extensions and hosted-service terms are not established.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. GNU AGPL-3.0-or-later for the desktop app, CLI and backend in one public repository; no closed component, derivatives must stay AGPL. Pinned v1.23.0.

### OWN-02: Hosting and exit

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Local desktop and self-hosted installs run on user-controlled machines with a documented state directory. The docs describe stopped full-state backup and automatic pre-migration database-only snapshots retaining three copies. Those snapshots omit artifacts, transcripts, uploads, configuration and secrets; no portable structured export/import contract was established.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Local-first: state in the app data directory (projects.json, tasks, settings), optional config sync to a private git repo, no account or backend, open-source so everything stays usable. Exports are the JSON files and git history.

### OWN-03: Data handling and telemetry

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-21. Docs state repositories and native harness credentials stay on machines you control and server state lives in a documented directory. Since 0.2.0 a daily usage report is on by default and can be turned off; crash reports stay opt-in. Usage reports carry an install id, schema version, Podium version, OS, architecture, bucketed install age and machine count, session counts per harness and whether issues were used. Crash reports carry the same install id, versions, OS and architecture, a fixed error type and up to 20 stack frames, each with a Podium source file path, line and function when there is one; error messages and frames outside Podium are dropped. Neither tier sends prompts, transcripts, your code or paths outside the Podium source tree. Model-provider handling is the harness own. Hosted analytics and website analytics are separate paths.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Code, prompts and artifacts stay on the machine except what the chosen agent CLIs send to their providers; no Termic backend. No telemetry is collected today: opt-in anonymous usage telemetry and crash reports are a planned item, off by default; crash logs are local and the user attaches them to bug reports.

### OWN-04: Price and included usage

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. No Podium price is published: podium.do/pricing returns 404 and the docs list billing as not implemented. The software is open source and free to download; model and compute costs are the user's own.
- **Termic**: 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 (AGPL-3.0) with no paid tier; sponsorship is optional; agent costs are paid to providers through their plans.

### OWN-05: Scenario cost and controls

- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
- **Termic**: 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 (each runs their own install); agent plans and hardware are the user's and not published.

### OWN-06: Availability and support

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium is pre-1.0. Stable v0.3.1 (2026-11-06), an update fix, follows v0.3.0 (2026-11-05), v0.2.0 (2026-10-11) and v0.1.0 (2026-08-21), with edge and dev prerelease channels. Windows and Linux desktop are Experimental, the native iPhone app is in private beta and hosted Podium is unconfirmed. Support runs through GitHub issues, Discord and private vulnerability reporting.
- **Termic**: 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 software: five releases between 2026-10-28 and 2026-11-13, GitHub issues, optional sponsorship; Windows and Docker mode are experimental; planned items listed; no support SLA or status page.

### OWN-07: Enterprise assurance

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

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

- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium is open-source Apache-2.0 software, and the download page calls it free and open source. Download links for macOS, Linux and Windows redirect to GitHub release assets without a login (observed by HTTP requests; not installed). No Podium charge is documented for self-hosting; agent provider usage is separate. The native iPhone app is private beta and hosted access is unconfirmed.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Fully free: whole app free with no trial, card, seat or cap; users pay agent subscriptions and hardware. BYO subscriptions and review work; two-person collaboration, remote compute and phone clients do not exist.

### OWN-09: Pricing transparency

- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
- **Termic**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-16 (6 days old); agent cross-checked 2026-11-17. Transparent: free with no tiers or markup; agent usage is billed by the user's own plans; no commitment, overage or cancellation terms apply.
