Terminals and runtimes keep your agents alive and visible. Canon puts an approved plan, acceptance criteria, an independent reviewer and a close that refuses by default in your repo, enforced by its CLI. They work side by side.
| canonworkflow harness + Cockpit | Herdragent runtime + clients | tmuxterminal multiplexer | Warpterminal app + agents | |
|---|---|---|---|---|
| The sprint pipeline | ||||
| Plan approved before code | Yes. Ticket and plan.md, you approve first |
None documented |
Not its job |
Agent planning and task lists, inside the app |
| Acceptance criteria per task | Yes. acceptance.md, every box checked to close |
None documented |
Not its job |
None documented |
| Review by an agent with no build history | Yes. Fresh evaluator, Read and Bash only |
None documented |
Not its job |
PR review agents in Factories |
| Close blocked by a mechanical gate | Yes. The CLI refuses on an unchecked box, missing summary or non-pass verdict. Bypass needs an explicit flag or a recorded waiver |
None documented |
Not its job |
Approval gates in a Factories config |
| Evidence behind each verdict | Yes. A file:line cite per criterion |
None documented |
Not its job |
Screenshot or video artifacts |
| Plan-vs-actual receipt | Yes. One row per criterion: delivered, waived, deferred or partial |
None documented |
Not its job |
None documented |
| Decisions kept in your repo | Yes. .tickets/ markdown, read back at the next start |
Sessions persist, decisions are not tracked |
Not its job |
Conversations stored locally, optional cloud sync |
| Grades PRs in CI | Yes. sprint-headless runs reviewer, evaluator and security review |
None documented |
Not its job |
PR review in Factories |
| Running agents | ||||
| Work survives closing the UI | Browser tab yes, a daemon owns the terminals. If the daemon stops, one click resumes |
Yes. The server owns the terminals |
Yes. Detach and reattach |
Local and cloud-synced conversations |
| Agent state at a glance | Yes. Working, idle or needs you, with desktop notifications |
Yes. Blocked, working, done, idle |
Panes only |
Conversation panel and agent notifications |
| Multi-machine and SSH | Local only today |
Yes. Saved SSH machines in one window |
Yes. Over ssh |
Cloud agents in Factories |
| Agents supported | Claude Code, Pi and Copilot CLI in the Cockpit |
22 agent CLIs detected |
Anything you can run in a pane |
Claude Code, Codex, OpenCode and its own agent |
| Project and ticket board | Yes. A kanban per project, built from .tickets/ |
None documented |
Not its job |
Task lists for agent work only |
| Repo health checks | Yes. Upkeep runs context-check, context-doctor, dead-code-cleanup and promote-learnings, read-only |
None documented |
Not its job |
None documented |
| Runs in your existing terminal | Cockpit is a browser window. The CLI works in any terminal |
Yes. TUI, CLI and plain SSH |
Yes. It is one |
Its Terminal replaces yours. Its Agent CLI works in any terminal |
| Ownership | ||||
| Local-first, no account | Yes. No SaaS, nothing hosted |
Yes. Herdr Cloud is coming soon |
Yes. |
Terminal downloads freely. Factories needs signup |
| License | MIT |
Apache 2.0 |
ISC |
Terminal is open source. Factories and Agent CLI licensing not stated |
| Cost | Free. You pay your model provider |
Free |
Free |
Factories is usage-based per agent run |
Checked 2026-10-01 against each product's own pages. Canon's gate was run against a scratch ticket, and it refused on a missing summary and on empty acceptance checklists. "None documented" means we found no such feature there, not that it cannot exist. Next check due 2026-12-31. Something out of date? Open an issue.
Canon doesn't replace a runtime or a terminal. It answers a different question: is the work done?
Herdr is a runtime: a server owns the terminals, agents keep working while you are away, and it tracks whether each one is blocked. Canon's Cockpit does a lighter version of that for one machine. What Herdr does not document is a plan, acceptance criteria or a review gate.
Herdr wins on multiple machines, SSH and the number of agent CLIs it detects. Use both: canon's CLI and skills run inside any terminal, including a Herdr pane.
tmux lets programs keep running after you detach, and it has no idea an agent is in one. Canon treats each piece of work as a ticket with a plan, a checklist and a verdict, and shows its state on a board.
tmux wins on being everywhere, dependency-free and scriptable. Use both: run the agent that runs sprint start in a tmux pane.
Warp pairs a terminal with agents, planning and code review, and Factories adds team orchestration, approval gates and run scoring across Slack, Linear, Jira and GitHub. Canon stays local: plans and verdicts are markdown files in your repo, graded by a second agent, enforced by the CLI.
Warp wins on team workflows, integrations and cloud agents. Use both: canon's sprint runs under Claude Code, which Warp can also run.
Install once, register the sprint skill, then ask your agent to run sprint start.
$curl -fsSL https://raw.githubusercontent.com/sunitghub/canon-skills/main/install.sh | bash
irm https://raw.githubusercontent.com/sunitghub/canon-skills/main/install.ps1 | iex