qkal / Canny
Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.
Why this job: says: coding agents, ai coding; topics: claude-code, codex, codex-cli
What it does
A supervision layer for AI coding agents. It hooks into Claude Code and Codex CLI, keeps a ledger of what the agent actually did, and will not let it finish on a claim.
Get started
git clone https://github.com/qkal/canny.git ~/.canny/src
node ~/.canny/src/dist/cli.js init
ln -s ~/.canny/src/dist/cli.js ~/.local/bin/canny - Maintenance
- Active
- Last commit 49 days ago
- Stars
- 134
- +3 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.3.0
- Released 49 days ago
- Built with
- TypeScript
- 86% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 20% closed
- 4 still open
- Pull requests
- 20 merged
- 2 waiting
- Releases
- 3
- 3 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| qybaihe / mu | 588 | yesterday | MIT | Mac, Windows, Linux |
| PrimeFoldTools / Andon | 168 | yesterday | MIT | No downloads |
| cozytab / fable5-mode | 106 | 3 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- TypeScript 86%
- JavaScript 12%
- Shell 2%
Topics
- agent-hooks
- ai-agents
- claude-code
- claude-code-hooks
- codex
- codex-cli
- guardrails
- jev
- typesafe
- typescript
Project record
- JobCoding agents
- StatusListed
- Commits23
- Forks18
- Watching0
- Stars in 28 days+15
- CreatedSep 11, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026