svayatta / agent-custody
Proof of what your AI agents did. Give your agents real power, without losing control of them.
Why this job: matched by what the repo talks about: agent, control, real, power
What it does
Give your agents real power, without losing control of them. Your policy checks your agent's actions before they run. What it forbids does not run. Each action that it checks leaves a signed receipt that anyone can verify.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit yesterday
- Stars
- 100
- +94 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.16.6
- Released yesterday
- Built with
- TypeScript
- 90% of the code
Is it looked after?
- Contributors
- 5
- Last 90 days
- Issues
- 69% closed
- 45 still open
- Pull requests
- 204 merged
- 8 waiting
- Releases
- 6
- 6 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| aiming-lab / AutoHarness | 469 | 7 months ago | MIT | No downloads |
| runxhq / runx | 103 | 7 days ago | Apache-2.0 | Mac, Windows, Linux |
More: languages, topics and project record
Languages
- TypeScript 90%
- Python 5%
- Vue 2%
- Lean 2%
Topics
- ai-agents
- audit
- cedar
- mcp
- provenance
- python
- transparency-log
- typescript
Project record
- JobAgent frameworks
- StatusListed
- Commits390
- Forks9
- Watching0
- Stars in 28 days+94
- CreatedSep 4, 2026
- First seen by usNov 12, 2026
- CheckedNov 12, 2026