Garudex-Labs / caracal
🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can only narrow, instant revocation, tamper-evident audit.
Why this job: matched by what the repo talks about: policy, audit, agent, action
What it does
One prompt injection, leaked key, or runaway loop turns an assistant into an incident. Security reviews block launches. Auditors have nothing to inspect.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 6 days ago
- Stars
- 229
- +1 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- 3 systems
- Mac, Windows, Linux
- Latest version
- v1.0.0
- Released 3 months ago
- Built with
- TypeScript
- 64% of the code
Is it looked after?
- Contributors
- 5
- Last 90 days
- Issues
- 93% closed
- 13 still open
- Pull requests
- 214 merged
- 5 waiting
- Releases
- 15
- 15 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| nolabs-ai / nono | 4,938 | yesterday | Apache-2.0 | Mac, Linux |
| emiliaprotocol / emilia-protocol | 550 | today | Apache-2.0 | No downloads |
| DobermanCore / Doberman-Core | 243 | 16 days ago | Apache-2.0 | No downloads |
More: download files, languages, topics, project record and preview image
Download files, v1.0.0
- Mac2 files, 12 downloads
- Windows1 file, 8 downloads
- Linux2 files, 16 downloads
Languages
- TypeScript 64%
- Go 22%
- Python 7%
- JavaScript 3%
Topics
- authorization
- agent-security
- ai-agents
- oauth2
- zero-trust
Project record
- JobAI security
- StatusListed
- Commits7,347
- Forks67
- Watching1
- Stars in 28 days+5
- CreatedJun 23, 2025
- First seen by usNov 7, 2026
- CheckedNov 10, 2026