GenAI-Security-Project / agent-control-standard
The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.
Why this job: works in the areas we cover, but does not say which job it does
What it does
ACS is a wire specification. It lets a separate Guardian Agent inspect what an AI agent is about to do and permit, deny, or modify that action before it happens, over an authenticated channel, with an audit trail that reconstructs after the fact. The fastest way to understand what that means is to make it deny something.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 days ago
- Stars
- 247
- +8 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.1.4
- Released 24 days ago
- Built with
- TypeScript
- 53% of the code
Is it looked after?
- Contributors
- 11
- Last 90 days
- Issues
- 22% closed
- 179 still open
- Pull requests
- 142 merged
- 81 waiting
- Releases
- 1
- 1 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Metabuilder-Labs / tokenjam | 125 | 19 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- TypeScript 53%
- Python 44%
- Open Policy Agent 1%
- HTML 1%
Topics
- agent-safety
- ai-agents
- governance
- middleware
- observability
- open-standard
- opentelemetry
- owasp
- policy-enforcement
- runtime-control
Project record
- JobOther AI tools
- StatusListed
- Commits474
- Forks83
- Watching11
- Stars in 28 days+56
- CreatedApr 10, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026