agentcontrol / agent-control
Centralized agent control plane for governing runtime agent behavior at scale. Configurable, extensible, and production-ready.
Why this job: topics: guardrails, ai-safety
What it does
Enforce runtime guardrails through a centralized control layer—configure once and apply across all agents. Agent Control evaluates inputs and outputs against configurable rules to block prompt injections, PII leakage, and other risks without changing your agent’s code.
Get started
uv venv
source .venv/bin/activate
uv pip install agent-control-sdk - Maintenance
- Active
- Last commit 4 days ago
- Stars
- 333
- +1 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v8.15.0
- Released 17 days ago
- Built with
- Python
- 70% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 27% closed
- 22 still open
- Pull requests
- 188 merged
- 30 waiting
- Releases
- 65
- 30+ 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 |
|---|---|---|---|---|
| DobermanCore / Doberman-Core | 243 | 13 days ago | Apache-2.0 | No downloads |
| Firma-AI / openfirma | 143 | 10 days ago | GPL-3.0 | Mac, Windows, Linux |
| mauhpr / agentlint | 143 | 2 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 70%
- TypeScript 30%
- Makefile <1%
- CSS <1%
Topics
- agentic-workflow
- ai-safety
- guardrails
- llm
- runtime-guardrails
Project record
- JobAI security
- StatusListed
- Commits346
- Forks57
- Watching5
- Stars in 28 days+6
- CreatedJan 30, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026