Assess Agent & MCP security Defense not yet reviewed
bernstein
Bernstein is an Apache-2.0 governance layer for AI agents that enforces policy-as-code (who may do what, approval gates, required records) over CLI coding agents and other agent workloads. It uses a deterministic, model-free scheduler and an opt-in HMAC-chained audit log that supports offline verification.
Promising or important to understand; evaluate, don't depend on it yet.
Facts
- Repository
- sipyourdrink-ltd/bernstein
- Homepage
- github.com
- Listed via
- Awesome list
- First seen
- 2026-11-10
- License
- Apache-2.0
- Stars
- 1,197
- Last commit
- 2026-11-09
- Checked
- 2026-11-10
Listing is not endorsement. Summaries and notes are AI-assisted and reviewed; repository facts refresh automatically.