Acacian/aegis
MCP Security & AuthThe governance layer for AI agents – a single API that unifies prompt‑injection blocking, PII masking, policy enforcement and audit across 12 frameworks without code changes
Features
- Unified contract (primitives) for any tool/LLM call
- Auto‑instrumentation of 12 agent frameworks with one line (`aegis.auto_instrument()`)
- Declarative policy language covering injection, PII, toxicity, RBAC, rate limits and more
- Tamper‑evident Merkle audit logs for runtime transparency
Recent releases
View all 18 releases →
Review required
v0.9.1
Security relevant
Auth
RBAC
Privilege escalation + resource gaming fixes
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Install & Platforms
Install via
pip
