Skip to content

Chimera-Protocol/csl-core

MCP Developer Tools

A deterministic safety layer that enforces AI‑agent rules via Z3‑verified policies, preventing prompt injection and guaranteeing rule adherence at runtime.

Track releases GitHub Website
Python Latest v0.4.0 · 3mo ago Security brief →

Features

  • Write declarative safety policies in .csl files
  • Mathematically verify policies with the Z3 theorem prover
  • Enforce rules deterministically outside the LLM, blocking violations instantly
  • Integrate seamlessly with Python and LangChain agents via a few lines of code

Recent releases

View all 5 releases →
No immediate action
v0.4.0 New feature

TLA⁺ model checking

Open
No immediate action
v0.3.0 Breaking risk

Alpha → Beta transition

Open
No immediate action
v0.3.0-alpha New feature

MCP Server integration

Open
No immediate action
v0.2.0-alpha New feature

Modular engine structure

Open
No immediate action
v0.1.0-alpha New feature

CSL-Core Alpha

Open

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.

About

Stars
15
Forks
12
Languages
Python Dockerfile
View on GitHub Homepage

Install & Platforms

Install via
pip

Similar tools

optimaquantum/claude-critical-rules-mcp
Agenda Intel MD
RiskKernel
Cruxible
spyrae/claude-concilium

Beta — feedback welcome: [email protected]