Skip to content
Chimera-Protocol/csl-core
MCP Developer Tools
A deterministic safety layer that enforces AI‑agent rules outside the model using mathematically verified policies
Python
·
Latest v0.4.0 · 1mo ago
Security brief →
Features
-
Write declarative safety rules in .csl files and verify them with Z3 theorem proving
-
Enforce policies at runtime deterministically, preventing prompt injection or rule bypasses
-
Integrate seamlessly with Python code via `load_guard` for on‑the‑fly verification
-
Extend to LangChain agents with a 3‑line wrapper that intercepts every tool call
No immediate action
v0.4.0
New feature
·
TLA⁺ model checking
No immediate action
v0.3.0
Breaking risk
·
Alpha → Beta transition
No immediate action
v0.3.0-alpha
New feature
·
MCP Server integration
No immediate action
v0.2.0-alpha
New feature
·
Modular engine structure
No immediate action
v0.1.0-alpha
New feature
·
CSL-Core Alpha
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
Languages
Python
·
Dockerfile
Search tools, categories, lists, and users
Use ↑↓ to navigate, Enter to open, Esc to close
No results for ""
⌘K to open
↑↓ navigate
⏎ open
