Chimera-Protocol/csl-core

Overview

CSL-core is a deterministic policy language for AI agents, using Z3 and TLA+ dual-engine formal verification to enforce constraints at runtime. It checks agent actions against predefined policies with sub-millisecond latency, ensuring behavior stays within safe bounds.

Best for

Best for
Developers building safety-critical AI agents that need formal runtime policy enforcement

Use cases

• Define safety guardrails for autonomous agent actions
• Verify agent behavior against formal specifications at runtime
• Enforce compliance policies in multi-agent systems

How to use

Install

pip install csl-core

Tools exposed

• verify_policy
• simulate_policy
• explain_policy
• scaffold_policy

Tested with

Claude Desktop, Cursor, VS Code

Notes

CSL-core is a deterministic policy language for AI agents, using Z3 and TLA+ dual-engine formal verification to enforce constraints at runtime. It checks agent actions against predefined policies with sub-millisecond latency, ensuring behavior stays within safe bounds.

14 stars on GitHub. Last updated 2026-05-31. Licensed Apache-2.0.

Use cases

• Define safety guardrails for autonomous agent actions
• Verify agent behavior against formal specifications at runtime
• Enforce compliance policies in multi-agent systems

Pros

• Dual-engine verification (Z3 + TLA+) provides strong formal guarantees
• Sub-millisecond runtime enforcement enables real-time use
• Deterministic policy language reduces ambiguity in agent behavior

Cons

• Small community (14 stars) means limited support and documentation
• Requires understanding of formal methods (Z3, TLA+) to use effectively
• Python-only implementation may limit integration with non-Python stacks

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.