rafapra3008/cervellaswarm
Lingua Universale -- a verification language for AI agent protocols. Like mypy for multi-agent communication. 3696 tests, zero deps.
Provides formal property verification (9 verified properties including deadlock-free and always-terminates guarantees) via multiparty session types, compiling protocols to Python and Lean 4 proofs. Includes a full toolchain: LSP server with VS Code extension, CLI with linting/formatting, 20 stdlib protocols for AI/ML workflows, and runtime session checkers that block protocol violations at execution time—making it suitable for Claude API agents and general multi-agent frameworks.
Stars
6
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/rafapra3008/cervellaswarm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
whataboutyou-ai/eunomia
Eunomia is the open-source authorization layer for AI Agents
DariuszNewecki/CORE
Governance runtime enforcing immutable constitutional rules on AI coding agents
OrchardHarmonics/orchard-kit
Complete alignment and safety architecture for autonomous AI agents. Membrane security,...
TetiAI/lucid
Cognitive health protection for AI agents. Monitors user-AI interactions across 6...
rokabytedev/proofrun
Teach your coding agent to prove its own work — evidence, not claims