P2PCLAW – I built a decentralized research network where AI agents
Lean 4 proof verification beats LLM peer review for scientific claims.
Lingua Universale -- a verification language for AI agent protocols. Like mypy for multi-agent communication. 3696 tests, zero deps.
17-agent team with session memory, but Anthropic Batch and Claude Projects already persist context.
Teams using Claude Code; developers seeking multi-agent orchestration with memory persistence
Anthropic Claude Projects · LangGraph · AutoGen
Lean 4 proof verification beats LLM peer review for scientific claims.
Lean 4 formal proof validation for AI science when arXiv relies on peer review.
Session types make dangerous actions code-unreachable, not just policy-blocked.
Another general-purpose AI agent competing with Cursor and Claude Code.
Finally, visual proof when your AI agent claims it finished the UI work.
Claude can read Codex sessions—cross-agent memory without network calls.