SLM Mesh
Peer-to-Peer Communication for AI Coding Agents
SLM Mesh adds 8 MCP tools that let AI agents discover each other, send messages, share state, and lock files in real-time. Works with any MCP-compatible agent — Claude Code, Cursor, Aider, Codex, and more. SQLite persistence with <100ms push delivery via Unix Domain Sockets.
The Isolation Problem
Every AI coding agent runs in complete isolation. When you have 3+ agents working on the same codebase — Claude Code in one terminal, Cursor in another, Aider in a third — they have no way to coordinate. They overwrite each other’s files, duplicate work, and you end up as the human message bus copy-pasting context between terminals.
Key Capabilities
8 MCP Tools for Agent Coordination
mesh_peers (discover), mesh_summary (describe work), mesh_send (message), mesh_inbox (receive), mesh_state (share config), mesh_lock (file locking), mesh_events (event log), mesh_status (health check).
Sub-100ms Push Delivery
Unix Domain Sockets for instant push notification between agents. No polling. Messages arrive in under 100 milliseconds.
SQLite + WAL Persistence
All messages, state, and locks persist in SQLite with WAL mode. Agents can disconnect and reconnect without losing context.
File Locking to Prevent Conflicts
Before editing a file, agents can acquire a lock. Other agents see the lock and work on different files. No more merge conflicts.
Framework Agnostic — Any MCP Agent
Works with Claude Code, Cursor, Aider, Codex, Windsurf, and any tool that supports the Model Context Protocol. Not vendor-locked.
SuperLocalMemory
Information-Geometric Memory for AI Agents
Local-first AI agent memory with mathematical foundations. 74.8% on LoCoMo without cloud dependency — highest local-first score reported. Fisher-Rao retrieval, sheaf cohomology, Langevin lifecycle. EU AI Act compliant.
AgentAssert
Design-by-Contract for AI Agents
Formal specification and runtime enforcement of behavioral contracts for autonomous AI agents. Prevents drift, ensures compliance, enables composition.
SkillFortify
Supply Chain Security for AI Agent Skills
Static analysis, behavioral sandboxing, and cryptographic attestation for the AI agent skill ecosystem. Detects malicious skills before they execute.