Tomorrow I'm launching Qualixar OS a runtime that handles the 80% of multi-agent AI work that isn't building agents: routing, quality control, cost tracking, memory, team design.
Run AI agents from any framework through one OS. Forge AI designs teams automatically — describe your goal, it picks models, topology, and budget. 13 execution topologies with formal semantics. Judge pipeline evaluates every output. 24-tab dashboard for monitoring. Cost-quality-latency routing across 15 providers. SLM-Lite local memory. 25 MCP tools. 2,936 tests. Backed by a 20-page peer-reviewed paper : https://arxiv.org/abs/2604.06392
Install: npx qualixar-os
SLM Mesh is an open-source MCP server that gives AI coding agents peer-to-peer communication.
SLM Mesh fixes this with 8 MCP tools:
- Peer discovery (scoped by machine, directory, or git repo)
- Direct messaging + broadcast
- Shared key-value state
- File locking with auto-expire
- Event bus for real-time coordination
Works with Claude Code, Cursor, Aider, Windsurf, Codex, VS Code — any MCP-compatible agent.
npm install -g slm-mesh