MCP servers for local-llm

MCP server that delegates Claude Code agent work to local models (llama.cpp / vLLM) on your own hardware

Pulse — Hermes-style self-improving AI agent. Reliability-first rebuild with evaluated skill self-evolution, multi-agent team orchestration, dialectic user modeling, and fully self-hosted default stac

let it loop (LIL): Deterministic AI engineer for complex coding. Hybrid LLM+Python with CONTRACT SYSTEM parsing intent, decomposing goals, enforcing checks, deterministic Python orchestration. Durable

Delegate coding work from Claude Code to a local pi agent — MCP tools with mid-run steer/abort, plus per-project discipline hooks.