MCP server Claude CodeCodexCursor
Local-first LLM router: keep sensitive data and bulk text labor on your own models, call the cloud only for the hard part. Privacy-routing (fail-closed) + manager-worker delegation + allowlist guard, MCP-native. Runs locally from the llm-localfirst Python package.
MCP server Claude CodeCodexCursor
Agent memory in a single SQLite file — no vector DB, no server, no cloud. Keyword recall on stdlib alone; torch-free hybrid semantic search via model2vec + sqlite-vec. Python lib + MCP server + CLI. Runs locally from the agentrecall-db Python package.
MCP server Claude CodeCodexCursor
A drop-in confidence gate for LLM agents: turn token logprobs into an accept / verify / ask-a-human routing decision, with honest per-model calibration. Runs locally from the mcp-confidence Python package.