Cymatix Context

v0.9.1 · Apache-2.0 · Python

Local-first context for LLM agents

An OpenAI-compatible proxy and MCP server over a persistent SQLite knowledge store. Point your client at it, and each turn it:

$ pip install cymatix-context
$ cymatix ingest ./docs --recursive
$ cymatix query "what changed in the retrieval path?"

Receipts: EnterpriseRAG-Bench leaderboard (v0.6.4 submission; current release is 0.9.1)

Retrieve

  • FTS5 lexical search widened by tags, synonyms, and co-activation
  • Fully algorithmic by default: never waits on a model

Deliver

  • Assembles to a hard token budget
  • Skips what a session already received, so context stays lean over turns

Calibrate

  • Every packet answers: know, with a confidence, or miss, with a reason
  • Agents can trust what they got, or refresh it

Surfaces

  • Proxy: transparent. An OpenAI client points at /v1/chat/completions and context rides in with the request; the know/miss verdict is applied inside the pipeline before anything ships upstream
  • MCP + CLI: explicit. Claude Code tools and cymatix query hand the context back to the caller, know/miss block attached
  • Agents: /context/packet returns the agent-grade form: verified evidence, stale-risk flags, and refresh targets to act on