# Cymatix-Context: Deterministic RAG for Agents with SQLite This repository profile is provided by osrepos.com, an open source repository discovery platform. Source: osrepos.com Repository profile: https://osrepos.com/repo/mbachaud-cymatix-context Generated for open source discovery and AI-assisted research. Cymatix Context is a local-first retrieval system for agents, built on SQLite FTS5 BM25. It returns a know-or-miss result without an LLM call on the retrieval path, through CLI, HTTP, and MCP interfaces. GitHub: https://github.com/mbachaud/Cymatix-Context OSRepos URL: https://osrepos.com/repo/mbachaud-cymatix-context ## Summary Cymatix Context is a local-first retrieval system for agents, built on SQLite FTS5 BM25. It returns a know-or-miss result without an LLM call on the retrieval path, through CLI, HTTP, and MCP interfaces. ## Topics - python - ai-agents - mcp - rag - local-first - knowledge-base ## Repository Information Last analyzed by OSRepos: Fri Oct 16 2026 17:19:27 GMT+0100 (Western European Summer Time) Detail views: 3 GitHub clicks: 1 ## Safety Notice OSRepos shares public repositories for knowledge and discovery only. Review source code, dependencies, licenses, and security implications before running or installing anything. ## Content ## Overview Cymatix Context is a local-first retrieval system for agents, built on SQLite FTS5 BM25. It indexes code and documents in a SQLite knowledge store, then retrieves and assembles context without an LLM call on the retrieval path. Its `know` / `miss` response contract is intended to help agents distinguish grounded context from a retrieval miss rather than guess. It provides CLI, HTTP, and MCP interfaces over the same retrieval primitives. The project is aimed at developers and agent builders who want a self-hosted context source, with deterministic retrieval behavior and an explicit signal when the store does not support an answer. ## Key Features - Ingests code and documents into a local SQLite knowledge store. - Uses FTS5 BM25, tags, synonym expansion, and ranking stages for retrieval; dense BGE-M3 recall is optional and off by default. - Returns a structured `know` or `miss` result, with freshness checks that can turn stale results into misses. - Offers CLI, HTTP, and MCP access to retrieval and packet-building functions. - Compresses and assembles retrieved context to fit a configured token budget, with an experimental opt-in full-text companion profile. - Includes session delivery that can elide documents already delivered in a session. ## Use Cases - Give coding agents a searchable, local index of a repository when answers should be grounded in project files. - Provide Claude Code, Codex, Gemini CLI, or other MCP clients with context from a shared local knowledge store. - Add retrieval to scripts or CI workflows through the CLI, without running a model for each query. - Serve context to an IDE or an agent using the HTTP API, including an OpenAI-compatible proxy workflow. ## Our Take This is an actively developed, unusually transparent agent-retrieval project, but teams should validate its retrieval quality on their own corpus and account for its concentrated maintainer base. **Good fit if:** - You want a local-first SQLite store and retrieval that does not call an LLM on the retrieval path. - Your agent integration can use its CLI, HTTP, or MCP interfaces and benefit from an explicit `know` / `miss` contract. - You are comfortable adopting a young project whose recent development and releases are active, while most contributions come from one person. **Look elsewhere if:** - You need retrieval quality established across your specific corpus without running your own evaluation; the README reports weak results on some benchmark categories and identifies them as open problems. - You need the `confidence` field to be a dependable trust score, since the project says it is under recalibration. - You need a retrieval system whose core feature set has been validated independently; the cymatics signal is described as experimental and not yet isolated against controls. ## Project Health | Signal | Value | |---|---| | Status | **Active**: regular commits and releases | | Last commit | 2026-10-14 (1 day ago) | | Commits, last 90 days | 100+ | | Releases, last 12 months | 28 (latest v0.11.3, 2026-10-11) | | Contributors | 3 (top contributor: 96% of commits) | | Issues closed, last 90 days | 11+ (typically closed in 9 days) | | Pull requests merged, last 90 days | 98 (typically merged in 0 days) | | Project age | 6 months | Checked on 2026-10-16 with the GitHub API. ## Project Facts - Language: Python - License: Apache-2.0 - Stars: 7 - Forks: 1 - Topics: agent-index, agent-mcp, context-engineering, deterministic, idf, knowledge-base, llm-agents, mcp - Website: https://cymatixcontext.com - Archived: no ## What You Need Detected in the repository: - Python >=3.11 (from pyproject.toml) - A test suite and automated checks on GitHub Actions ## Getting Started Python 3.11 or later is required. For the recommended CPU and MCP working set: ```bash pip install "cymatix-context[cpu,mcp]" python -m spacy download en_core_web_sm ``` Then ingest a project and query it: ```bash cymatix ingest path/to/your/project/ --recursive cymatix query "how does this project work?" ``` See the [README](https://github.com/mbachaud/Cymatix-Context) and [setup guide](https://github.com/mbachaud/Cymatix-Context/blob/beta/docs/SETUP.md) for configuration and integration details. ## License in Plain Words **Apache-2.0** (permissive). - Commercial use: yes - Modify and redistribute: yes - You must keep: the license, the NOTICE file and a note of your changes - Share your changes: no - Includes an explicit patent grant from the contributors A summary, not legal advice: the LICENSE file is what applies. ## Alternatives - [ragtime](https://osrepos.com/repo/mattv8-ragtime): Ragtime offers a self-hosted RAG API and chat UI with FAISS or pgvector indexes and model integrations, rather than SQLite FTS5 retrieval without an LLM call. - [cq](https://osrepos.com/repo/mozilla-ai-cq): cq focuses on coding agents sharing and validating reusable lessons, rather than general-purpose local knowledge retrieval through CLI, HTTP, and MCP. - [ReMe](https://osrepos.com/repo/agentscope-ai-reme): ReMe manages searchable, editable Markdown memory from agent conversations and resources, rather than retrieving knowledge with SQLite FTS5 BM25. - [utopia](https://osrepos.com/repo/deeplethe-utopia): Utopia organizes knowledge as an ontology-guided, bitemporal graph with evidence-backed answers and human review, rather than a local BM25 search index. | Project | Language | License | Stars | Status | |---|---|---|---|---| | **Cymatix-Context** | Python | Apache-2.0 | 7 | Active | | [ragtime](https://osrepos.com/repo/mattv8-ragtime) | Python | MIT | 34 | Active | | [cq](https://osrepos.com/repo/mozilla-ai-cq) | Go | Apache-2.0 | 1.3k | Active | | [ReMe](https://osrepos.com/repo/agentscope-ai-reme) | Python | Apache-2.0 | 3.5k | Active | | [utopia](https://osrepos.com/repo/deeplethe-utopia) | Rust | Apache-2.0 | 8k | New | ## Considerations - The project is young, although its measured activity indicates regular commits and releases and ongoing issue and pull-request handling. Its contributor activity is highly concentrated in one person, which is a maintenance and continuity risk. - SQLite is the local store. The core install is described as dependency-light; optional embeddings pull in PyTorch, and the README says dense recall is off by default. - The README reports a substantial accuracy gap for the sharded path and recommends unsharded use for accuracy-sensitive corpora. Several benchmark categories also remain weak. - Cymatics reordering is explicitly experimental, and the `confidence` value is not yet presented as a reliable trust signal. - The project is licensed under Apache-2.0. Review the license and third-party attributions in [NOTICE](https://github.com/mbachaud/Cymatix-Context/blob/beta/NOTICE) when incorporating it.