{"name":"Cymatix-Context: Deterministic RAG for Agents with SQLite","description":"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","url":"https://osrepos.com/repo/mbachaud-cymatix-context","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/mbachaud-cymatix-context","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/mbachaud-cymatix-context.md","json":"https://osrepos.com/repo/mbachaud-cymatix-context.json","topics":["python","ai-agents","mcp","rag","local-first","knowledge-base"],"keywords":["python","ai-agents","mcp","rag","local-first","knowledge-base"],"stars":null,"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.","content":"## Overview\n\nCymatix 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.\n\nIt 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.\n\n## Key Features\n\n- Ingests code and documents into a local SQLite knowledge store.\n- Uses FTS5 BM25, tags, synonym expansion, and ranking stages for retrieval; dense BGE-M3 recall is optional and off by default.\n- Returns a structured `know` or `miss` result, with freshness checks that can turn stale results into misses.\n- Offers CLI, HTTP, and MCP access to retrieval and packet-building functions.\n- Compresses and assembles retrieved context to fit a configured token budget, with an experimental opt-in full-text companion profile.\n- Includes session delivery that can elide documents already delivered in a session.\n\n## Use Cases\n\n- Give coding agents a searchable, local index of a repository when answers should be grounded in project files.\n- Provide Claude Code, Codex, Gemini CLI, or other MCP clients with context from a shared local knowledge store.\n- Add retrieval to scripts or CI workflows through the CLI, without running a model for each query.\n- Serve context to an IDE or an agent using the HTTP API, including an OpenAI-compatible proxy workflow.\n\n## Our Take\n\nThis 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.\n\n**Good fit if:**\n- You want a local-first SQLite store and retrieval that does not call an LLM on the retrieval path.\n- Your agent integration can use its CLI, HTTP, or MCP interfaces and benefit from an explicit `know` / `miss` contract.\n- You are comfortable adopting a young project whose recent development and releases are active, while most contributions come from one person.\n\n**Look elsewhere if:**\n- 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.\n- You need the `confidence` field to be a dependable trust score, since the project says it is under recalibration.\n- 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.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **Active**: regular commits and releases |\n| Last commit | 2026-10-14 (1 day ago) |\n| Commits, last 90 days | 100+ |\n| Releases, last 12 months | 28 (latest v0.11.3, 2026-10-11) |\n| Contributors | 3 (top contributor: 96% of commits) |\n| Issues closed, last 90 days | 11+ (typically closed in 9 days) |\n| Pull requests merged, last 90 days | 98 (typically merged in 0 days) |\n| Project age | 6 months |\n\nChecked on 2026-10-16 with the GitHub API.\n\n## Project Facts\n\n- Language: Python\n- License: Apache-2.0\n- Stars: 7\n- Forks: 1\n- Topics: agent-index, agent-mcp, context-engineering, deterministic, idf, knowledge-base, llm-agents, mcp\n- Website: https://cymatixcontext.com\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Python >=3.11 (from pyproject.toml)\n- A test suite and automated checks on GitHub Actions\n\n## Getting Started\n\nPython 3.11 or later is required. For the recommended CPU and MCP working set:\n\n```bash\npip install \"cymatix-context[cpu,mcp]\"\npython -m spacy download en_core_web_sm\n```\n\nThen ingest a project and query it:\n\n```bash\ncymatix ingest path/to/your/project/ --recursive\ncymatix query \"how does this project work?\"\n```\n\nSee 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.\n\n## License in Plain Words\n\n**Apache-2.0** (permissive).\n\n- Commercial use: yes\n- Modify and redistribute: yes\n- You must keep: the license, the NOTICE file and a note of your changes\n- Share your changes: no\n- Includes an explicit patent grant from the contributors\n\nA summary, not legal advice: the LICENSE file is what applies.\n\n## Alternatives\n\n- [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.\n- [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.\n- [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.\n- [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.\n\n| Project | Language | License | Stars | Status |\n|---|---|---|---|---|\n| **Cymatix-Context** | Python | Apache-2.0 | 7 | Active |\n| [ragtime](https://osrepos.com/repo/mattv8-ragtime) | Python | MIT | 34 | Active |\n| [cq](https://osrepos.com/repo/mozilla-ai-cq) | Go | Apache-2.0 | 1.3k | Active |\n| [ReMe](https://osrepos.com/repo/agentscope-ai-reme) | Python | Apache-2.0 | 3.5k | Active |\n| [utopia](https://osrepos.com/repo/deeplethe-utopia) | Rust | Apache-2.0 | 8k | New |\n\n## Considerations\n\n- 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.\n- 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.\n- 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.\n- Cymatics reordering is explicitly experimental, and the `confidence` value is not yet presented as a reliable trust signal.\n- 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.","metrics":{"detailViews":3,"githubClicks":1},"dates":{"published":null,"modified":"2026-10-16T16:19:27.000Z"}}