Index source code into a local knowledge base with keyword, semantic, and hybrid search modes.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.BENCH_FIXTURE_PATHBENCH_KEYWORD_QUERYBENCH_MDBENCH_MODEL_SLUGBENCH_OUTBENCH_PROJECTBENCH_PROJECT_NAMEBENCH_QUERYBENCH_ROUNDSBENCH_SEARCH_QUERYBENCH_STORAGE_BASEBENCH_SYMBOL_QUERYCHUNK_OVERLAPCHUNK_SIZEEMBEDDING_DIMENSIONSMAX_FILE_SIZEOLLAMA_MODEL— "": "bge-m3:567m",OLLAMA_URL— 2. Ollama — install from [ollama.com](https://ollama.com/), then: ollama pull bge-m3:567m and keep ollama serve running (or set to a remote server).QDRANT_API_KEY— For Qdrant Cloud, add and set QDRANT_URL to your HTTPS cluster URL — details in [Getting started](docs/getting-started.md).QDRANT_COLLECTION_PREFIXQDRANT_URL— "": "http://localhost:6333"RERANK_TIMEOUT_MS— Timeout for that POST (default 15000).RERANK_URL— ## Optional rerank ()SEARCH_AUTO_ROUTESEARCH_KEYWORD_FALLBACK_SEMANTICSEARCH_RERANK— false disables post-retrieval reorder entirely (default: enabled).SEARCH_RERANK_POOL— Max candidates considered before trim (default 50).STORAGE_PATH[](https://m8ven.ai/mcp/andyanh174-vibe-hnindex-1hk6fz)