cortex-vec provides a command-line interface for managing and querying a vector store built on top of a markdown-based knowledge vault. It combines traditional BM25 keyword search with modern embedding-based semantic retrieval to deliver accurate results for local RAG applications. Ideal for developers building AI agents or tools that need fast, private access to personal knowledge bases without relying on cloud services.
In the Developer Tools space, cortex-vec takes a focused approach. It focuses on retrieving relevant information from a local markdown knowledge vault using hybrid search. It is built as an open-source project for developers. The project is open source (Apache-2.0). It runs on the command line.
XBlueSky builds and maintains cortex-vec, and it first shipped in 2026. The project is developed in the open on GitHub with 12 stars and 181 commits in the last 90 days. Among its 4 catalogued features are Hybrid Retrieval, BM25 Search, and Embedding Search.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match