CodeRAG is a local-first semantic code search tool that enables developers to search and understand large or custom codebases using hybrid vector and keyword retrieval. It runs entirely on the user's machine, providing privacy and speed, and offers features like symbol-aware chunking and AI-generated answers. Designed for developers who need efficient, offline code search.
CodeRAG sits in PulseGate's Coding AI & assistants category. It focuses on searching and understanding large or custom codebases efficiently without relying on cloud APIs. CodeRAG is a consumer product aimed at developers working with large or custom codebases. CodeRAG costs nothing to use. It runs on the web, Windows, and macOS.
Neverdecel builds and maintains CodeRAG, and it first shipped in 2024. The project is developed in the open on GitHub with 228 stars and 57 commits in the last 90 days. Key capabilities include semantic code search, hybrid retrieval, and local-first operation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do