local-first semantic code search engine
A fast semantic search and retrieval engine
The living wiki that writes itself.
Semantic code search using vector embeddings. Search your codebase with natural language queries at the function level.
MediaWiki Code2Code Search is a high-performance semantic search tool designed specifically for the MediaWiki open-source ecosystem, integrated with the Software Heritage archive. It utilises a single-stage neural retrieval architecture to help developers navigate complex codebases with high precision and minimal resource usage.
AI-powered codebase intelligence platform that enables semantic code search, repository Q&A, AST analysis, dependency graphs, automated documentation, PR reviews, and architecture visualization using RAG, LangGraph, and Groq.
Give AI coding agents a map before they read your code. Statically maps your codebase structure and dependencies, enriches components with LLM summaries, and links Git commits/Jira tickets to nodes. Optimizes agent context windows and token usage with compact, queryable JSON blueprints.
Index any repo into a Tree-sitter code graph and search it semantically or exact match, so AI agents stop wasting tokens grepping around.
JCT: An intent-based semantic code search engine for Python that retrieves code using natural-language queries. Combines AST parsing, embeddings, and ranking to support concept-driven development, evaluation, and research in code retrieval.
Add a description, image, and links to the code-search-engine topic page so that developers can more easily learn about it.
To associate your repository with the code-search-engine topic, visit your repo's landing page and select "manage topics."