Local code intelligence MCP server and CLI for AI coding agents
Local‐first MCP server for multi‐repository semantic code search with Qdrant and llama. Turns your entire workspace into private context for AI coding assistants like Claude Code, Codex, Cursor, Copilot, Antigravity and Windsurf.
Local code map for AI coding agents: find, trace, and predict change impact with file:line evidence. Claude Code · Codex · OpenCode · MCP. No network by default.
Code intelligence MCP server for AI coding agents. AST-level codebase understanding — semantic search, symbol navigation, real reference graphs, and cross-language bridge detection across many languages. Local-first; works with any MCP client (Claude Code, Cursor, Copilot).
CloneHunter finds duplicate code across mixed-language repositories. It runs a semantic retrieval pipeline with model inference and indexing to catch harder, non-trivial duplicate patterns.
Information retrieval on source code through natural language queries
ONNX-powered code embeddings for Node.js & browser — int8 quantized BERT model, zero network dependency. Semantic code search, RAG, and AI tools for TypeScript/JavaScript.
A super simple and experimental MCP/CLI based semantic code/document search tool.
Semantic Code Search using GPT2 small model as Code and Query Encoder
Serverless semantic code-search assistant using Amazon Bedrock, Claude, Pinecone, and language-aware repository indexing.
A repository-aware AI coding assistant for macOS, Windows and Linux. Indexes your codebase into a local knowledge graph, then answers with citations back to the exact file and line. Bring your own model keys, or run Ollama fully offline. Free to use; source not public.
To associate your repository with the semantic-code-search topic, visit your repo's landing page and select "manage topics."