Code Context Engine

•
467
•

Indexes codebases for AI agents, enabling them to search relevant code instead of re-reading files and significantly reducing token costs with cross-session memory.

Stop your AI coding agent from re-reading your entire codebase every session, drastically cutting down on input tokens and saving costs. Code Context Engine provides a local, zero-cloud, zero-config server that intelligently indexes your project using AST parsing. It offers hybrid search capabilities, combining vector and BM25 retrieval with code graph expansion, and stores cross-session memory for decisions and code areas. This allows AI tools like Claude, VS Code Copilot, Cursor, Gemini CLI, and OpenAI Codex to query for precise context, leading to up to 94% token savings and a more efficient development workflow.

Características Principales

01Semantic code indexing via Tree-sitter AST parsing for accurate context
02Persistent cross-session memory for recalling AI decisions and code areas
03Live dashboard and dollar estimates for tracking token savings
043 GitHub stars
05Hybrid vector and BM25 search with code graph expansion and confidence scoring
06Achieves up to 94% token savings for AI coding agent interactions (benchmarked)
07Local-first MCP server with zero-cloud, zero-config setup and editor auto-detection

Casos de Uso

01Optimize AI coding agent interactions by significantly reducing token consumption
02Provide intelligent, context-aware code retrieval for large language models in development environments
03Maintain development context and architectural decisions across multiple AI coding sessions