codegraph-brain builds a semantic code graph using tree-sitter for deterministic fully-qualified name resolution, call-graph construction, impact analysis, and architectural drift detection. It is designed specifically for AI agents and LLM tooling, exposing the graph through the Model Context Protocol (MCP). The package enables precise code understanding and is available as an open-source Python library under the MIT license.
codegraph-brain sits in PulseGate's Developer Tools category. It focuses on building reliable context for AI agents that need to understand, navigate, and reason about large codebases without hallucinated references or architectural drift. codegraph-brain is an open-source project aimed at developers. The project is open source (MIT). codegraph-brain is available on the command line and API, and it can be self-hosted.
It is developed by zaebee, and it first shipped in 2026. The project is developed in the open on GitHub with 199 commits in the last 90 days. Key capabilities include Semantic Code Graph, FQN Resolution, and Impact Analysis. It exposes integrations via an MCP server and a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Other projects tracked alongside this one