Semantic code graph builder with 45 MCP tools, VS Code extension, and persistent memory for AI agents.
CodeGraph is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view codegraph-ai/CodeGraph --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
CodeGraph creates a map of your codebase showing how functions, classes, and files relate to each other. It gives AI coding assistants structured understanding instead of just searching text. You can use it via MCP tools, a VS Code extension, or in CI pipelines.
CodeGraph is a cross-language code intelligence tool that builds a semantic graph of your codebase. It parses 37 languages using tree-sitter and exposes the graph through 45 MCP tools, a VS Code extension, and a persistent memory layer. AI agents can query the graph for structured code understanding—like finding callers, callees, dependencies, and impact analysis—instead of grepping through files. It supports multiple embedding models for semantic search, profiles to narrow the tool surface, and a graph-only mode for fast CI integration. The tool is designed for developers and AI agents working with large codebases, enabling better refactoring, code review, and knowledge management.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 51 days ago.
17 GitHub stars indicate community interest.
0 open issues signal maintenance load.
Apache-2.0 license detected.
AI-powered code review in CI with automatic PR comments showing blast radius and test gaps.
Refactoring assistance by analyzing call chains and dependencies across the codebase.
Onboarding new developers by providing a semantic map of the codebase structure.
Semantic code search to find relevant functions or classes based on natural language queries.
Automated documentation generation from code graph relationships.
Indexing may expose sensitive code structure if the workspace contains private repositories; ensure proper access controls.
Embedding models run locally but may use significant CPU/GPU resources; graph-only mode avoids this.
17
Stars
1
Forks
0
Issues
Apache-2.0
License
A project template that turns your repository into stable infrastructure for AI-assisted development.
Local code intelligence MCP server and CLI for AI coding agents, providing semantic search and call graph analysis.
Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
Semantic code graph builder with 45 MCP tools, VS Code extension, and persistent memory for AI agents.
AI agent developers building coding assistants, Software engineers working on large, multi-language codebases, DevOps engineers integrating code analysis into CI pipelines
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Indexing may expose sensitive code structure if the workspace contains private repositories; ensure proper access controls. Embedding models run locally but may use significant CPU/GPU resources; graph-only mode avoids this.
Similar or complementary options to evaluate include attractor-guided-engineering-template, codanna, context7.
Jun 7, 2026
2 security/trust notes recorded.
Setup difficulty is 2/5.