CodeGraph transforms codebases into semantic knowledge graphs for AI agents to reason about.
codegraph is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view jakedismo/codegraph-rust --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 builds a knowledge graph from your codebase, linking functions, modules, and dependencies. AI agents can then search and understand your code's structure, not just text. It uses AST parsing and optional LSP for deep code understanding.
CodeGraph is a Rust-based tool that indexes your entire codebase into a semantically searchable knowledge graph. Unlike simple embedding-based search, it creates real graph relationships between code elements (functions, classes, modules) using AST parsing, FastML, and optional LSP resolution. It supports multiple indexing tiers (fast, balanced, full) to trade off speed and richness. The graph enables AI agents to understand code architecture, dependencies, and dataflow, making context management efficient for tools like Claude Code, Cursor, and Gemini CLI. It uses SurrealDB as backend and provides MCP integration for agentic code analysis.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 219 days ago.
788 GitHub stars indicate community interest.
33 open issues signal maintenance load.
No license detected; review before production use.
Enable AI coding assistants to understand your entire codebase architecture before generating code.
Perform impact analysis by tracing dataflow and dependencies across functions and modules.
Search for code semantically, finding relevant functions with their relationships intact.
Automate code review by providing agents with full context of changes and affected areas.
Onboard new developers by generating interactive knowledge graphs of the codebase.
Indexing may expose sensitive code or API keys if the codebase contains them; ensure proper access controls.
LSP-based indexing requires external language servers, which may introduce security vulnerabilities if not trusted.
The tool stores code metadata in SurrealDB; ensure database security and encryption.
788
Stars
75
Forks
33
Issues
Local codebase intelligence CLI and MCP server for AI coding agents with change-safety gates and audit evidence.
An offline MCP server that indexes your codebase for semantic search, code search, and git history retrieval.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
CodeGraph transforms codebases into semantic knowledge graphs for AI agents to reason about.
AI/ML engineers building agentic coding tools, Senior developers using AI assistants like Claude Code or Cursor, DevOps engineers integrating semantic code search into CI/CD
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 or API keys if the codebase contains them; ensure proper access controls. LSP-based indexing requires external language servers, which may introduce security vulnerabilities if not trusted.
Similar or complementary options to evaluate include roam-code, code-memory, MCP Server Collection.
Jun 6, 2026
3 security/trust notes recorded.
Setup difficulty is 4/5.