code intelligence / knowledge graph for AI coding agents
Local-first code intelligence graph that indexes codebases with Tree-sitter, tracks changes incrementally, and serves context over MCP/CLI to cut AI token use in review/large-repo workflows.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Use when your repository mixes SQL/config/docs with code and you want one local graph for all of them.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Use when you want a compiled C implementation with automatic change sync and no Python runtime.
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
Use when you need millisecond-scale indexing and query in a single static binary.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Use when you need multi-language, multi-repo graph access through MCP, CLI, and API.
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d
Use when a Python code-graph MCP/CLI without review-specific extras fits your stack.
Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.
Use when you want a SQLite-backed graph with audit evidence, change-safety gates, and no API keys.
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.
Use when you want one Rust binary that combines semantic search with a knowledge-graph MCP server.
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.
Use when you want an MCP graph engine with compounding context for many coding-agent CLIs.
Compounding Context for AI Coding Assistants — MCP graph engine for Claude Code, Cursor, Copilot, Gemini, OpenCode
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Use when your priority is Q&A/editing over a mono-repo, not an incremental review graph.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Use when semantic retrieval plus editing tools are more useful than a tree-sitter graph.
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
Use when you want an agent-agnostic context layer rather than a standalone code graph server.
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
Use when hybrid semantic search and impact analysis over large repos matter more than review-specific indexing.
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.
Use when you prefer vector/Milvus-based code search over a persistent AST graph.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Use when your code is on GitHub and you want on-demand symbol retrieval without local indexing.
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Use when you also need to search and prove context across all of GitHub, not only local repos.
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
Use when you want a Rust MCP/CLI code-intelligence server rather than a Python graph stack.
Local code intelligence MCP server and CLI for AI coding agents
Use when a Rust code-graphRAG server backed by SurrealDB fits your stack.
100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Use when a minimal local AST code-search CLI is sufficient and MCP/persistent graph is not needed.
A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!
Use when you only need local semantic search and call-graph queries without persistent graph/MCP infrastructure.
Semantic Search & Call Graphs for AI Agents (100% Local)
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Use when you want a visual interactive code-atlas product for people, not an embeddable MCP/CLI service.
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
These projects were analysed and named code-review-graph among their alternatives. The relationship is not symmetric — how code-review-graph rates them is a separate judgement, made when code-review-graph is analysed in its own right.
calls code-review-graph “Choose for a review-focused graph with benchmarked context reductions via MCP/CLI.”
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
calls code-review-graph “Same local code-graph for MCP/CLI; choose when you want a lightweight Python tool aimed at shrinking review-token context rather than a full graph-RAG web UI.”
GitNexus: The Zero-Server Code Intelligence Engine
calls code-review-graph “if you want a Python/MIT local-first MCP graph tailored for code-review context reduction”
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
calls code-review-graph “Choose when you want Python MCP and CLI with benchmarked context reduction for reviews.”
Your entire engineering context, deeply understood
calls code-review-graph “choose it for a local-first graph MCP focused on code review context reduction.”
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
calls code-review-graph “Use it when review-time context trimming with published benchmarks is the primary goal.”
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
calls code-review-graph “Local code-intelligence graph aimed at code-review and large-repo context reduction; choose it for review workflows rather than editing.”
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent