code knowledge graph for AI agents
Pre-indexed local code knowledge graph that auto-syncs with code changes to provide AI coding agents with surgical context, reducing token usage and tool calls.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
choose for a single static binary MCP server with 158-language graph indexing and sub-ms queries.
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.
choose for hybrid semantic search plus dependency graphs with symbol-level impact analysis.
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.
choose for 257-language support and multi-repository graph via CLI/MCP/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
choose for a skill-based code/document knowledge graph with deterministic AST parsing.
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.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose for a zero-dependency single-binary token-reduction proxy instead of a code graph.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
choose for a TypeScript context layer over multiple agents; no standalone graph daemon.
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
choose if you need an agent context guard/memory layer with permissions rather than graph indexing.
LeanCTX — Context Intelligence for AI systems.
choose for generic output compression (logs/RAG) before the LLM rather than code graph indexing.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
choose for sandboxed tool output and session memory rather than a graph-based code index.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
choose for a lighter code-search MCP when full graph coverage is overkill.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
interactive code-graph explorer for humans, not an embeddable agent-agnostic server.
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 codegraph among their alternatives. The relationship is not symmetric — how codegraph rates them is a separate judgement, made when codegraph is analysed in its own right.
calls codegraph “Choose for a C-based pre-indexed graph with auto-sync and lower token usage.”
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 codegraph “Same pre-indexed code knowledge graph; choose for an auto-syncing local C daemon consumed by many agent CLIs rather than GitNexus's web/zero-server product.”
GitNexus: The Zero-Server Code Intelligence Engine
calls codegraph “if you want a C/MIT MCP server that auto-syncs a pre-indexed graph on code changes”
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 codegraph “Use when you want a compiled C implementation with automatic change sync and no Python runtime.”
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
calls codegraph “Choose when you want a C single-binary MCP server with auto-sync instead of a Python runtime.”
Your entire engineering context, deeply understood
calls codegraph “Choose it when you want a code knowledge graph to cut tool calls/tokens instead of generic compression.”
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
calls codegraph “Pre-indexed, auto-syncing graph for many agent CLIs; choose it when minimizing tokens is the main goal.”
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
calls codegraph “Pre-indexed code knowledge graph; choose it when your token waste is from fetching code context, not tool output.”
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
calls codegraph “choose it when you prefer a pre-indexed knowledge graph over semantic embeddings; it auto-syncs and supports multiple agents.”
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
calls codegraph “Choose it if you prefer a pre-indexed graph that auto-syncs on change over on-demand ripgrep/LSP queries.”
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