Octocode is an open-source (Apache-2.0) code intelligence tool by Muvon, written in Rust, delivered as a single binary that combines semantic search, a tree-sitter-based symbol/file knowledge graph, and a built-in MCP server usable from Claude Desktop, Cursor, Windsurf, Claude Code, Octomind, and other MCP clients. Its differentiator is understanding code structure (imports, calls, extends, implements) rather than treating code as flat text chunks, plus optional LSP support for go-to-definition and find-references. The project ships a reproducible retrieval benchmark showing that keyword-tuned hybrid retrieval notably improves Hit@5 and Recall@10. It is local-first and needs no API key by default, making it attractive to privacy-conscious teams that want structural understanding; however, it is a community project rather than an official product, and adopters should evaluate cloud data egress and index permissions before rolling it out.
Strongest · Documentation 15/20 Weakest · Reliability 9/20
Static review · not runListed 2026-09-18
Read the FMRS scoring method →Runtime：Prebuilt binary
VOYAGE_API_KEY
Optional cloud embedding provider key from voyageai.com (free tier available); local FastEmbed is the default, so no key is needed.
OPENROUTER_API_KEY
Optional, for LLM features like commit messages and code review; get it at openrouter.ai.
OPENAI_API_KEY
Optional, needed only when using OpenAI embedding models (e.g. text-embedding-3-small); get it at platform.openai.com.
JINA_API_KEY
Optional, needed when using Jina embedding models (e.g. jina-embeddings-v3); get it at jina.ai.
GOOGLE_API_KEY
Optional, needed when using Google embedding models (e.g. text-embedding-005); get it at Google AI Studio.
curl -fsSL https://raw.githubusercontent.com/Muvon/octocode/master/install.sh | sh, or on macOS brew install muvon/tap/octocode, or cargo install octocode, or from source cargo install --git https://github.com/Muvon/octocode, or download a binary from GitHub Releases.export VOYAGE_API_KEY="your-voyage-api-key".cd /your/project then run octocode index.octocode search "authentication middleware"; filter by language with --language rust, or search commit history with --mode commits.{"mcpServers":{"octocode":{"command":"octocode","args":["mcp","--path","/your/project"]}}} to your MCP client config. With Claude Code you can run claude mcp add octocode -- octocode mcp --path /path/to/your/project.octocode mcp --path /your/project --with-lsp="rust-analyzer".octocode config --graphrag-enabled true then re-run octocode index.{
"mcpServers": {
"octocode": {
"command": "octocode",
"args": [
"mcp",
"--path",
"/your/project"
]
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"octocode": {
"command": "octocode",
"args": [
"mcp",
"--path",
"/your/project"
]
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add octocode -- octocode mcp --path /your/project
Run it in a terminal; replace any <…> placeholders with your own values first.
After adding the octocode MCP server config, restart the client and confirm tools like semantic_search, graphrag, and structural_search appear in the tool list; then ask "Where is authentication handled?" — if the AI answers with a concrete file path via semantic_search, the connection works.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
Octocode is a Rust-built code intelligence tool that turns a project into a navigable knowledge graph so that Claude, Cursor, and other MCP clients can search, understand, and navigate the codebase structure. It builds a live graph of file and symbol nodes with deterministic contains, imports, calls, extends, and implements relationships directly from the current source via tree-sitter AST parsing; the MCP graphrag tool works from this graph without an index, embeddings, or an LLM. Optional indexed GraphRAG overlays semantic file matches, LLM descriptions, and broader file-level architectural relationships. Retrieval is hybrid: semantic similarity combined with BM25 full-text search and reranking. It is local-first by default, using fastembed so embeddings can run without an API key, while cloud embedding providers such as Voyage, OpenAI, Jina, and Google are also supported. It supports full tree-sitter AST parsing for 17 languages and is licensed under Apache-2.0.
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
AI-powered NPM package analysis MCP server
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
Source revision 65266c4f51ca Data synced 2026-11-02 Read the FMRS scoring method