Octocode
Semantic code indexer with GraphRAG knowledge graph. Index your codebase, search in natural language, and expose everything via MCP so AI agents understand architecture β not just files.
README
Octocode - Intelligent Code Indexer and Graph Builder
Β© 2025 Muvon Un Limited (Hong Kong) | Website | Product Page
π Overview
Octocode is a powerful code indexer and semantic search engine that builds intelligent knowledge graphs of your codebase. It combines advanced AI capabilities with local-first design to provide deep code understanding, relationship mapping, and intelligent assistance for developers.
β¨ Key Features
- π Semantic Code Search - Natural language queries with multi-query support
- πΈοΈ Knowledge Graph (GraphRAG) - Automatic relationship discovery between files
- π Multi-Language Support - Rust, Python, JavaScript, TypeScript, Go, PHP, C++, Ruby, and more
- π§ AI-Powered Features - Smart commits, code review, memory system with semantic search
- π MCP Server Integration - Built-in Model Context Protocol server with LSP support
- β‘ Performance & Flexibility - Intelligent LanceDB optimization, local/cloud embedding models
π¦ Quick Installation
# Universal install script (Linux, macOS, Windows)
curl -fsSL https://raw.githubusercontent.com/Muvon/octocode/master/install.sh | sh
Alternative methods:
- Download from GitHub Releases
- Install with Cargo:
cargo install --git https://github.com/Muvon/octocode
For detailed installation instructions, see Installation Guide.
π API Keys Setup
β οΈ Required for functionality:
# Required: Voyage AI (embeddings) - 200M free tokens/month
export VOYAGE_API_KEY="your-voyage-api-key"
# Optional: OpenRouter (LLM features)
export OPENROUTER_API_KEY="your-openrouter-api-key"
Get your free API keys:
- Voyage AI: Get free API key (200M tokens/month free)
- OpenRouter: Get API key (optional, for AI features)
π Quick Start
# 1. Index your codebase
octocode index
# 2. Search with natural language
octocode search "HTTP request handling"
# 3. Multi-query search for comprehensive results
octocode search "authentication" "middleware"
# 4. AI-powered git workflow
octocode commit --all
# 5. Start MCP server for AI assistants
octocode mcp --path /path/to/your/project
π Complete Documentation
π Quick Navigation
- Installation Guide - Detailed installation methods and building from source
- Getting Started - First steps and basic workflow
- API Keys Setup - Complete API configuration guide
- Configuration Guide - Configuration system, templates, and customization
- Commands Reference - Complete command reference with examples
- Advanced Usage - Advanced features and workflows
- MCP Integration - Model Context Protocol server setup
- LSP Integration - Language Server Protocol integration
- Memory System - Memory management and semantic search
- Release Management - AI-powered release automation
- Architecture - Core components and system design
- Performance - Performance metrics and optimization
- Contributing - Development setup and contribution guidelines
π Supported Languages
| Language | Extensions | Features |
|---|---|---|
| Rust | .rs |
Full AST parsing, pub/use detection, module structure |
| Python | .py |
Import/class/function extraction, docstring parsing |
| JavaScript | .js, .jsx |
ES6 imports/exports, function declarations |
| TypeScript | .ts, .tsx |
Type definitions, interface extraction |
| Go | .go |
Package/import analysis, struct/interface parsing |
| PHP | .php |
Class/function extraction, namespace support |
| C++ | .cpp, .hpp, .h |
Include analysis, class/function extraction |
| Ruby | .rb |
Class/module extraction, method definitions |
| JSON | .json |
Structure analysis, key extraction |
| Bash | .sh, .bash |
Function and variable extraction |
| Markdown | .md |
Document section indexing, header extraction |
π Privacy & Security
- π Local-first option: FastEmbed and SentenceTransformer run entirely offline (macOS only)
- π Secure storage: API keys stored locally, environment variables supported
- π Respects .gitignore: Never indexes sensitive files or directories
- π‘οΈ MCP security: Server runs locally with no external network access for search
- π Cloud embeddings: Voyage AI and other providers process only file metadata, not source code
π€ Support & Community
- π Issues: GitHub Issues
- π§ Email: opensource@muvon.io
- π’ Company: Muvon Un Limited (Hong Kong)
βοΈ License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
Built with β€οΈ by the Muvon team in Hong Kong
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.