Serena is under active development! See the latest updates, upcoming features, and lessons learned to stay up to date.

### LLM Integration Serena provides the necessary [tools](#full-list-of-tools) for coding workflows, but an LLM is required to do the actual work, orchestrating tool use. Serena can be integrated with an LLM in several ways: * by using the **model context protocol (MCP)**. Serena provides an MCP server which integrates with * Claude Desktop, * IDEs like VSCode, Cursor or IntelliJ, * Extensions like Cline or Roo Code * Goose (for a nice CLI experience) * and many others, including [the ChatGPT app soon](https://x.com/OpenAIDevs/status/1904957755829481737) * by using **Agno – the model-agnostic agent framework**. Serena's Agno-based agent allows you to turn virtually any LLM into a coding agent, whether it's provided by Google, OpenAI or Anthropic (with a paid API key) or a free model provided by Ollama, Together or Anyscale. * by incorporating Serena's tools into an agent framework of your choice. Serena's tool implementation is decoupled from the framework-specific code and can thus easily be adapted to any agent framework. ### Programming Language Support & Semantic Analysis Capabilities Serena's semantic code analysis capabilities build on **language servers** using the widely implemented language server protocol (LSP). The LSP provides a set of versatile code querying and editing functionalities based on symbolic understanding of the code. Equipped with these capabilities, Serena discovers and edits code just like a seasoned developer making use of an IDE's capabilities would. Serena can efficiently find the right context and do the right thing even in very large and complex projects! So not only is it free and open-source, it frequently achieves better results than existing solutions that charge a premium. Language servers provide support for a wide range of programming languages. With Serena, we provide * direct, out-of-the-box support for: * Python * TypeScript/Javascript * PhP * Go (need to install go and gopls first) * Rust * C/C++ * Java (_Note_: startup is slow, initial startup especially so. There seem to be issues with java on macos) * indirect support (may require some code changes/manual installation) for: * Ruby (untested) * C# (untested) * Kotlin (untested) * Dart (untested) These languages are supported by the language server library [multilspy](https://github.com/microsoft/multilspy), which Serena uses under the hood. But we did not explicitly test whether the support for these languages actually works. Further languages can, in principle, easily be supported by providing a shallow adapter for a new language server implementation. ## Table of Contents - [What Can I Use Serena For?](#what-can-i-use-serena-for) - [Free Coding Agents with Serena](#free-coding-agents-with-serena) - [Quick Start](#quick-start) * [Setup](#setup) * [Configuration](#configuration) * [Project Activation](#project-activation) * [MCP Server (Claude Desktop)](#mcp-server-claude-desktop) + [Troubleshooting](#troubleshooting) * [Claude Code](#claude-code) * [Other MCP Clients (Cline, Roo-Code, Cursor, Windsurf, etc.)](#other-mcp-clients-cline-roo-code-cursor-windsurf-etc)

Serena

ツール