Serena is an open-source coding agent toolkit that empowers LLMs with IDE-like semantic code retrieval and editing capabilities. It integrates with various LLMs and IDEs, enabling efficient and precise code manipulation directly within the codebase.

Is serena open source?

Yes, licensed under GPL-3.0-or-later.

serena

Active·★ 30.1k·GPL-3.0-or-later·Updated 2026-10-08

★ Most Popular★ Trending★ Essential

Serena describes itself as "the IDE for your coding agent". It is an MCP server that gives agents semantic code retrieval, editing, refactoring and debugging tools that operate on symbols rather than line numbers or text search. An agent can find a function's references, rename a symbol across files or move code with one call instead of many fragile text edits, which matters most in large codebases.

It works with any MCP client, including Claude Code, Codex, OpenCode, Gemini CLI, Cursor, VS Code, JetBrains assistants and Claude Desktop. Two backends power the analysis: free language servers (LSP) supporting more than 40 programming languages by default, or a paid Serena JetBrains Plugin that reuses your JetBrains IDE's code analysis. Serena also includes a memory system for long-lived agent workflows.

Getting started: install uv, then run `uv tool install -p 3.13 serena-agent` and `serena init`, and configure the launch command in your client following the official client guide. The project warns against installing it through MCP or plugin marketplaces, whose commands are often outdated.

#LLM Agent#Code Analysis#IDE Tools#LSP#JetBrains#Coding#Data Analysis

Features

01Transforms LLMs into fully-featured coding agents for direct codebase interaction.

02Offers IDE-like semantic code retrieval and editing tools, operating at the symbol level.

03Highly flexible, not tied to specific LLMs, frameworks, or interfaces.

04Supports over 30 programming languages through LSP or its JetBrains plugin.

05Improves LLM (token) efficiency and code quality, especially in large and complex projects.

Why choose it

+Symbol-level tools (references, renames, moves) replace many error-prone text edits with single atomic operations.

+Language-server backend supports over 40 languages for free; a JetBrains backend is available for teams already using those IDEs.

+Works with essentially every major coding agent and IDE through MCP.

+Includes a memory system and a layered configuration for long-running projects.

Trade-offs

!The Serena application is licensed under GPL-3.0-or-later (its SolidLSP component is MIT), which matters if you plan to modify and redistribute it.

!Some languages need extra dependencies for their language servers, so setup varies by stack.

!The JetBrains backend is a paid plugin, and it does not support Rider or CLion.

!Its many options take time to learn; the project recommends reading the user guide before relying on it.

Compatibility

Claude Code

Supported

Verified via docs

JetBrains IDEs

Native (except Rider)

Verified via docs

VS Code

MCP

Verified via docs

Language Server Protocol (LSP)

30+ Languages

Verified via docs

ChatGPT

mcpo

Verified via docs

MCP Clients

Various Clients (e.g., OpenWebUI, Jan)

Verified via docs

Quick start

$ uv tool install -p 3.13 serena-agent

Use cases

↳Efficiently retrieving and editing code within an LLM agent, optimizing token usage and saving costs.

↳Implementing new features or refactoring existing code with symbol-level precision.

↳Navigating and manipulating complex, large-scale codebases more effectively than simplistic file-based approaches.

How it compares

≈vs mcp-language-server: both expose language-server features through MCP; Serena adds higher-level editing and refactoring tools, a memory system and a JetBrains backend.

≈vs codebase-memory-mcp: codebase-memory-mcp builds a persistent knowledge graph of the codebase for fast queries; Serena focuses on precise symbol-level navigation and editing.

≈vs jCodeMunch MCP: jCodeMunch focuses on token-efficient symbol retrieval via tree-sitter; Serena uses full language servers and also edits code.

Alternatives

Context7★ 62.8k

MCP Server that provides up-to-date code documentation for LLMs and AI code editors.

vs →

Gemini CLI★ 107.3k

An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.

vs →

MindsHub (formerly MindsDB)★ 39.8k

MindsHub (formerly MindsDB) is an agent workspace for knowledge work and software development, with connected data sources, a model router across frontier and open models, open-source agent harnesses, and publishable artifacts.

GitHub MCP Server★ 33.5k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

n8n★ 206.7k

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Microsoft AutoGen★ 61.3k

A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.

CrewAI★ 59.5k

Framework for orchestrating role-playing, autonomous AI agents. By working together, your Crew can tackle complex tasks.

ToolJet★ 41.1k

ToolJet is the open-source foundation of ToolJet AI - the AI-native platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀

See all alternatives →

Comments

No comments yet. Be the first!

serena

Active·★ 30.1k·GPL-3.0-or-later·Updated 2026-10-08

★ Most Popular★ Trending★ Essential

#LLM Agent#Code Analysis#IDE Tools#LSP#JetBrains#Coding#Data Analysis

Features

01Transforms LLMs into fully-featured coding agents for direct codebase interaction.

02Offers IDE-like semantic code retrieval and editing tools, operating at the symbol level.

03Highly flexible, not tied to specific LLMs, frameworks, or interfaces.

04Supports over 30 programming languages through LSP or its JetBrains plugin.

05Improves LLM (token) efficiency and code quality, especially in large and complex projects.

Why choose it

+Symbol-level tools (references, renames, moves) replace many error-prone text edits with single atomic operations.

+Language-server backend supports over 40 languages for free; a JetBrains backend is available for teams already using those IDEs.

+Works with essentially every major coding agent and IDE through MCP.

+Includes a memory system and a layered configuration for long-running projects.

Trade-offs

!The Serena application is licensed under GPL-3.0-or-later (its SolidLSP component is MIT), which matters if you plan to modify and redistribute it.

!Some languages need extra dependencies for their language servers, so setup varies by stack.

!The JetBrains backend is a paid plugin, and it does not support Rider or CLion.

!Its many options take time to learn; the project recommends reading the user guide before relying on it.

Compatibility

Claude Code

Supported

Verified via docs

JetBrains IDEs

Native (except Rider)

Verified via docs

VS Code

MCP

Verified via docs

Language Server Protocol (LSP)

30+ Languages

Verified via docs

ChatGPT

mcpo

Verified via docs

MCP Clients

Various Clients (e.g., OpenWebUI, Jan)

Verified via docs

Quick start

$ uv tool install -p 3.13 serena-agent

Use cases

↳Efficiently retrieving and editing code within an LLM agent, optimizing token usage and saving costs.

↳Implementing new features or refactoring existing code with symbol-level precision.

↳Navigating and manipulating complex, large-scale codebases more effectively than simplistic file-based approaches.

How it compares

≈vs mcp-language-server: both expose language-server features through MCP; Serena adds higher-level editing and refactoring tools, a memory system and a JetBrains backend.

≈vs codebase-memory-mcp: codebase-memory-mcp builds a persistent knowledge graph of the codebase for fast queries; Serena focuses on precise symbol-level navigation and editing.

≈vs jCodeMunch MCP: jCodeMunch focuses on token-efficient symbol retrieval via tree-sitter; Serena uses full language servers and also edits code.