$git clone https://github.com/oraios/serena* Serena provides essential semantic code retrieval, editing, refactoring and debugging tools that are akin to an IDE's capabilities, operating at the symbol level and exploiting relational structure. * It integrates with any client/LLM via the model context protocol (**MCP
| 1 | <p align="center" style="text-align:center;"> |
| 2 | <img src="resources/serena-logo.svg#gh-light-mode-only" style="width:500px"> |
| 3 | <img src="resources/serena-logo-dark-mode.svg#gh-dark-mode-only" style="width:500px"> |
| 4 | </p> |
| 5 | |
| 6 | <h3 align="center"> |
| 7 | The IDE for Your Coding Agent |
| 8 | </h3> |
| 9 | |
| 10 | <div align="center"> |
| 11 | <a href="https://discord.com/invite/cVUNQmnV4r"><img src="https://img.shields.io/badge/discord-join-5865F2?style=flat-square&labelColor=0a0e14&logo=discord&logoColor=5865F2" alt="discord"></a> |
| 12 | <a href="https://github.com/oraios/serena/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-b0e8ff?style=flat-square&labelColor=0a0e14" alt="license"></a> |
| 13 | </div> |
| 14 | <br> |
| 15 | |
| 16 | |
| 17 | * Serena provides essential **semantic code retrieval, editing, refactoring and debugging tools** that are akin to an IDE's capabilities, |
| 18 | operating at the symbol level and exploiting relational structure. |
| 19 | * It integrates with any client/LLM via the model context protocol (**MCP**). |
| 20 | |
| 21 | Serena's **agent-first tool design** involves robust high-level abstractions, distinguishing it from |
| 22 | approaches that rely on low-level concepts like line numbers or primitive search patterns. |
| 23 | |
| 24 | Practically, this means that your agent operates **faster, more efficiently and more reliably**, especially in larger and |
| 25 | more complex codebases. |
| 26 | |
| 27 | > [!IMPORTANT] |
| 28 | > Do not install Serena via an MCP or plugin marketplace! They contain outdated and suboptimal installation commands. |
| 29 | > Instead, follow our [Quick Start](#quick-start) instructions. |
| 30 | |
| 31 | ## Quick Demo |
| 32 | |
| 33 | https://github.com/user-attachments/assets/8d11646e-b80e-4723-b9d7-32d6101b5f58 |
| 34 | |
| 35 | :tv: Longer video: [Introduction to Serena in 5 Minutes (YouTube)](https://www.youtube.com/watch?v=5QN7gN1KYLA) |
| 36 | |
| 37 | ## What Our "End Users" Say |
| 38 | |
| 39 | While it is humans who download and set up Serena, our end users are essentially AI agents. |
| 40 | As the ones actually applying Serena's tools, they are in the best position to evaluate Serena. |
| 41 | |
| 42 | We crafted an unbiased evaluation prompt that leads the agent to perform ~20 routine coding tasks, |
| 43 | representative of everyday development work, |
| 44 | in order to estimate the value added by Serena's tools when used alongside its own built-ins. |
| 45 | |
| 46 | Here's a one-sentence summary of what the agents had to say: |
| 47 | |
| 48 | **Opus 4.6 (high) in Claude Code on a large Python codebase:** |
| 49 | > "Serena's IDE-backed semantic tools are the single most impactful addition to my toolkit – cross-file renames, moves, and reference lookups that |
| 50 | would cost me 8–12 careful, error-prone steps collapse into one atomic call, and I would absolutely ask any developer I work with to set them up." |
| 51 | |
| 52 | **GPT 5.4 (high) in Codex CLI on a Java codebase:** |
| 53 | > "As a coding AI agent, I would ask my owner to add Serena because it gives me the missing IDE-level understanding of symbols, references, and |
| 54 | refactorings, turning fragile text surgery into calmer, faster, more confident code changes where semantics matter." |
| 55 | |
| 56 | **GPT 5.4 (medium) in Copilot CLI on a large, multi-language monorepo:** |
| 57 | > "As a coding agent, I’d absolutely ask my owner to add Serena because it makes me noticeably sharper and calmer on |
| 58 | real code – especially symbol-aware navigation, cross-file refactors, and monorepo dependency jumps – while I still lean |
| 59 | on built-ins for tiny text edits and non-code work." |
| 60 | |
| 61 | Different agents in different settings independently converge on the same verdict. |
| 62 | |
| 63 | _Give your agent the tools it has been asking for and add Serena MCP to your client!_ |
| 64 | |
| 65 | See our [documentation](https://oraios.github.io/serena/04-evaluation/000_evaluation-intro.html) for the full methodology and much more detailed evaluation results, or run your own evaluation on a project of your choice. |
| 66 | |
| 67 | |
| 68 | ## How Serena Works |
| 69 | |
| 70 | Serena provides the necessary [tools](https://oraios.github.io/serena/01-about/035_tools.html) for coding workflows, |
| 71 | but an LLM is required to do the actual work, orchestrating tool use. |
| 72 | |
| 73 | Serena can extend the functionality of your existing AI client via the **model context protocol (MCP)**. |
| 74 | Most modern A |