# oraios/serena

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities  - the IDE for your agent

Repository: https://github.com/oraios/serena
Canonical: https://ross.abutalabs.com/products/serena
Homepage: https://oraios.github.io/serena
Language: Python
License: MIT
License Family: permissive
Topics: agent, ai, vibe-coding, mcp-server, ai-coding, language-server, programming, claude, claude-code, codex, ide, jetbrains
Last push: 2026-08-20T06:51:15+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 96, longevity 37
- inputs: {"age_days": 528, "days_push": 13, "days_rel": 24, "gap_med": 7.0, "n_releases_24m": 15}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 28526, forks 1919 (observed 2026-08-28T04:11:48.371930+00:00)

## What it is
Serena is an MCP toolkit that gives AI coding agents semantic code retrieval, editing, refactoring, and debugging capabilities at the symbol level, powered by language servers. It integrates with any MCP-compatible client such as Claude Code, Codex, or JetBrains IDEs.

## Use cases
- give my coding agent IDE-level semantic code tools
- enable cross-file renames and reference lookups for an AI agent
- connect a language server to Claude Code via MCP
- make my LLM agent work reliably in large codebases
- semantic code search and editing for AI agents
- set up an MCP server for coding assistance
- refactor code with an AI agent without fragile text edits

## When to choose
- you use an MCP-compatible coding agent (Claude Code, Codex, Copilot CLI) and want symbol-level code understanding
- you work in large or multi-language codebases where text-based agent edits are error-prone
- you want faster, more reliable refactoring and navigation from your AI assistant

## When to avoid
- you don't use AI coding agents or MCP clients
- you need a standalone IDE rather than agent tooling
- you only work in tiny projects where simple grep-based agent tools suffice

## Facets
- artifact type: library
- maturity: active
- function: mcp, agent-framework, developer-tools, search-engine, parser
- domain: developer-tools, large-language-models, programming-languages
- platform: python, cross-platform, cli
- tags: mcp-server, coding-agent, semantic-code-tools, language-server-protocol, refactoring, code-retrieval, ide-tools, vibe-coding, ai-agents

## Member repositories
- oraios/serena (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:48.371930+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:54:22.204201+00:00, confidence not recorded.
  - readme: https://github.com/oraios/serena (fetched 2026-08-28T04:11:48.371930+00:00, sha 74265a5162b0)
  - homepage: https://oraios.github.io/serena (fetched 2026-08-29T07:50:45.303904+00:00, sha a1b369e1d44c)
- Data as of 2026-08-30T08:39:29.467469+00:00.