# oraios/serena

> An MCP server that gives coding agents IDE-level semantic tools: symbol-level retrieval, editing, refactoring and debugging via language servers (40+ languages).

- Magnitude: 2.5 out of 10 — Steady
- Stars: 30,973 total · +4 stars measured 2026-11-01, 11:01–14:32 UTC, ≈ 15 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · Created: 2025-03-23 · Last push: 2026-10-28
- GitHub: https://github.com/oraios/serena · Homepage: https://oraios.github.io/serena · Page: https://gitnova.dev/en/r/oraios/serena

## Useful for

- Connect Serena to Claude Code or Cursor so the agent does cross-file renames and reference lookups in one call
- Set up semantic navigation over a large monorepo for an agent via the LSP backend
- Use the Serena JetBrains plugin for refactoring in Java or Kotlin projects

## Why it’s here

- Star-counter measurements on 2026-11-01 (UTC), 11:01–14:32: 30969 → 30973 stars (+4). This is the change over that interval.
- Estimated end-of-day forecast: about +15 stars, using observed gains and the previous day.
- GitHub Trending Python today: #14, +57 stars.
- About 9 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 2,118
- Issues and pull requests: 2,089
- Watchers: 93
- Average over the last week: 41 per day
- Usual pace: 41 per day
- Stars in the last hour (measured): 3
- Latest release: v2.1.0 (2026-10-19)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-03 … 2026-11-01: 18, 27, 44, 33, 29, 27, 35, 37, 23, 29, 35, 37, 36, 37, 17, 25, 33, 119, 66, 45, 44, 24, 37, 34, 52, 34, 37, 49, 64, 4

## Spotted in now

- GitHub Trending Python today: #14, +57 stars

## More in this category

1. **deepseek-ai/dsh-superagent-prototype** — 9.6 · Breakout · AI agents · TypeScript · +3,601 stars measured 2026-11-01, 00:01–14:28 UTC, ≈ 5,614 by evening
   Research prototype of a proactive coding agent for a single GitHub repository, packaged as a bundle for DeepSeek Harness: it listens to GitHub and Feishu, opens work items and replies in the original conversation, for example with a pull…
   Full card: https://gitnova.dev/en/r/deepseek-ai/dsh-superagent-prototype.md
2. **pingdotgg/t3code** — 9.4 · Breakout · AI agents · TypeScript · +1,335 stars measured 2026-11-01, 00:01–14:28 UTC, ≈ 2,311 by evening
   T3 Code is an agent harness control surface for agents on your machine, with mobile (iOS, Android), web and Electron desktop apps. It works with your Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity subscriptions if…
   Full card: https://gitnova.dev/en/r/pingdotgg/t3code.md
3. **Orkas-AI/Orkas** — 8.5 · Breakout · AI agents · JavaScript · +970 stars measured 2026-11-01, 00:01–14:28 UTC, ≈ 1,565 by evening
   A local-first desktop app with a team of AI agents: a Commander turns a goal into to-dos and coordinates 16 built-in specialists plus external coding agents (Claude Code, Codex, etc.) within projects with scheduling and connectors.
   Full card: https://gitnova.dev/en/r/Orkas-AI/Orkas.md
4. **wangzan101/Mika** — 8.3 · Breakout · AI agents · Kotlin · +748 stars measured 2026-11-01, 00:01–14:28 UTC, ≈ 1,226 by evening
   Mika is an on-device AI agent for Android that carries out one-sentence requests by operating apps and the web on a hidden background screen while you keep using your phone. It uses your own model API key, with no project servers.
   Full card: https://gitnova.dev/en/r/wangzan101/Mika.md
5. **heydamir/unslop** — 8.0 · Breakout · AI agents · JavaScript · +859 stars measured 2026-11-01, 00:01–14:28 UTC, ≈ 1,522 by evening
   A Claude skill that audits and redesigns AI-generated, «vibecoded» UI screen by screen, replacing purple gradients, glows and emoji labels with a deliberate design direction.
   Full card: https://gitnova.dev/en/r/heydamir/unslop.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-01 14:39 UTC, updated every 30 minutes.