RadarTopicsBuildersWeeklyReads
Open Source Radar
nexu-io/

nexu

GitHubWebsite

nexu is an open-source desktop client written in TypeScript that connects an OpenClaw agent to WeChat, Feishu, Slack, Discord, and other IM channels, with local data handling and OAuth-based login options. It includes GUI installers, built-in Feishu Skills, multi-model support, and a local-first data path.

3.2kstars
260forks
224issues
MITlicense
2026since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
Reviewgenerated from repository data · Aug 5, 2026

What it is

nexu is an open-source desktop client that runs your OpenClaw 🦞 Agent inside IM channels like WeChat, Feishu, Slack, Discord, and others. It provides a GUI-based setup, built-in Feishu Skills, multi-model support (Gemini and more), and the option to bring your own API Key. All data stays on your machine.

How it works

The project is a desktop Electron-based client that enables connecting an OpenClaw agent to IM platforms. It supports OAuth login for certain models (MiniMax, OpenAI Codex, GLM) and allows using your own API keys. The UI aims for a GUI-driven experience without requiring CLI setup.

Getting started

System requirements include macOS 12+ (Apple Silicon & Intel) and Windows 10+. Installation options list downloads from nexu.io or Releases. First launch prompts signing in with a nexu account or adding your API Key to use the client without an account.

Commands for development (in repo):

pnpm dev start           # Start full local stack with hot reload
pnpm dev stop            # Stop local stack
pnpm build               # Production build
pnpm lint
pnpm test

Recent releases

Latest 5 releases:

  • v0.1.12 (2026-04-13): Windows support is here — Nexu now officially supports Windows as a first-class desktop platform. Install, upgrade, local runtime, tray behavior, and SkillHub extraction all
  • v0.1.11 (2026-04-08): Desktop Rewards Center — Earn credits by starring the repo, sharing assets, and inviting friends. Track your balance and claim rewards directly from the desktop app. (#789)
  • v0.1.10 (2026-04-02): Seedance 2.0 video generation — Generate 15-20 second AI videos right from your bot conversations. Star the repo and join the community group to get free credits. (#749, #75
  • v0.1.9 (2026-04-01): Plays nice with other OpenClaw apps — Other OpenClaw-based apps on the same machine? No problem — Nexu now coexists gracefully, running side by side without interference. (#
  • v0.1.8 (2026-03-30): Now available for Intel Macs — Native builds for both Apple Silicon and Intel. (#550) WhatsApp & Telegram! — Connect your bots to two of the world's most popular me

Traction

Stars: 3239. Forks: 260. Open issues: 224. Language: TypeScript. License: MIT. Created: 2026-02-25. Last push: 2026-04-26.

Behind the repo

N/A

Caveats

License: MIT. Age: created 2026-02-25. Last push 2026-04-26. Open issues: 224. The README mentions Windows/macOS/Intel support and multiple platform downloads, plus a GUI-first install experience.

Agent skills inside · 21
All skills →
qiaomu-mondo-poster-design一句话生成大师级海报、书籍封面、专辑封面和各类设计作品。无需懂PS、配色或艺术史,AI自动选择最佳风格(基于33+位传奇设计师)。支持多平台多比例:公众号封面(21:9)、小红书配图(3:4)、文章配图(16:9)、书籍封面(9:16)、专辑封面(1:1)、电影海报(9:16)。包含AI提示词优化、风格对比、图生图转换功能。触发词:"Mondo风格"、"书籍封面设计"、"专辑封面"、"海报设计"、"读书笔记配图"、"公众号封面"、"小红书配图"、"文章配图"。One-sentence generation of master-level posters, book covers, album covers and designs. 33+ legendary designer styles with multi-platform aspect ratio support (21:9, 16:9, 3:4, 1:1, 9:16).Design & Presentationscriptsresearch-to-diagram深度调研主题并自动生成知识关系图谱PDF。接收研究主题后自动进行网络调研、信息收集、知识整理,最终生成专业的可视化关系图谱。适用于"研究...并做图"、"深度分析...并可视化"、"生成知识图谱"等场景。Otherscriptsstatic-deployDeploy static pages to nexu.space. Use when user says deploy, publish, ship, or go live with a static site/page. Uploads files from workspace to <project-slug>.nexu.space via Wrangler + Cloudflare Pages. Supports first deploy and redeploy.DevOps & Cloudscriptslibtv-videoSeedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation, style transfer, and text-to-image using Seedance 2.0 model. Also supports Kling 3.0, Wan 2.6, Midjourney, Seedream 5.0. Trigger phrases: seedance, generate video, make a video, generate image, make an image, draw, libtv, liblib.Media & Videoscriptsnano-banana-one-shopAll-in-one image generation with Gemini models. Supports Nano Banana (3.1 Flash), Nano Banana Pro (3 Pro), and Nano Banana 2 (2.5 Flash). Triggers on "generate image", "image generation", "nano banana", "edit image".Otherscriptsnano-bananaGenerate or edit images via Nano Banana image models. Triggers on "generate image", "image generation", "nano banana", "edit image", "nano banana pro", "nano banana 2Otherscripts
SharePost on XLinkedIn
All trending reposRevenue-verified startups →