open-design alternatives
nexu-io/open-design is a Claude subagent with 103.5k stars and a 97/100 Trust Score. It is a solid option, but not the only one: these are the 8 strongest picks in the same category, compared by Trust Score, maintenance and community.
- 1
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Higher Trust Score (100 vs 97) and verified tier.Install - 2titanwings/distilly25.9k
Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.
Higher Trust Score (100 vs 97) and verified tier.Install - 3EverMind-AI/EverOS13.6k
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Higher Trust Score (100 vs 97) and verified tier.Install - 4
✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.
Verified tier, Trust 97/100.Install - 5
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
Verified tier, Trust 97/100.Install - 6Q00/ouroboros6.3k
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
Verified tier, Trust 97/100.Install - 7
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Verified tier, Trust 97/100.Install - 8
Comparison generated from directory data (Trust Score, stars, activity), refreshed daily. open-design last activity: today.