12 open-source projects share topics or a category with Kun. Each comparison below is drawn from recorded GitHub metadata — language, license, activity and review status. None of them is a judgement about which is better for you.
Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram.
Choose LobsterAI if…
you need a detected license — this one reports MIT License
you specifically need agent or autonomous-agents
Shares ai-agent, ai-assistant, automation, desktop-app with Kun.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Choose dify if…
you want something your agent can install directly rather than a library to wire up yourself
you want the more widely starred option (160.3k)
you specifically need agent or agentic-ai
Shares agentic-workflow, automation, deepseek, llm with Kun.
Personal AI desktop agent for Windows, macOS, Linux, Android & iOS. Set a goal, it works on its own. Teams (pair two desktops, agents + humans), Agent2Agent, Workflows, Codework, multi-agent orgs, desktop + browser automation. 15+ AI providers, BYOK. No Docker, no terminal. Agent Skills (SKILL.md). Migration importer. Recurring autonomous tasks.
Choose skales if…
you prefer a smaller, narrower project to a large one
you specifically need agentic-ai or android
Shares ai-agent, ai-assistant, automation, desktop-app with Kun.
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
Choose yao if…
you would rather work in Go than TypeScript
you want something your agent can install directly rather than a library to wire up yourself
you specifically need agent-harness or agent-orchestration
Shares coding-agent, deepseek, local-first, mcp with Kun.
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.
Choose ouroboros if…
you would rather work in Python than TypeScript
you need a detected license — this one reports MIT License
you want something your agent can install directly rather than a library to wire up yourself
you specifically need agent-os or agentic-ai
Shares ai-agent, coding-agent, deepseek, mcp with Kun.