Explore live open-source projects and AI models.

Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi... Read more

AI coding agent in your terminal. Works with any LLM - DeepSeek, Qwen, GPT-5, Claude, Gemini, Kimi, Ollama. 100+ models via litellm. ~1300 lines of Python.

[Legacy] Optimized AGENTS.md system instructions for AI CLI/IDE agents. Token-efficient (Caveman ~75%), skills, subagent orchestration, security checks. Drop-in config for Qwen, Claude, Codex, Cursor и других.

Autonomous multi-agent CVE analysis on Android. No cloud. No GPU. No API key. MNN + Qwen in Termux. BLAKE3 tamper-proof logs. Config-driven. 300€ phone.

WebLLM Gateway：让 Qwen/DeepSeek 网页模型接入 OpenAI/Anthropic 兼容 Agent 工具链，支持 OpenClaw、Hermes、Claude Code、Codex 工具调用

🔀 AI Coding Agent 模型切换器：为 Claude Code / Codex 一键切换 DeepSeek、Qwen、Kimi、OpenRouter 等模型，内置本地 LLM 代理、API Key 管理和 macOS 桌面版。

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decisions.

Generative web browsing chat agent with text + vision input. Powered by MultiOn, llama-3, llava, qwen, Next.js, FastAPI, and Supabase. Landed me an internship at MultiOn :)

Reproducing AgenticQwen (arXiv:2604.21590) — dual-flywheel data synthesis + GRPO RL training for agentic small LLMs