Starred repositories
Skills for Real Engineers. Straight from my .agents directory.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globally sync your mind for all agents: transparent, controllable, and evolving symbiotically.
The implementation of ACL main 2026 paper "ReCreate: Reasoning and Creating Domain Agents Driven by Experience"
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构…
🙌 OpenHands: AI-Driven Development
[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
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 …
HTTP, HTTP2, HTTPS, Websocket debugging proxy
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
FlashMLA: Efficient Multi-head Latent Attention Kernels
Fully open reproduction of DeepSeek-R1
FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design
Cell is a Serverless First, componentized, platform-independent progressive application framework based on TypeScript. Cell 是基于 TypeScript 的 Serverless First、组件化、平台无关的渐进式应用框架。
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
Newsfeeds website using nodejs as server and mongo as storage backends, including a simple recommendation system. 基于Node.js的新闻聚合网站, 支持基于用户行为推荐新闻.
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
A PyTorch native platform for training generative AI models
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.