Starred repositories
Rust-based cross-platform screen and input recorder using ffmpeg
keystroke visualizer for Windows, lets you easily display your keystrokes while recording screencasts.
MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.
The quickest and easiest way to add a Zapier-like workflow UI experience to your product. Define actions in your backend and expose a Workflow UI using pre-built React components.
My personal Claude Code and OpenAI Codex setup with battle-tested skills, plugins, hooks and agents that I use daily.
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …
An MCP server exposing full Chrome DevTools Protocol debugging: breakpoints, step/run, call stacks, eval, and source maps.
From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
AI Agent Builder and Runtime by Docker Engineering
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…
Tongyi Deep Research, the Leading Open-source Deep Research Agent
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
A version of verl to support diverse tool use
📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
🌸 Best framework to build web agents, and deploy serverless web automation functions on reliable browser infra.
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…
Shared data types for building collaborative software
Build, run, manage agentic software at scale.
Infinite Photorealistic Worlds using Procedural Generation
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
verl: Volcano Engine Reinforcement Learning for LLMs