🤖 Everything you need to create an LLM Agent—tools, prompts, frameworks, and models—all in one place.

LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG

Desktop AI Assistant powered by o1, o3, GPT-4, GPT-4 Vision, Gemini, Claude, Llama 3, DeepSeek, Bielik, DALL-E, chat, vision, voice control, image generation and analysis, agents, command execution, file upload/download, speech synthesis and recognition, access to Web, memory, presets, assistants, plugins, and more. Linux, Windows, Mac

Latest Advances on System-2 Reasoning

Search-o1: Agentic Search-Enhanced Large Reasoning Models

🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Collect every awesome work about r1!

multi1: create o1-like reasoning chains with multiple AI providers (and locally). Supports LiteLLM as backend too for 100+ providers at once.

Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".

Building open version of OpenAI o1 via reasoning traces (Groq, ollama, Anthropic, Gemini, OpenAI, Azure supported) Demo: https://huggingface.co/spaces/pseudotensor/open-strawberry

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

The Multi-Agent Reasoning framework creates an interactive chatbot where AI agents collaborate via structured reasoning and Swarm Integration for optimal answers. Simulating a team that discusses, debates, and refines responses, it enables complex problem-solving and precise results. Now with Prompt Caching to reduce latency and costs.

Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"

Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".

Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

A framework making it effortless to convert any llm model into a reasoning agent like o1 or DeepSeek's r1

Terminal Voice Assistant is a powerful and flexible tool designed to help users interact with their terminal using natural language commands.

超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1

✨ Official code for our paper: "Uncertainty-o: One Model-agnostic Framework for Unveiling Epistemic Uncertainty in Large Multimodal Models".