Modular Multi-Agent System for Scientific Research Assistance

Kimi K2 is the large language model series developed by Moonshot AI team

Enables AG2 (formerly Autogen) agents to securely execute code in isolated remote sandboxes using YepCode’s serverless runtime.

ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.

Official logos and other brand assets for AG2

A TTS model capable of generating ultra-realistic dialogue in one pass.

Agent Connect Protocol Specification

A JavaScript library for seamless integration and communication with AG2 agents

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

Sample code and application showcases to get you going with AG2 (formally AutoGen)

Minimal reproduction of DeepSeek R1-Zero

LK embedded kernel

Linux kernel source tree

🏡 Open source home automation that puts local control and privacy first.

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/sNGSwQME3x

Make AG2 Agents Collaborate: Drag, Drop, and Orchestrate with Waldiez

The fastest way to bring multi-agent workflows to production.

The AI Code Editor

A toolkit for building computer use AI agents

A programming framework for agentic AI. Discord: https://discord.gg/pAbnFJrkgZ

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

[NeurIPS 2024] A task generation and model evaluation system for multimodal language models.

MLX: An array framework for Apple silicon

LLM inference in C/C++

LLM training in simple, raw C/CUDA