Deploy serverless AI workflows at scale. Firebase for AI agents

[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

Best practices & guides on how to write distributed pytorch training code

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Local realtime voice AI

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

Animation engine for explanatory math videos

Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

An open-source RAG-based tool for chatting with your documents.

Efficient Triton Kernels for LLM Training

基于大语言模型(LLM)和多智能体(Multi-Agent)，探究AI写小说能力的边界

LLM story writer with a focus on high-quality long output based on a user provided prompt.

Microsoft Automatic Mixed Precision Library

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

A high-throughput and memory-efficient inference and serving engine for LLMs

Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.

AIOS: AI Agent Operating System

[ACL'25] Official Code for LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs

A framework for few-shot evaluation of language models.

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

🙌 OpenHands: AI-Driven Development

Open-Sora: Democratizing Efficient Video Production for All

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.