FlashMLA: Efficient MLA Decoding Kernel for Hopper GPUs

DeepEP: an efficient expert-parallel communication library

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Go Bindings for CRIU

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Checkpoint/Restore tool

使用文心一言+Python-pptx ，一键生成你的专属PPT

Generative Agents: Interactive Simulacra of Human Behavior

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

[IJCAI 2024] Generate different roles for GPTs to form a collaborative entity for complex tasks.

Harness LLMs with Multi-Agent Programming

Problem solving by engaging multiple AI agents in conversation with each other and the user.

GPTeam: An open-source multi-agent simulation

Chain together LLMs for reasoning & orchestrate multiple large models for accomplishing complex tasks

🦜🔗 Build context-aware reasoning applications

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

🐫 CAMEL: Finding the Scaling Law of Agents. The first and the best multi-agent framework. https://www.camel-ai.org

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

LLM inference in C/C++

LLMPerf is a library for validating and benchmarking LLMs