User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

Hindsight: Agent Memory That Learns

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Robust Speech Recognition via Large-Scale Weak Supervision

Get your documents ready for gen AI

Ultralytics YOLO 🚀

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

MLX: An array framework for Apple silicon

An Open Source Machine Learning Framework for Everyone

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Open Source Computer Vision Library

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

A hyperparameter optimization framework

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Minimalist ML framework for Rust

✨ AI Coding, Vim Style

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

🦉 Data Versioning and ML Experiments

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

Deep Learning for humans

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Machine Learning Toolkit for Kubernetes

A python library for user-friendly forecasting and anomaly detection on time series.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

SciPy library main repository

🐍 Geometric Computer Vision Library for Spatial AI

Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

Parallel computing with task scheduling

An open source extension that connects AI agents to computational notebooks in JupyterLab.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

The open source coding agent.

Production-ready platform for agentic workflow development.

The agent engineering platform

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

LLM inference in C/C++

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

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

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

🙌 OpenHands: AI-Driven Development

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

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

scikit-learn: machine learning in Python

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

A natural language interface for computers

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Unsloth Studio is a web UI for training and running open models like Qwen3.5, Gemma 4, DeepSeek, gpt-oss locally.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

A programming framework for agentic AI

Universal memory layer for AI Agents

Build AI Agents, Visually

Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

LlamaIndex is the leading document agent and OCR platform

Focus on prompting and generating

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

The original local LLM interface. Text, vision, tool-calling, training, and more. 100% offline.

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

aider is AI pair programming in your terminal

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

A library for efficient similarity search and clustering of dense vectors.

Extremely fast Query Engine for DataFrames, written in Rust

Open-Source Frontier Voice AI

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active.

Easily train a good VC model with voice data <= 10 mins!

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Cross-platform, customizable ML solutions for live and streaming media.

DSPy: The framework for programming—not prompting—language models

Self-hosted AI coding assistant

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

⏩ Source-controlled AI checks, enforceable in CI. Powered by the open-source Continue CLI

A modular graph-based Retrieval-Augmented Generation (RAG) system

The fundamental package for scientific computing with Python.

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

SOTA Open Source TTS

Open-Sora: Democratizing Efficient Video Production for All

Build resilient language agents as graphs.

Integrate cutting-edge LLM technology quickly and easily into your apps

Data infrastructure for AI

Generative Models by Stability AI

Lightpanda: the headless browser designed for AI and automation

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

🤗 smolagents: a barebones library for agents that think in code.

SGLang is a high-performance serving framework for large language models and multimodal models.

Official inference repo for FLUX.1 models

LLM Frontend for Power Users.

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone

The agent that grows with you

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Fast and memory-efficient exact attention

DeepSeek Coder: Let the Code Write Itself

Roo Code gives you a whole dev team of AI agents in your code editor.

From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.

Universal LLM Deployment Engine with ML Compilation

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

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Open-source vector similarity search for Postgres

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

State-of-the-Art Text Embeddings

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

Train transformer language models with reinforcement learning.

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

Inference code for CodeLlama models

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

Ongoing research training transformer models at scale

Wan: Open and Advanced Large-Scale Video Generative Models

The LLM Evaluation Framework

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

Open Machine Learning Compiler Framework

Supercharge Your LLM Application Evaluations 🚀

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

Official implementation of AnimateDiff.

A framework for few-shot evaluation of language models.

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Go ahead and axolotl questions

Retrieval and Retrieval-augmented LLMs

A collaboration friendly studio for NeRFs

Large Language Model Text Generation Inference

The open source codebase powering HuggingChat

Hackable and optimized Transformers building blocks, supporting a composable construction.

Fast and Accurate ML in 3 Lines of Code

Python bindings for llama.cpp

A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

[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

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Official repository for LTX-Video

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

AutoML library for deep learning

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

Typescript/React Library for AI Chat💬🚀

AI Observability & Evaluation

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

Accessible large language models via k-bit quantization for PyTorch.

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

the LLM vulnerability scanner

the LLM vulnerability scanner

Tools for merging pretrained large language models.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Unified framework for robot learning built on NVIDIA Isaac Sim

SkyReels-V2: Infinite-length Film Generative model

Adding guardrails to large language models.

Modeling, training, eval, and inference code for OLMo

TripoSR: Fast 3D Object Reconstruction from a Single Image

Efficient Triton Kernels for LLM Training

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework. Website: https://swarms.ai

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

PyTorch native post-training library

Model interpretability and understanding for PyTorch

Robust recipes to align language models with human and AI preferences

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

Chronos: Pretrained Models for Time Series Forecasting

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

CUDA accelerated rasterization of gaussian splatting

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

A fast inference library for running LLMs locally on modern consumer-class GPUs

On-device AI across mobile, embedded and edge for PyTorch

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

Gemma open-weight LLM library, from Google DeepMind

Set of tools to assess and improve LLM security.

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Minimal CLI coding agent by Mistral

This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks

Simple, safe way to store and distribute tensors

The best OSS video generation models, created by Genmo

Synthetic data generation for tabular data

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

A library for mechanistic interpretability of GPT-style language models

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

The Security Toolkit for LLM Interactions

PyTorch native quantization and sparsity for training and inference

Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.

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

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

Machine learning metrics for distributed, scalable PyTorch applications.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Deploy your agentic worfklows to production

Home of StarCoder2!

GLM-5: From Vibe Coding to Agentic Engineering

Vim plugin for LLM-assisted code/text completion

Large-scale LLM inference engine

Moonshot's most powerful model

A beautiful local-first coding agent running in your terminal - built by the community for the community ⚒

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Interface for OuteTTS models.

Automated Time Series Forecasting

Newelle - Your Ultimate Virtual Assistant

Training Sparse Autoencoders on Language Models

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

Official implementation of Half-Quadratic Quantization (HQQ)

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"

Multi-Agent Reinforcement Learning with JAX

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

Nornicdb is a low-latency, Graph + Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Uses Neo4j Bolt/Cypher and qdrant's gRPC drivers so you can switch with no changes. Then, adding intelligent features like schemas, managed embeddings, LLM reranking+inferrence, GPU acceleration, Auto-TLP, Memory Decay, and MCP server.

The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]

Opensource Memory for Agents

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Making large AI models cheaper, faster and more accessible