Awesome Open Source AI

pytorch/pytorch

pytorch

98.8k

Tensors and Dynamic neural networks in Python with strong GPU acceleration

tensorflow/tensorflow

tensorflow

194.5k

An Open Source Machine Learning Framework for Everyone

jax-ml/jax

jax-ml

35.3k

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

google/flax

google

7.1k

Flax is a neural network library for JAX that is designed for flexibility.

pyro-ppl/numpyro

pyro-ppl

2.6k

Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.

keras-team/keras

keras-team

63.9k

Deep Learning for humans

tinygrad/tinygrad

tinygrad

32.1k

You like pytorch? You like micrograd? You love tinygrad! ❤️

pyg-team/pytorch_geometric

pyg-team

23.6k

Graph Neural Network Library for PyTorch

tracel-ai/burn

tracel-ai

14.8k

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

huggingface/candle

huggingface

19.9k

Minimalist ML framework for Rust

rust-ml/linfa

rust-ml

4.6k

A Rust machine learning framework.

FluxML/Flux.jl

FluxML

4.7k

Relax! Flux is the ML library that doesn't make you tensor

huggingface/transformers

huggingface

158.8k

🤗 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.

huggingface/sentence-transformers

huggingface

18.5k

State-of-the-Art Text Embeddings

huggingface/tokenizers

huggingface

10.6k

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

pandas-dev/pandas

pandas-dev

48.3k

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

pola-rs/polars

pola-rs

38k

Extremely fast Query Engine for DataFrames, written in Rust

rapidsai/cudf

rapidsai

9.6k

cuDF - GPU DataFrame Library

modin-project/modin

modin-project

10.4k

Modin: Scale your Pandas workflows by changing a single line of code

dask/dask

dask

13.8k

Parallel computing with task scheduling

numpy/numpy

numpy

31.7k

The fundamental package for scientific computing with Python.

scipy/scipy

scipy

14.6k

SciPy library main repository

networkx/networkx

networkx

16.8k

Network Analysis in Python

scikit-learn/scikit-learn

scikit-learn

65.6k

scikit-learn: machine learning in Python

dmlc/xgboost

dmlc

28.2k

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

lightgbm-org/LightGBM

lightgbm-org

18.2k

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.

catboost/catboost

catboost

8.9k

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.

sktime/sktime

sktime

9.7k

A unified framework for machine learning with time series

Nixtla/statsforecast

Nixtla

4.7k

Lightning ⚡️ fast forecasting with statistical and econometric models.

optuna/optuna

optuna

13.8k

A hyperparameter optimization framework

autogluon/autogluon

autogluon

10.2k

Fast and Accurate ML in 3 Lines of Code

microsoft/FLAML

microsoft

4.3k

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

keras-team/autokeras

keras-team

9.3k

AutoML library for deep learning

EpistasisLab/tpot

EpistasisLab

10k

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

huggingface/accelerate

huggingface

9.6k

🚀 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

deepspeedai/DeepSpeed

deepspeedai

42k

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

Dao-AILab/flash-attention

Dao-AILab

23.1k

Fast and memory-efficient exact attention

facebookresearch/xformers

facebookresearch

10.4k

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

Lightning-AI/pytorch-lightning

Lightning-AI

31k

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

microsoft/onnxruntime

microsoft

19.8k

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

arogozhnikov/einops

arogozhnikov

9.4k

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

huggingface/safetensors

huggingface

3.7k

Simple, safe way to store and distribute tensors

Lightning-AI/torchmetrics

Lightning-AI

2.4k

Machine learning metrics for distributed, scalable PyTorch applications.

pytorch/ao

pytorch

2.8k

PyTorch native quantization and sparsity for training and inference

shap/shap

shap

25.2k

A game theoretic approach to explain the output of any machine learning model.

QwenLM/Qwen

QwenLM

20.9k

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

deepseek-ai/DeepSeek-V3

deepseek-ai

102.5k

No description provided.

google-deepmind/gemma

google-deepmind

4.3k

Gemma open-weight LLM library, from Google DeepMind

MiniMax-AI/MiniMax-M1

MiniMax-AI

3.1k

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

MoonshotAI/Kimi-K2.5

MoonshotAI

1.7k

Moonshot's most powerful model

microsoft/PhiCookBook

microsoft

3.7k

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

zai-org/GLM-5

zai-org

2.1k

GLM-5: From Vibe Coding to Agentic Engineering

allenai/OLMo

allenai

6.5k

Modeling, training, eval, and inference code for OLMo

meta-llama/llama-models

meta-llama

7.5k

Utilities intended for use with Llama models.

deepseek-ai/DeepSeek-Coder

deepseek-ai

23k

DeepSeek Coder: Let the Code Write Itself

meta-llama/codellama

meta-llama

16.3k

Inference code for CodeLlama models

QwenLM/Qwen3-Coder

QwenLM

16.2k

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

bigcode-project/starcoder2

bigcode-project

2.1k

Home of StarCoder2!

ibm-granite/granite-code-models

ibm-granite

1.3k

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

QwenLM/Qwen3-VL

QwenLM

18.9k

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

OpenGVLab/InternVL

OpenGVLab

9.9k

[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

zai-org/GLM-V

zai-org

2.3k

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

LLaVA-VL/LLaVA-NeXT

LLaVA-VL

4.6k

No description provided.

OpenBMB/MiniCPM-o

OpenBMB

24.3k

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

openai/whisper

openai

97.2k

Robust Speech Recognition via Large-Scale Weak Supervision

edwko/OuteTTS

edwko

1.4k

Interface for OuteTTS models.

fishaudio/fish-speech

fishaudio

29.1k

SOTA Open Source TTS

facebookresearch/audiocraft

facebookresearch

23.1k

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.

microsoft/VibeVoice

microsoft

36.1k

Open-Source Frontier Voice AI

resemble-ai/chatterbox

resemble-ai

24.1k

SoTA open-source TTS

nari-labs/dia

nari-labs

19.2k

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

hexgrad/kokoro

hexgrad

6.3k

https://hf.co/hexgrad/Kokoro-82M

stepfun-ai/Step-Audio

stepfun-ai

4.6k

No description provided.

mistralai/mistral-inference

mistralai

10.8k

Official inference library for Mistral models

hpcaitech/Open-Sora

hpcaitech

28.8k

Open-Sora: Democratizing Efficient Video Production for All

zai-org/CogVideo

zai-org

12.6k

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

genmoai/mochi

genmoai

3.6k

The best OSS video generation models, created by Genmo

guoyww/AnimateDiff

guoyww

12.1k

Official implementation of AnimateDiff.

ggml-org/llama.cpp

ggml-org

101.4k

LLM inference in C/C++

ollama/ollama

ollama

167.2k

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

ml-explore/mlx

ml-explore

25.1k

MLX: An array framework for Apple silicon

mlc-ai/mlc-llm

mlc-ai

22.3k

Universal LLM Deployment Engine with ML Compilation

mlc-ai/web-llm

mlc-ai

17.7k

High-performance In-browser LLM Inference Engine

abetlen/llama-cpp-python

abetlen

10.1k

Python bindings for llama.cpp

LostRuins/koboldcpp

LostRuins

9.9k

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

potato-os/core

potato-os

70

Local AI box on Raspberry Pi.

llm-d/llm-d

llm-d

2.9k

Achieve state of the art inference performance with modern accelerators on Kubernetes

InternLM/lmdeploy

InternLM

7.8k

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

vllm-project/vllm

vllm-project

75.3k

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

huggingface/text-generation-inference

huggingface

10.8k

Large Language Model Text Generation Inference

sgl-project/sglang

sgl-project

25.4k

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

NVIDIA/TensorRT-LLM

NVIDIA

13.3k

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.

aphrodite-engine/aphrodite-engine

aphrodite-engine

1.7k

Large-scale LLM inference engine

sgl-project/ome

sgl-project

412

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

triton-inference-server/server

triton-inference-server

10.5k

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

EricLBuehler/mistral.rs

EricLBuehler

6.8k

Fast, flexible LLM inference

kvcache-ai/ktransformers

kvcache-ai

16.9k

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

mozilla-ai/llamafile

mozilla-ai

24k

Distribute and run LLMs with a single file.

bitsandbytes-foundation/bitsandbytes

bitsandbytes-foundation

8.1k

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

casper-hansen/AutoAWQ

casper-hansen

2.3k

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

AutoGPTQ/AutoGPTQ

AutoGPTQ

5k

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

dropbox/hqq

dropbox

924

Official implementation of Half-Quadratic Quantization (HQQ)

turboderp-org/exllamav2

turboderp-org

4.5k

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

huggingface/optimum

huggingface

3.3k

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

langchain-ai/langgraph

langchain-ai

28.4k

Build resilient language agents as graphs.

crewAIInc/crewAI

crewAIInc

48k

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

microsoft/autogen

microsoft

56.7k

A programming framework for agentic AI

stanfordnlp/dspy

stanfordnlp

33.4k

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

microsoft/semantic-kernel

microsoft

27.6k

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

huggingface/smolagents

huggingface

26.4k

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

langchain-ai/langchain

langchain-ai

132.4k

The agent engineering platform

NousResearch/hermes-agent

NousResearch

24.8k

The agent that grows with you

agno-agi/agno

agno-agi

39.2k

Build, run, manage agentic software at scale.

pydantic/pydantic-ai

pydantic

16.1k

AI Agent Framework, the Pydantic way

FoundationAgents/MetaGPT

FoundationAgents

66.6k

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

camel-ai/camel

camel-ai

16.6k

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

openai/swarm

openai

21.3k

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

kyegomez/swarms

kyegomez

6.2k

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

run-llama/llama_deploy

run-llama

2.1k

Deploy your agentic worfklows to production

mastra-ai/mastra

mastra-ai

22.7k

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

bytedance/deer-flow

bytedance

57.8k

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.

openai/openai-agents-python

openai

20.6k

A lightweight, powerful framework for multi-agent workflows

OpenHands/OpenHands

OpenHands

70.6k

🙌 OpenHands: AI-Driven Development

block/goose

block

35.6k

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

anomalyco/opencode

anomalyco

137.1k

The open source coding agent.

Aider-AI/aider

Aider-AI

42.8k

aider is AI pair programming in your terminal

badlogic/pi-mono

badlogic

31.5k

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

mistralai/mistral-vibe

mistralai

3.8k

Minimal CLI coding agent by Mistral

Nano-Collective/nanocoder

Nano-Collective

1.6k

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

google-gemini/gemini-cli

google-gemini

100.2k

An open-source AI agent that brings the power of Gemini directly into your terminal.

langflow-ai/langflow

langflow-ai

146.6k

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

langgenius/dify

langgenius

135.9k

Production-ready platform for agentic workflow development.

camel-ai/owl

camel-ai

19.3k

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

TransformerOptimus/SuperAGI

TransformerOptimus

17.4k

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

SakanaAI/AI-Scientist-v2

SakanaAI

4.8k

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

MervinPraison/PraisonAI

MervinPraison

6.6k

PraisonAI 🦞 - Your 24/7 AI employee team. Automate and solve complex challenges with low-code multi-agent AI that plans, researches, codes, and delivers to Telegram, Discord, and WhatsApp. Handoffs, guardrails, memory, RAG, 100+ LLMs.

simular-ai/Agent-S

simular-ai

10.8k

Agent S: an open agentic framework that uses computers like a human

letta-ai/letta

letta-ai

21.9k

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

mem0ai/mem0

mem0ai

52k

Universal memory layer for AI Agents

ScottRBK/forgetful

ScottRBK

239

Opensource Memory for Agents

vectorize-io/hindsight

vectorize-io

7.3k

Hindsight: Agent Memory That Learns

chroma-core/chroma

chroma-core

27.2k

Data infrastructure for AI

qdrant/qdrant

qdrant

30k

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/

weaviate/weaviate

weaviate

15.9k

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​.

milvus-io/milvus

milvus-io

43.6k

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

facebookresearch/faiss

facebookresearch

39.6k

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

orneryd/NornicDB

orneryd

381

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.

lancedb/lancedb

lancedb

9.8k

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

pgvector/pgvector

pgvector

20.6k

Open-source vector similarity search for Postgres

FlagOpen/FlagEmbedding

FlagOpen

11.5k

Retrieval and Retrieval-augmented LLMs

illuin-tech/colpali

illuin-tech

2.6k

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

HKUDS/LightRAG

HKUDS

32.1k

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

HKUDS/RAG-Anything

HKUDS

15.1k

"RAG-Anything: All-in-One RAG Framework"

neuml/txtai

neuml

12.4k

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

michaelfeil/infinity

michaelfeil

2.7k

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

unclecode/crawl4ai

unclecode

63.4k

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

lightpanda-io/browser

lightpanda-io

27.1k

Lightpanda: the headless browser designed for AI and automation

clusterzx/paperless-ai

clusterzx

5.5k

An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.

edwko/OuteTTS

edwko

1.4k

Interface for OuteTTS models.

fishaudio/fish-speech

fishaudio

29.1k

SOTA Open Source TTS

facebookresearch/audiocraft

facebookresearch

23.1k

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.

hpcaitech/Open-Sora

hpcaitech

28.8k

Open-Sora: Democratizing Efficient Video Production for All

genmoai/mochi

genmoai

3.6k

The best OSS video generation models, created by Genmo

guoyww/AnimateDiff

guoyww

12.1k

Official implementation of AnimateDiff.

Comfy-Org/ComfyUI

Comfy-Org

107.8k

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

Haoming02/sd-webui-forge-classic

Haoming02

999

The good ol' Forge WebUI, now updated with new features~

lllyasviel/Fooocus

lllyasviel

48k

Focus on prompting and generating

black-forest-labs/flux

black-forest-labs

25.4k

Official inference repo for FLUX.1 models

huggingface/diffusers

huggingface

33.3k

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

invoke-ai/InvokeAI

invoke-ai

26.9k

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.

Stability-AI/sd3.5

Stability-AI

1.5k

No description provided.

open-mmlab/PowerPaint

open-mmlab

1.1k

[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model. 一个高质量多功能的图像修补模型，可以同时支持插入物体、移除物体、图像扩展、形状可控的物体生成，只需要一个模型

xinntao/Real-ESRGAN

xinntao

34.9k

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

Wan-Video/Wan2.1

Wan-Video

15.7k

Wan: Open and Advanced Large-Scale Video Generative Models

Tencent-Hunyuan/HunyuanVideo

Tencent-Hunyuan

11.9k

HunyuanVideo: A Systematic Framework For Large Video Generation Model

SkyworkAI/SkyReels-V2

SkyworkAI

6.7k

SkyReels-V2: Infinite-length Film Generative model

Lightricks/LTX-Video

Lightricks

9.8k

Official repository for LTX-Video

Stability-AI/generative-models

Stability-AI

27.1k

Generative Models by Stability AI

ace-step/ACE-Step-1.5

ace-step

8.5k

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

FunAudioLLM/CosyVoice

FunAudioLLM

20.4k

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

yl4579/StyleTTS2

yl4579

6.2k

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

RVC-Project/Retrieval-based-Voice-Conversion-WebUI

RVC-Project

35.1k

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

open-mmlab/Amphion

open-mmlab

9.7k

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

multimodal-art-projection/YuE

multimodal-art-projection

6.1k

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

myshell-ai/OpenVoice

myshell-ai

36.2k

Instant voice cloning by MIT and MyShell. Audio foundation model.

Tencent-Hunyuan/Hunyuan3D-2

Tencent-Hunyuan

13.4k

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

microsoft/TRELLIS

microsoft

12.1k

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

xxlong0/Wonder3D

xxlong0

5.3k

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

VAST-AI-Research/TripoSR

VAST-AI-Research

6.3k

TripoSR: Fast 3D Object Reconstruction from a Single Image

nerfstudio-project/nerfstudio

nerfstudio-project

11.4k

A collaboration friendly studio for NeRFs

nerfstudio-project/gsplat

nerfstudio-project

4.8k

CUDA accelerated rasterization of gaussian splatting

hiyouga/LlamaFactory

hiyouga

69.5k

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

axolotl-ai-cloud/axolotl

axolotl-ai-cloud

11.6k

Go ahead and axolotl questions

unslothai/unsloth

unslothai

59.4k

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

Lightning-AI/litgpt

Lightning-AI

13.3k

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

meta-pytorch/torchtune

meta-pytorch

5.7k

PyTorch native post-training library

huggingface/trl

huggingface

17.9k

Train transformer language models with reinforcement learning.

huggingface/peft

huggingface

20.9k

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

linkedin/Liger-Kernel

linkedin

6.3k

Efficient Triton Kernels for LLM Training

arcee-ai/mergekit

arcee-ai

6.9k

Tools for merging pretrained large language models.

argilla-io/distilabel

argilla-io

3.2k

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

datajuicer/data-juicer

datajuicer

6.2k

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

argilla-io/argilla

argilla-io

4.9k

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

sdv-dev/SDV

sdv-dev

3.5k

Synthetic data generation for tabular data

deepspeedai/DeepSpeed

deepspeedai

42k

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

hpcaitech/ColossalAI

hpcaitech

41.4k

Making large AI models cheaper, faster and more accessible

NVIDIA/Megatron-LM

NVIDIA

15.9k

Ongoing research training transformer models at scale

ray-project/ray

ray-project

41.9k

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

ray-project/ray

ray-project

41.9k

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

mlflow/mlflow

mlflow

25.1k

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.

treeverse/dvc

treeverse

15.5k

🦉 Data Versioning and ML Experiments

clearml/clearml

clearml

6.6k

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

wandb/weave

wandb

1.1k

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

bentoml/BentoML

bentoml

8.6k

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

zenml-io/zenml

zenml-io

5.3k

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

kubeflow/kubeflow

kubeflow

15.6k

Machine Learning Toolkit for Kubernetes

kserve/kserve

kserve

5.3k

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

langfuse/langfuse

langfuse

24.4k

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

Arize-ai/phoenix

Arize-ai

9.2k

AI Observability & Evaluation

evidentlyai/evidently

evidentlyai

7.4k

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.

comet-ml/opik

comet-ml

18.6k

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

BerriAI/litellm

BerriAI

42.2k

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

openlit/openlit

openlit

2.3k

Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs.

traceloop/openllmetry

traceloop

7k

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

Agenta-AI/agenta

Agenta-AI

4k

The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

Helicone/helicone

Helicone

5.4k

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

NVIDIA-NeMo/Guardrails

NVIDIA-NeMo

5.9k

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

guardrails-ai/guardrails

guardrails-ai

6.6k

Adding guardrails to large language models.

protectai/llm-guard

protectai

2.8k

The Security Toolkit for LLM Interactions

anulum/director-ai

anulum

2

Real-time LLM hallucination guardrail — NLI + RAG fact-checking with token-level streaming halt. Drop-in for any LLM backend.

meta-llama/PurpleLlama

meta-llama

4.1k

Set of tools to assess and improve LLM security.

NVIDIA/garak

NVIDIA

7.5k

the LLM vulnerability scanner

promptfoo/promptfoo

promptfoo

19.4k

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.

EleutherAI/lm-evaluation-harness

EleutherAI

12k

A framework for few-shot evaluation of language models.

stanford-crfm/helm

stanford-crfm

2.7k

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.

LiveCodeBench/LiveCodeBench

LiveCodeBench

834

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

TIGER-AI-Lab/MMLU-Pro

TIGER-AI-Lab

359

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

open-compass/opencompass

open-compass

6.8k

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.

confident-ai/deepeval

confident-ai

14.4k

The LLM Evaluation Framework

vibrantlabsai/ragas

vibrantlabsai

13.2k

Supercharge Your LLM Application Evaluations 🚀

huggingface/lighteval

huggingface

2.4k

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

huggingface/evaluate

huggingface

2.4k

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

huggingface/datasets

huggingface

21.4k

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

togethercomputer/RedPajama-Data

togethercomputer

4.9k

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

xlang-ai/OSWorld

xlang-ai

2.7k

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

protectai/llm-guard

protectai

2.8k

The Security Toolkit for LLM Interactions

promptfoo/promptfoo

promptfoo

19.4k

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.

PKU-Alignment/safe-rlhf

PKU-Alignment

1.6k

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

huggingface/alignment-handbook

huggingface

5.5k

Robust recipes to align language models with human and AI preferences

OpenRLHF/OpenRLHF

OpenRLHF

9.3k

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

TransformerLensOrg/TransformerLens

TransformerLensOrg

3.3k

A library for mechanistic interpretability of GPT-style language models

ndif-team/nnsight

ndif-team

883

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

decoderesearch/SAELens

decoderesearch

1.3k

Training Sparse Autoencoders on Language Models

meta-pytorch/captum

meta-pytorch

5.6k

Model interpretability and understanding for PyTorch

NVIDIA/garak

NVIDIA

7.5k

the LLM vulnerability scanner

Azure/PyRIT

Azure

2

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

tensorflow/tensorflow

tensorflow

194.5k

An Open Source Machine Learning Framework for Everyone

microsoft/onnxruntime

microsoft

19.8k

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

opencv/opencv

opencv

86.9k

Open Source Computer Vision Library

ultralytics/ultralytics

ultralytics

55.4k

Ultralytics YOLO 🚀

facebookresearch/detectron2

facebookresearch

34.3k

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

facebookresearch/sam2

facebookresearch

18.8k

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.

kornia/kornia

kornia

11.2k

🐍 Geometric Computer Vision Library for Spatial AI

google-ai-edge/mediapipe

google-ai-edge

34.5k

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

DLR-RM/stable-baselines3

DLR-RM

13k

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

vwxyzjn/cleanrl

vwxyzjn

9.5k

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

FLAIROx/JaxMARL

FLAIROx

780

Multi-Agent Reinforcement Learning with JAX

isaac-sim/IsaacLab

isaac-sim

6.8k

Unified framework for robot learning built on NVIDIA Isaac Sim

Farama-Foundation/Gymnasium

Farama-Foundation

11.6k

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

thuml/Time-Series-Library

thuml

11.9k

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

amazon-science/chronos-forecasting

amazon-science

5.1k

Chronos: Pretrained Models for Time Series Forecasting

unit8co/darts

unit8co

9.3k

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

winedarksea/AutoTS

winedarksea

1.4k

Automated Time Series Forecasting

pytorch/executorch

pytorch

4.5k

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

openvinotoolkit/openvino

openvinotoolkit

10k

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

apache/tvm

apache

13.2k

Open Machine Learning Compiler Framework

langflow-ai/langflow

langflow-ai

146.6k

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

langgenius/dify

langgenius

135.9k

Production-ready platform for agentic workflow development.

openclaw/openclaw

openclaw

348k

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

open-webui/open-webui

open-webui

130k

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

oobabooga/text-generation-webui

oobabooga

46.4k

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

lobehub/lobehub

lobehub

74.7k

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.

danny-avila/LibreChat

danny-avila

35.2k

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.

huggingface/chat-ui

huggingface

10.6k

The open source codebase powering HuggingChat

khoj-ai/khoj

khoj-ai

33.9k

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.

qwersyk/Newelle

qwersyk

1.3k

Newelle - Your Ultimate Virtual Assistant

Mintplex-Labs/anything-llm

Mintplex-Labs

57.6k

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

FlowiseAI/Flowise

FlowiseAI

51.5k

Build AI Agents, Visually

nomic-ai/gpt4all

nomic-ai

77.2k

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

janhq/jan

janhq

41.6k

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

SillyTavern/SillyTavern

SillyTavern

25.2k

LLM Frontend for Power Users.

Aider-AI/aider

Aider-AI

42.8k

aider is AI pair programming in your terminal

Arize-ai/phoenix

Arize-ai

9.2k

AI Observability & Evaluation

promptfoo/promptfoo

promptfoo

19.4k

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.

confident-ai/deepeval

confident-ai

14.4k

The LLM Evaluation Framework

NVIDIA/garak

NVIDIA

7.5k

the LLM vulnerability scanner

continuedev/continue

continuedev

32.3k

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

TabbyML/tabby

TabbyML

33.3k

Self-hosted AI coding assistant

cline/cline

cline

59.9k

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.

openinterpreter/open-interpreter

openinterpreter

63k

A natural language interface for computers

RooCodeInc/Roo-Code

RooCodeInc

23k

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

ggml-org/llama.vim

ggml-org

1.9k

Vim plugin for LLM-assisted code/text completion

olimorris/codecompanion.nvim

olimorris

6.4k

✨ AI Coding, Vim Style

jupyterlab/jupyter-ai

jupyterlab

4.2k

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

assistant-ui/assistant-ui

assistant-ui

9.2k

Typescript/React Library for AI Chat💬🚀

fastai/fastai

fastai

28k

The fastai deep learning library

Comfy-Org/example_workflows

Comfy-Org

23

A repo for storing all ComfyUI example workflows.

pytorch/examples

pytorch

23.8k

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.