Top 100 AI Open Source Projects on GitHub
Top 100 AI Open Source
100 Projects · 8 Categories Updated 2025

100 Most-Starred AI &
ML Open Source Repos

Curated by GitHub star count — frameworks, agents, LLMs, image generation, voice, code assistants, RAG, and developer tooling, organized by category.

100
Projects
8
Categories
5M+
Total Stars
2025
Updated
🛠
AI Tooling Platforms, SDKs & productivity tools 13 repos
AP
awesome-chatgpt-prompts
f · Community
★ 108k
Curated collection of the best ChatGPT prompt examples and personas for developers and power users.
Markdown
↗ GitHub
GA
GPT Academic
binary-husky
★ 65k
LLM-enhanced academic research interface with paper reading, code editing, and LaTeX support.
Python
↗ GitHub
DF
Dify
Dify AI
★ 61k
Open-source LLM app development platform with visual orchestration, RAG pipeline, and model hub.
TypeScript
↗ GitHub
N8
n8n
n8n-io
★ 47k
Extendable workflow automation with 200+ integrations, AI nodes, and self-hosting support.
TypeScript
↗ GitHub
LB
LobeChat
LobeHub
★ 47k
Modern AI chat framework with plugin marketplace, vision, TTS, and multi-model support.
TypeScript
↗ GitHub
CC
Langchain-Chatchat
ChatChat Space
★ 33k
Local private knowledge Q&A system combining LangChain with local LLMs for enterprise use.
Python
↗ GitHub
OP
OpenAI Python SDK
OpenAI
★ 22k
Official Python library for the OpenAI API with async support, streaming, and typed responses.
Python
↗ GitHub
HY
Haystack
deepset
★ 17k
End-to-end NLP framework for building custom Q&A, document search, and RAG pipelines.
Python
↗ GitHub
LL
LiteLLM
BerriAI
★ 16k
Call 100+ LLM APIs using the OpenAI input/output format with one unified Python SDK.
Python
↗ GitHub
EV
OpenAI Evals
OpenAI
★ 14k
Framework for evaluating LLMs and LLM systems with built-in and custom evaluation metrics.
Python
↗ GitHub
GD
Guidance
Microsoft
★ 18k
Constrained LLM generation with templates, output validation, and structured response control.
Python
↗ GitHub
PF
PromptFlow
Microsoft
★ 9.4k
Build, evaluate, and deploy high-quality LLM flows from prototype to production with monitoring.
Python
↗ GitHub
PE
PEFT
Hugging Face
★ 16k
Parameter-efficient fine-tuning: LoRA, Prefix Tuning, P-Tuning for large pretrained models.
Python
↗ GitHub
🤖
AI Agents Autonomous agents, multi-agent frameworks & orchestration 15 repos
AG
AutoGPT
Significant Gravitas
★ 167k
Experimental autonomous AI agent that chains GPT calls to accomplish complex long-horizon tasks without human input.
LC
LangChain
LangChain AI
★ 92k
Build context-aware reasoning applications with LLMs using chains, agents, tools, and memory modules.
OI
Open Interpreter
Open Interpreter
★ 55k
LLM-powered terminal that writes and runs code locally — a natural-language interface to your computer.
MG
MetaGPT
geekan
★ 44k
Multi-agent LLM framework assigning PM, architect, and engineer roles to build complete software projects.
AU
AutoGen
Microsoft
★ 34k
Enable next-generation LLM applications via multi-agent conversations with human-in-the-loop support.
OH
OpenHands
All Hands AI
★ 34k
Platform for autonomous AI software agents that can write, edit, run, debug, and browse the web.
HG
HuggingGPT (JARVIS)
Microsoft
★ 24k
Connect ChatGPT with hundreds of Hugging Face expert models to solve complex AI tasks step-by-step.
CD
ChatDev
OpenBMB
★ 26k
Communicative agents for software development — LLM-powered team of PM, developer, and QA tester.
SK
Semantic Kernel
Microsoft
★ 22k
SDK integrating LLMs into .NET, Python, and Java apps with plugins, planners, and memory.
CA
CrewAI
CrewAI Inc
★ 22k
Framework for orchestrating role-based autonomous AI agent teams for complex collaborative tasks.
SW
Swarm
OpenAI
★ 17k
Lightweight, experimental multi-agent orchestration framework for educational purposes from OpenAI.
PH
Phidata
Phidata HQ
★ 15k
Build AI assistants with memory, knowledge, tools, and reasoning from a unified agent framework.
SV
Skyvern
Skyvern AI
★ 9k
Automate browser workflows using LLMs and computer vision — no brittle CSS selectors needed.
CM
CAMEL
CAMEL AI
★ 6k
Communicative Agents for Mind Exploration — role-playing multi-agent framework for LLM cooperation.
LK
LiveKit Agents
LiveKit
★ 5k
Build real-time multimodal voice and video AI agents with production-ready WebRTC infrastructure.
🧠
LLM & Models Large language model repos, serving engines & fine-tuning 30 repos
HF
Transformers
Hugging Face
★ 131k
State-of-the-art pretrained models for NLP, vision, and audio on PyTorch, TensorFlow, and JAX.
OL
Ollama
Ollama
★ 95k
Run Llama 3, Mistral, Gemma, and 80+ large language models locally with a single command.
G4
GPT4All
Nomic AI
★ 70k
Run private, no-internet LLMs locally on CPU and GPU — privacy-first AI assistant for everyone.
LC
llama.cpp
ggerganov
★ 66k
LLM inference in pure C/C++ with quantization — runs Llama, Mistral, and Gemma on CPU with no GPU.
LL
LLaMA
Meta AI
★ 57k
Open foundation language model from Meta — 7B to 65B parameters for research and production use.
CG
ChatGLM-6B
THUDM
★ 40k
Bilingual Chinese-English dialogue language model based on the General Language Model architecture.
NG
nanoGPT
karpathy
★ 37k
Minimal, fast GPT-2 training and inference codebase — the simplest, fastest repo for training medium-size GPTs.
FC
FastChat
LMSYS Org
★ 36k
Open platform for training, serving, and evaluating LLMs — home of Vicuna and Chatbot Arena.
LF
LLaMA-Factory
hiyouga
★ 35k
Unified fine-tuning framework for 100+ LLMs with LoRA, QLoRA, full-parameter, and RLHF support.
VL
vLLM
vLLM Project
★ 35k
High-throughput, memory-efficient LLM inference and serving engine powered by PagedAttention.
LC
llm.c
karpathy
★ 28k
LLM training in pure C and CUDA with no PyTorch dependency — fast, educational GPT-2 implementation.
L3
LLaMA 3
Meta AI
★ 26k
Next-generation open foundation models from Meta with 8B, 70B, and 405B parameter variants.
LA
LocalAI
mudler
★ 24k
Free, open-source OpenAI-compatible local inference server for LLMs, image, and audio generation.
US
Unsloth
unslothai
★ 22k
Finetune LLMs 2× faster with 50% less VRAM — Llama 3, Mistral, Gemma with no accuracy loss.
MG
minGPT
karpathy
★ 20k
Clean, minimal PyTorch re-implementation of GPT training — ~300 lines, pure education-first codebase.
LV
LLaVA
haotian-liu
★ 20k
Visual instruction tuning for large multimodal models — connects CLIP vision encoder with language models.
Q2
Qwen 2
Alibaba QwenLM
★ 14k
Series of open language models from Alibaba with strong multilingual and coding capabilities.
MB
Mamba
State Spaces
★ 12k
Linear-time sequence model with selective state spaces — a compelling alternative to Transformers at scale.
OL
OpenLLM
BentoML
★ 10k
Run any open-source LLM as an OpenAI-compatible REST API server with easy local and cloud deployment.
LP
llama-cpp-python
abetlen
★ 9k
Python bindings for llama.cpp — run local LLMs with an OpenAI-compatible Python API.
MI
Mistral
Mistral AI
★ 9k
Reference implementation of Mistral 7B — an efficient, high-performance open-weights language model.
MN
MiniCPM
OpenBMB
★ 8k
Edge-capable language models with strong performance for mobile and IoT — small but mighty LLMs.
TI
TGI
Hugging Face
★ 8k
Production-grade toolkit for deploying and serving Large Language Models at scale with low latency.
DV
DeepSeek-V2
DeepSeek AI
★ 8k
Mixture-of-Experts language model — 236B total parameters, 21B active, strong and economical inference.
GN
GPT-NeoX
EleutherAI
★ 7k
20B parameter autoregressive language model trained on the Pile dataset — open and fully replicable.
IV
InternVL
OpenGVLab
★ 6k
Vision-language foundation models matching closed-source GPT-4V performance on major visual benchmarks.
P3
Phi-3 CookBook
Microsoft
★ 5k
Samples and guides for Microsoft's Phi-3 small language models — fine-tuning, inference, and deployment.
GM
Gemma PyTorch
Google
★ 5k
Lightweight open models built with Gemini research — capable yet compact LLMs for diverse use cases.
QV
Qwen-VL
Alibaba QwenLM
★ 4k
Large vision-language model supporting image, text, and multi-region visual understanding and generation.
TT
TorchTune
PyTorch
★ 4k
PyTorch-native library for fine-tuning and experimenting with LLMs using simple, modular APIs.
G4
GLM-4
THUDM
★ 4k
General language model with all-tools capability — function calling, code, browsing, and image understanding.
🎨
Image Generation Diffusion models, visual AI & creative tools 8 repos
SD
SD WebUI
AUTOMATIC1111
★ 141k
Feature-rich browser interface for Stable Diffusion with extensions, scripts, and advanced controls.
CU
ComfyUI
comfyanonymous
★ 59k
Powerful modular node-based UI for Stable Diffusion workflows with custom extension support.
SB
Stable Diffusion
Stability AI
★ 37k
Latent text-to-image diffusion model for high-resolution photorealistic image synthesis from text prompts.
CN
ControlNet
lllyasviel
★ 29k
Neural network for adding spatial conditioning controls to Stable Diffusion via auxiliary encoders.
RE
Real-ESRGAN
xinntao
★ 28k
Practical algorithms for general real-world image and video super-resolution using enhanced ESRGAN.
DI
Diffusers
Hugging Face
★ 25k
State-of-the-art diffusion model library for image, audio, and 3D generation — training and inference.
IV
InvokeAI
InvokeAI
★ 23k
Professional Stable Diffusion toolkit for creatives with a node editor, canvas, and custom workflows.
CV
CogVideo
THUDM
★ 7k
Large-scale text-to-video generation model pre-trained on billions of text-video aligned pairs.
🎙
Voice & Audio Speech recognition, TTS, and voice cloning 8 repos
WH
Whisper
OpenAI
★ 72k
Robust general-purpose speech recognition trained on 680,000 hours of multilingual web audio data.
GS
GPT-SoVITS
RVC-Boss
★ 37k
1-minute voice cloning with few-shot zero-shot TTS — fine-tune your own voice model quickly and easily.
WC
whisper.cpp
ggerganov
★ 35k
High-performance C/C++ port of OpenAI Whisper enabling real-time, on-device speech transcription.
CT
Coqui TTS
Coqui AI
★ 35k
Deep learning text-to-speech toolkit with 1,100+ pretrained models and dozens of supported languages.
BK
Bark
Suno AI
★ 34k
Text-prompted generative audio model producing voice, music, sound effects, and multilingual speech.
OV
OpenVoice
MyShell AI
★ 29k
Instant, flexible voice cloning with precise tone, style, and language control for diverse speakers.
TT
Tortoise TTS
neonbjb
★ 12k
Multi-voice TTS system producing remarkably realistic speech — slow but exceptional audio quality output.
AM
Amphion
OpenMMLab
★ 7k
Open-source audio, music, and speech generation toolkit providing a unified research platform.
⚙️
ML Frameworks Core training, distributed computing & scientific ML 11 repos
TF
TensorFlow
Google
★ 185k
End-to-end open source ML platform for training and deploying models across every environment and device.
PT
PyTorch
Meta AI
★ 82k
Tensors and dynamic neural networks with strong GPU acceleration — the go-to deep learning framework.
DS
DeepSpeed
Microsoft
★ 34k
Deep learning optimization library enabling training of 100B+ parameter models with extreme efficiency.
RY
Ray
Anyscale
★ 32k
Unified framework for scaling AI and Python applications from a laptop to a large distributed cluster.
JX
JAX
Google
★ 29k
Composable NumPy transformations — autograd, JIT compilation, VMAP, and PMAP on CPUs, GPUs, and TPUs.
TG
tinygrad
tinygrad
★ 26k
Simple deep learning framework with a ~1000-line Python core — for learning and fast inference on edge.
MF
MLflow
MLflow
★ 18k
Open-source platform for the full ML lifecycle — experiment tracking, model registry, and deployment.
AF
AlphaFold
Google DeepMind
★ 12k
AI system predicting protein 3D structures with near-atomic accuracy — a landmark biology breakthrough.
TR
Triton
OpenAI
★ 12k
A language and compiler for writing highly efficient custom GPU kernels without requiring CUDA expertise.
AC
Accelerate
Hugging Face
★ 8k
Run PyTorch training on any distributed configuration with minimal code change and maximum performance.
FX
Flax
Google
★ 6k
Neural network library built on JAX — focused on flexibility and performance for deep learning research.
🔍
RAG & Vector Search Retrieval-augmented generation, vector databases & document Q&A 9 repos
PG
PrivateGPT
imartinez
★ 53k
Ask questions to your documents using LLMs locally — full privacy, no data ever leaves your machine.
LI
LlamaIndex
LlamaIndex
★ 36k
Data framework for connecting LLMs to external knowledge, databases, and structured data sources.
MV
Milvus
Milvus
★ 31k
Cloud-native vector database built for scalable similarity search and AI-powered application backends.
LG
LocalGPT
PromtEngineer
★ 20k
Chat privately with your local documents using LLMs — zero data leaves your device at any time.
KT
Kotaemon
Cinnamon
★ 20k
Clean, customizable RAG-based UI for chatting with your documents — easy to self-host and extend.
RP
ChatGPT Retrieval Plugin
OpenAI
★ 20k
ChatGPT plugin enabling semantic document search using various vector database backends.
QD
Qdrant
Qdrant
★ 20k
Vector database and search engine built in Rust — designed for high performance AI application backends.
CH
Chroma
Chroma
★ 16k
Open-source AI-native embedding database for building LLM apps with blazing-fast semantic retrieval.
WV
Weaviate
Weaviate
★ 11k
Open-source ML-native vector database — store objects and vectors for semantic search and RAG pipelines.
💻
Code AI AI coding assistants, code search & completion 4 repos
TB
Tabby
TabbyML
★ 22k
Self-hosted, open-source AI coding assistant — a privacy-friendly GitHub Copilot alternative you own.
CO
Continue
Continue Dev
★ 18k
Open-source AI code assistant integrating deeply into VS Code and JetBrains with any LLM backend.
TypeScript
↗ GitHub
DS
DeepSeek-Coder
DeepSeek AI
★ 12k
Code-focused LLM trained on 2T tokens of code and natural language — strong fill-in-the-middle performance.
BP
Bloop
Bloop AI
★ 10k
AI-powered code search and navigation — search your entire codebase using natural language queries.

Star counts are approximate as of 2025 · Data sourced from public GitHub repositories

Built for the open source AI community · GitHub