AI Tools Directory

PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.

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

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.

Inspect: A framework for large language model evaluations

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.

Build memory-native AI agents with Memory OS — an open-source framework for long-term memory, retrieval, and adaptive learning in large language models. Agent Memory | Memory System | Memory Management | Memory MCP | MCP System | LLM Memory | Agents Memory System |

A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

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

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.

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

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

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

Large Language Model Text Generation Inference

OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)

🥂 Gracefully face hCaptcha challenge with multimodal large language model.

Adding guardrails to large language models.

Tools for merging pretrained large language models.

Automated Penetration Testing Agentic Framework Powered by Large Language Models

Access large language models from the command-line

AttackGen is a cybersecurity incident response testing tool that leverages the power of large language models and the comprehensive MITRE ATT&CK framework. The tool generates tailored incident response scenarios based on user-selected threat actor groups and your organisation's details.

Open Source Generative Process Automation (i.e. Generative RPA). AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models

Minimalistic large language model 3D-parallelism training

Reverse Engineering: Decompiling Binary Code with Large Language Models

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

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

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

Dream 7B, a large diffusion language model

Autonomous agents for everyone

AI Agent + Coding Agent + 300+ assistants: agentic AI desktop with autonomous coding, intelligent automation, and unified access to frontier LLMs.

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

🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai

DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！

Agent Zero AI framework

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code support via MCP protocol. Ranked #1 in agent-based frameworks.

✨ Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Autonomous Agents (LLMs) research papers. Updated Daily.

A holistic framework to enable the design, development, and evaluation of autonomous AIOps agents.

Build autonomous, resilient and observable AI agents with built-in workflow orchestration, security, statefulness and telemetry.

Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

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.

🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.

A symbiotic AI agent that remembers everything, acts autonomously, and extends your cognition.

Autonomous GPT-4 agent platform

A god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In this virtual world, AI characters possess independent thinking and memory, capable of autonomous social interactions, task completion, and developing complex social relationships through continuous communication.

A collection of autonomous agents 🤖️ powered by LLM.

TypeScript AI platform with AI chat, Autonomous agents, Software developer agents, chatbots and more

BaseAI — The Web AI Framework. The easiest way to build serverless autonomous AI agents with memory. Start building local-first, agentic pipes, tools, and memory. Deploy serverless with one command.

agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin993886460 (Beware of fake account)

AI writing agent powered by kimi-k2-thinking - autonomously creates novels and stories with deep reasoning

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

Build your autonomous hedge fund in minutes. AutoHedge harnesses the power of swarm intelligence and AI agents to automate market analysis, risk management, and trade execution.

AIlice is a fully autonomous, general-purpose AI agent.

OpenManus is an open-source initiative to replicate the capabilities of the Manus AI agent, a state-of-the-art general-purpose AI developed by Monica, which excels in autonomously executing complex tasks.

The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web

多平台模型接入，可扩展，多种输出格式，提供大语言模型聊天服务的插件 | A bot plugin for LLM chat with multi-model integration, extensibility, and various output formats

ComfyUI nodes for the Ultimate Stable Diffusion Upscale script by Coyote-A.

FLUX, Stable Diffusion, SDXL, SD3, LoRA, Fine Tuning, DreamBooth, Training, Automatic1111, Forge WebUI, SwarmUI, DeepFake, TTS, Animation, Text To Video, Tutorials, Guides, Lectures, Courses, ComfyUI, Google Colab, RunPod, Kaggle, NoteBooks, ControlNet, TTS, Voice Cloning, AI, AI News, ML, ML News, News, Tech, Tech News, Kohya, Midjourney, RunPod

High quality training free inpaint for every stable diffusion model. Supports ComfyUI

SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.

Multi-Platform Package Manager for Stable Diffusion

A selection of nodes for Stable Diffusion ComfyUI

fast-stable-diffusion + DreamBooth

Dynamic Thresholding (CFG Scale Fix) for Stable Diffusion (SwarmUI, ComfyUI, and Auto WebUI)

AI一键批量生成各类短视频,自动批量混剪短视频,自动把视频发布到抖音,快手,小红书,视频号上,赚钱从来没有这么容易过! 支持本地语音模型chatTTS,fasterwhisper,GPTSoVITS,支持云语音：Azure,阿里云,腾讯云。支持Stable diffusion,comfyUI直接AI生图。Generate short videos with one click using AI LLM,print money together! support:chatTTS,faster-whisper,GPTSoVITS,Azure,tencent Cloud,Ali Cloud.

Unleash endless possibilities with ComfyUI and Stable Diffusion, committed to crafting refined AI-Gen tools and cultivating a vibrant community for both developers and users.

A user-friendly plug-in that makes it easy to generate stable diffusion images inside Photoshop using either Automatic or ComfyUI as a backend.

Customizable Stable Diffusion frontend for ComfyUI

A framework for efficient model inference with omni-modality models

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

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Interactive visualizations of the geometric intuition behind diffusion models.

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

A general fine-tuning kit geared toward image/video/audio diffusion models.

Enjoy the magic of Diffusion models!

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

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.

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

High quality training free inpaint for every stable diffusion model. Supports ComfyUI

A MLX port of FLUX and other state of the art diffusion image models based on the Huggingface Diffusers implementation.

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

collection of diffusion model papers categorized by their subareas

[ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!

dLLM: Simple Diffusion Language Modeling

WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.

The ultimate training toolkit for finetuning diffusion models

A character-level language diffusion model trained on Tiny Shakespeare

Kandinsky 5.0: A family of diffusion models for Video & Image generation

Tiny AutoEncoder for Stable Diffusion (and other image models)

Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model

[ICCV 2025] Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".

Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

A pipeline parallel training script for diffusion models.

[ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simplified Inference (< 8G VRAM for 1024X768 resolution).

Code repo for "Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio" at the (CAI2) workshop, jointly held at (COLING 2022)

Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools

Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas, Perplexity Comet, Dia and Microsoft CoPilot Edge Browser

Free, ultrafast Copilot alternative for Vim and Neovim

Free, ultrafast Copilot alternative for Emacs

Flexpilot - Open-Source, Native and a True GitHub Copilot Alternative for VS Code

Clipboard Conqueror is a novel copy and paste copilot alternative designed to bring your very own LLM AI assistant to any text field.

VSCode extension of Quack Companion 💻 Turn your team insights into a portable plug-and-play context for code generation. Alternative to GitHub Copilot powered by OSS LLMs (Mistral, Gemma, etc.), served with Ollama.

Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.

A complete alternative for Overleaf with VSCode + Web + Git Integration + Copilot + Grammar & Spell Checker + Live Collaboration Support. Based on GitHub Codespace and Dev container.

An open-source alternative to GitHub copilot that runs locally.

FauxPilot - an open-source alternative to GitHub Copilot server

A alternative to Github Copilot for vscode until you get the access to github copilot

slime is an LLM post-training framework for RL Scaling.

🤗 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.

ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.

Fully Open Framework for Democratized Multimodal Training

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.

A Framework for LLM-based Multi-Agent Reinforced Training and Inference

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.

Awesome LLM pre-training resources, including data, frameworks, and methods.

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

Machine learning Guide. Learn all about Machine Learning Tools, Libraries, Frameworks, Large Language Models (LLMs), and Training Models.

A framework for creating grounded instruction based datasets and training conversational domain expert Large Language Models (LLMs).

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

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

🏗️ Fine-tune, build, and deploy open-source LLMs easily!

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

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

A powerful tool for creating fine-tuning datasets for LLM

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

Distributed AI Model Training and Fine-Tuning on Kubernetes

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

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

A survey on harmful fine-tuning attack for large language model

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

This repository contains different LLM chatbot projects (RAG, LLM agents, etc.) and well-known techniques for training and fine tuning LLMs.

🚀 One-stop solution for creating your digital avatar from chat history 💡 Fine-tune LLMs with your chat logs to capture your unique style, then bind to a chatbot to bring your digital self to life. 从聊天记录创造数字分身的一站式解决方案

Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

The easiest & fastest way to run customized and fine-tuned LLMs locally or on the edge

The Fastest Way to Fine-Tune LLMs Locally

Self-paced bootcamp on Generative AI. Tutorials on ML fundamentals, Ollama, LLMs, RAGs, LangChain, LangGraph, Fine-tuning, DSPy & AI Agents (CrewAI), (Using ChatGPT, gpt-oss, Claude, Qwen3, Gemma3, Llama 3)

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Framework for enhancing LLMs for RAG tasks using fine-tuning.

Local first semantic code search and chat | Leverage custom copilots with fine-tuning datasets from code in Alpaca, Conversational, Completion and Instruction format

This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

A pure MLX-based training pipeline for fine-tuning LLMs using GRPO on Apple Silicon.

Guide for fine-tuning Llama/Mistral/CodeLlama models and more

Official repository of my book "A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face"

Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

A curated list of Large Language Model resources, covering model training, serving, fine-tuning, and building LLM applications.

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

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

RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.

[EMNLP 2025] ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

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

A Survey on Multimodal Retrieval-Augmented Generation

This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG) pipeline.

A minimal Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

A Blazor Web App and Minimal API for performing RAG (Retrieval Augmented Generation) and vector search using the native VECTOR type in Azure SQL Database and Azure OpenAI.

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

Awesome-RAG-Vision: a curated list of advanced retrieval augmented generation (RAG) for Computer Vision

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Build your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js, TypeScript and Azure

This repository contains resources and materials for the "AI Agents and Retrieval Augmented Generation (RAG) for Cybersecurity Operations" and other courses by Omar Santos.

Running local Language Language Models (LLM) to perform Retrieval-Augmented Generation (RAG)

Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.

XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation

A community-driven collection of RAG (Retrieval-Augmented Generation) frameworks, projects, and resources. Contribute and explore the evolving RAG ecosystem.

Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

This repository contains advanced LLM-based chatbots for Q&A using LLM agents, and Retrieval Augmented Generation (RAG) and with different databases. (VectorDB, GraphDB, SQLite, CSV, XLSX, etc.)

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

A framework for fine-tuning retrieval-augmented generation (RAG) systems.

A full-stack demo showcasing a local RAG (Retrieval Augmented Generation) pipeline to chat with your PDFs.

"Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation" by Yifan Feng, Hao Hu, Xingliang Hou, Shiquan Liu, Shihui Ying, Shaoyi Du, Han Hu, and Yue Gao.

Visualization for a Retrieval-Augmented Generation (RAG) Assistant 🤖❤️📚

Retrieval-augmented generation (RAG) template powered by the AI SDK.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.

RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

Open-source document chat platform with semantic search, RAG (Retrieval Augmented Generation), and multi-provider AI support (OpenRouter, OpenAI, ImageRouter).