R3xpook

crawl4ai

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

llama_index

LlamaIndex is the leading framework for building LLM-powered agents over your data.

gradio

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

crewAI

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

BitNet

Official inference framework for 1-bit LLMs

Janus

Janus-Series: Unified Multimodal Understanding and Generation Models

stable-diffusion-webui-forge

ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Phi4, ...) (AAAI 2025).

chat-ui

Open source codebase powering the HuggingChat app

modelscope

ModelScope: bring the notion of Model-as-a-Service to life.

smol-course

A course on aligning smol models.

Liger-Kernel

Efficient Triton Kernels for LLM Training

swarms

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

lingua

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

OmniGen

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

entropix

Entropy Based Sampling and Parallel CoT Decoding

smollm

Everything about the SmolLM and SmolVLM family of models

distilabel

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

Smart-AutoClicker

An open-source auto clicker on images for Android

maestro

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

Qwen2-VL-Finetune

An open-source implementaion for fine-tuning Qwen2-VL and Qwen2.5-VL series by Alibaba Cloud.

self-adaptive-llms

A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!

search-and-learn

Recipes to scale inference-time compute of open models

magpie

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

multi1

multi1: create o1-like reasoning chains with multiple AI providers (and locally). Supports LiteLLM as backend too for 100+ providers at once.

lmms-finetune

A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.

Meissonic

[ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

joy-caption-batch

A batch captioning tool for joy_caption

Zamba2

PyTorch implementation of models from the Zamba2 series.

open-agentinstruct

An open-source recreation of the AgentInstruct agentic workflow for synthetic data generation