Stars
🕷️ Undetectable, Lightning-Fast, and Adaptive Web Scraping for Python
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
Make websites accessible for AI agents
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser instance that lets you automate the web without worrying about infrastructure.
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Lightning-fast serving engine for any AI model of any size. Flexible. Easy. Enterprise-scale.
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
ACPI hotpatches, fixes, and guides for OpenCore. Optimize your Hackintosh and run macOS 13+ on Wintel PCs with OpenCore Legacy Patcher.
NVIDIA Linux open GPU with P2P support
Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥
Official implementation of Half-Quadratic Quantization (HQQ)
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
A fast inference library for running LLMs locally on modern consumer-class GPUs
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…
A high-throughput and memory-efficient inference and serving engine for LLMs
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
An Open Source text-to-speech system built by inverting Whisper.
Privilege Escalation Enumeration Script for Windows
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Universal LLM Deployment Engine with ML Compilation
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.