🎨 Diagram as Code for prototyping cloud system architectures

Python tool for converting files and office documents to Markdown.

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

OSX (macOS) inside a Docker container.

End-to-End Speech Processing Toolkit

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Hypothesis is a powerful, flexible, and easy to use library for property-based testing.

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

Bandit is a tool designed to find common security issues in Python code.

Agent Framework / shim to use Pydantic with LLMs

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

Replace 'hub' with 'ingest' in any github url to get a prompt-friendly extract of a codebase

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Efficient Triton Kernels for LLM Training

A python library for self-supervised learning on images.

Supercharge your API testing, catch bugs, and ensure compliance

🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library

Schedule-Free Optimization in PyTorch

Easy token price estimates for 400+ LLMs. TokenOps.

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

The fastest way to build robust AI agents

Agentless🐱: an agentless approach to automatically solve software development problems

Recipes to scale inference-time compute of open models

utilities for decoding deep representations (like sentence embeddings) back to text

🐝 GPTSwarm: LLM agents as (Optimizable) Graphs

[CVPR 2024] OneLLM: One Framework to Align All Modalities with Language