The world's simplest facial recognition api for Python and the command line

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

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

Get your documents ready for gen AI

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Stable Diffusion with Core ML on Apple Silicon

An extremely fast Python type checker and language server, written in Rust.

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

Go ahead and axolotl questions

Official repository for LTX-Video

The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

🎇 Quickly search over billions of images

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

Pure-Python Git implementation

Creates standalone executables from Python scripts with the same performance as the original script. It is cross-platform and should work on any platform that Python runs on.

Inspect: A framework for large language model evaluations

Communicate with an LLM provider using a single interface

🔮 Scalable reverse image search built on Kubernetes and Elasticsearch

Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)

Forget the past. Social Amnesia makes sure your social media accounts only show your posts from recent history, not from "that phase" 5 years ago.

Python bindings to PDFium, reasonably cross-platform.

Training Model Behavior in Agentic Systems

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

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

PGlite wrapper in Python for testing. Test your app with Postgres just as lite as SQLite.

Code for paper "G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment"