Automate anything with Codex CLI in a local Docker container with cron, file watchers, webhooks, search/indexing, speech, and hundreds of tools on tap.

SigNoz is an open-source observability platform native to OpenTelemetry with logs, traces and metrics in a single application. An open-source alternative to DataDog, NewRelic, etc. 🔥 🖥. 👉 Open sour…

Abseil Common Libraries (Python)

Beads - A memory upgrade for your coding agent

This is a repo with links to everything you'd ever want to learn about data engineering

Easily compute clip embeddings and build a clip retrieval system with them

An open source implementation of CLIP.

Reference PyTorch implementation and models for DINOv3

PyTorch code and models for the DINOv2 self-supervised learning method.

Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

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

[NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors

We write your reusable computer vision tools. 💜

Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

A high-throughput and memory-efficient inference and serving engine for LLMs

[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.

Toolbox of models, callbacks, and datasets for AI/ML researchers.

Easy benchmarking of all publicly accessible implementations of convnets

Code from the paper "Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models"

Contexts Optical Compression

The best ChatGPT that $100 can buy.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Multidimensional item response theory

Bayesian IRT models in Python

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

High-performance retrieval engine for unstructured data

AutoEvals is a tool for quickly and easily evaluating AI model outputs using best practices.

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.