How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make your agents production-ready.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Terra Invicta-inspired space battle simulator where AI models make tactical decisions in near-future ship combat scenarios

Liquid Audio - Speech-to-Speech audio models by Liquid AI

Universal memory layer for AI Agents

This Repo contains working code for my Neptune.ai blogs

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

Color conversion & manipulation library by the editors of the CSS Color specifications

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

GaiaPlatform - Main repository

Containers for machine learning

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

[CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

Fully automated homelab from empty disk to running services with a single command.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

NeuralProphet: A simple forecasting package

A research library for pytorch-based neural network pruning, compression, and more.

Count total lines of code across a GitHub organization

🧘 Things I think about when I write React code 🧘

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

Code for 3D object detection for autonomous driving

A fast and robust point cloud registration library

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

OpenVSLAM: A Versatile Visual SLAM Framework

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

DeepCalib: A Deep Learning Approach for Automatic Intrinsic Calibration of Wide Field-of-View Cameras