A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Open-Source Coding Agent in the terminal

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

Vehicle MTMC Tracking

Wan: Open and Advanced Large-Scale Video Generative Models

[AAAI 2025] GraSP: Simple yet Effective Graph Similarity Predictions

Trajectory prediction method using a stacked normalizing flow for fast and accurate density estimation.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Real-time webcam demo with SmolVLM and llama.cpp server

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

[TMLR 2026] LibMoE: A LIBRARY FOR COMPREHENSIVE BENCHMARKING MIXTURE OF EXPERTS IN LARGE LANGUAGE MODELS

Kolmogorov Arnold Networks

Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)

Temporal Graph Convolutional Network for Urban Traffic Flow Prediction Method

This repository contains several machine learning models that try to detect whether a room is occupied.

1DConvNet applied to room occupancy detection based on data from several environment sensors. Data courtesy of the UCI Machine Learning Repository.

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

A Python Library for Graph Outlier Detection (Anomaly Detection)

Game list rebuilding tool for SF2000 handheld

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

The implementation and data for the paper "Forecasting Unobserved Node States with spatio-temporal Graph Neural Networks".

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

CodeBERT

Data and code for the IEEE S&P'22 paper SAILFISH: Vetting Smart Contract State-Inconsistency Bugs in Seconds

Source code of EtherSolve: static analysis of Ethereum bytecode

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Smart Contract Vulnerability Detection Using Graph Neural Networks (IJCAI-20 Accepted)

Graph Neural Network Library for PyTorch