skrl is a modular Reinforcement Learning library implemented in PyTorch, JAX, and NVIDIA Warp that supports a wide variety of environment interfaces for training agents.

A tuned OpenCL BLAS library that provides high-performance linear algebra routines for a wide variety of GPUs and accelerators.

A multi-tenant Postgres platform that decouples storage from compute to help B2B SaaS applications scale securely and efficiently with integrated vector database support.

An AI-native software testing platform that uses a single YAML-based declarative language to automate API, Web, mobile, and LLM tests without requiring traditional code scripts.

A long-context code retrieval and reproduction benchmark that measures an LLM's ability to reproduce specific function bodies verbatim from a large source corpus.

A unified and lightweight framework for the curation, packaging, loading, and evaluation of massive AI datasets, supporting multiple formats like LMDB and Pickle.

A bridge enabling two-way communication between the CARLA simulator and ROS, allowing for the control of autonomous driving agents and the retrieval of sensor data.

A lightweight, hackable framework for chat-based LLMs that provides model-agnostic tool usage and function calling without opinionated prompt management.

A lightweight, local-first Markdown editor that integrates with local and cloud AI to serve as a distraction-free writing assistant.

A multi-channel, multi-language chatbot solution on AWS that uses LLMs and RAG to automate customer support across chat, voice, and SMS.

An R package providing fast C++ implementations of density-based clustering algorithms like DBSCAN and HDBSCAN for spatial data analysis and outlier detection.

A Python toolbox for evaluating grayscale and binary image segmentation models, providing comprehensive metrics and automated curve plotting.

A node-based visual editor that streamlines AI movie production by automating the workflow between LLMs for prompting and ComfyUI for image and video generation.

UGround is an open‑source visual‑language model (2 B/7 B/72 B) fine‑tuned to locate UI elements in screenshots from a textual description. The repo ships pretrained weights, a >1 M‑image GUI grounding dataset, evaluation scripts for four benchmarks, and a Hugging Face demo. Inference runs via vLLM with a simple prompt that returns (x, y) coordinates. The 72 B model achieves state‑of‑the‑art scores on the ScreenSpot benchmark and is described in an ICLR 2025 oral paper.

A flexible grid-based environment for Partially-Observable Multi-Agent Pathfinding (PO-MAPF), designed for testing decentralized navigation and collision avoidance in multi-agent systems.

An autonomous AI agent pipeline for rigorous academic research that automates literature review, full-text verification, and APA 7th document generation.

A provider-agnostic PHP SDK that provides a uniform API for interacting with various generative AI models for text, image, and embedding generation.

A collection of student autonomous driving models (BEVFormer, UniAD, VAD) trained via a world-model RL teacher for benchmarking in the Bench2Drive framework.

An open-source reporting and ETL framework for creating professional reports and automating data tasks from any database or NoSQL source.

A Python quantitative‑trading platform that structures the workflow into a “Three‑Ministries‑Six‑Departments” hierarchy, offers back‑testing, multi‑strategy management, risk‑first execution, and an AI‑driven natural‑language stock‑screening feature. It runs via a FastAPI + HTML dashboard, supports multiple data sources, and is free for personal/academic use (commercial use needs a license).

A fast, lightweight Flutter plugin for scanning barcodes and QR codes with the device camera, supporting Android, iOS, macOS, and web with real-time detection and customizable camera behavior.

eCAL is a high-performance, brokerless middleware for interprocess communication that provides publish-subscribe and server-client patterns with zero configuration.

A C# framework for audio and video fingerprinting and recognition, enabling the fast identification of media content through acoustic and video hashes.

A Burp Suite extension for WeChat mini-program penetration testing that automates decryption, API extraction, and uses AI to infer request parameters from decompiled source code.

A Python library for cloud-native Synthetic Aperture Radar (SAR) processing that provides geometric and radiometric terrain correction for Sentinel-1 satellite data.

FarmBot OS is the operating system for FarmBot devices, enabling the automated operation of the core hardware.

Neanderthal is a Clojure library for high-performance matrix and linear algebra computations utilizing optimized native BLAS and LAPACK routines on CPU and GPU.

A type-safe, in-memory tabular data processing library for the JVM that provides compile-time column access and functional transformations.

Bacalhau is a distributed compute orchestration framework that enables "Compute Over Data," allowing users to run jobs directly where large datasets are stored to reduce latency and costs.

An AI research assistant that connects AI industry trends to the financial and operational impact on AI infrastructure companies across the supply chain.

A Python implementation of the RANSAC method for fitting primitive geometric shapes to 3D point clouds, useful for 3D reconstruction and SLAM.

An interactive, high-performance data table for Jupyter notebooks that streamlines exploratory data analysis with features like autocleaning, histograms, and lazy loading.

A high-performance Go implementation of the Jieba Chinese word segmentation tool, providing multiple segmentation modes and POS tagging.

A lightweight web dashboard for monitoring and managing OpenClaw AI agents, models, and sessions without requiring a database.

A Python toolbox for visualizing high-dimensional data through an integrated pipeline of dimensionality reduction, clustering, and advanced 2D/3D plotting.

A single-binary Kubernetes dashboard with multi-cluster management and AI integration for automated troubleshooting and resource monitoring.

A sample chat web application that integrates with Azure OpenAI, supporting both general chat and RAG-based conversations using various Azure and third-party data sources.

A JIT compiler for high-performance GPU programming written in C#, enabling .NET developers to write GPU kernels without native dependencies.

A TypeScript SDK for the v0 API that allows developers to programmatically create chats and generate UI previews using v0's generative AI capabilities.

A cross-platform C++/Python development toolkit for connecting to, configuring, and visualizing data from Ouster Lidar sensors.

A header-only C++ template library providing custom arithmetic plug-in types to optimize AI and HPC algorithms through mixed-precision and alternative number formats.

A modular library of statistical algorithms that implement differential privacy to enable the privacy-preserving computation of data insights.

A cross-platform, modular terminal and browser designed to centralize the installation, configuration, and management of local AI interfaces and WebUIs.

A fast, parallelized sparse matrix multiplication library that integrates top-n result selection to reduce memory usage and improve performance when matching large feature vectors.

A POSIX-compatible generative shell that integrates AI agents directly into the command line for natural language command generation and agentic scripting.

An Ansible-based framework for automating the setup and benchmarking of distributed AI clusters using tools like llama.cpp and distributed-llama.

A browser extension that integrates AI chat capabilities directly into the web browsing experience, supporting multiple LLM APIs and site-specific integrations.

A Python implementation of the CMA-ES algorithm for derivative-free numerical optimization of difficult, non-convex, and noisy problems in continuous and mixed-integer spaces.