Open ChatGPT Atlas is an open‑source Chrome/Edge extension (and optional Electron app) that lets an AI control the browser (via Gemini 2.5 Computer‑Use) and call over 500 third‑party services (via Composio). Install with Node, load the built `dist` folder, add your Google and optional Composio API keys, then use the sidebar chat to give natural‑language commands like “click this button” or “create a GitHub issue.” It offers visual feedback, safety confirmations, and runs entirely client‑side.

Text0 is an AI-powered text editor that provides smart autocomplete and reference-aware suggestions by integrating with tools like GitHub, Notion, and Linear.

A modular framework for fate mapping in single-cell data that uses Markov state modeling to estimate cellular dynamics and differentiation probabilities.

An operating system for AI computers that simplifies the deployment and management of AI infrastructure on owner-controlled hardware across NVIDIA, AMD, and Intel accelerators.

Python bindings for the depthai-core C++ library, allowing developers to build AI and computer vision applications for Luxonis hardware using Python.

A local-first AI application and agent platform that turns model runtimes into durable apps and versioned services, featuring optimized local inference for large MoE models.

Nyno is a backend-as-code framework that allows developers to build and deploy AI workflows using a simple configuration language instead of writing complex backend code.

A streaming anomaly detection library that uses calibrated forecasters to turn data streams into surprise signals with controlled false-alarm rates.

A Haskell library for probabilistic programming that enables the modular composition of Bayesian inference algorithms.

A token management platform that standardizes various AI model APIs into OpenAI, Anthropic, and Gemini formats to enable unified access across different tools.

A fast Rust-based tokenizer and morphological analyzer that optimizes the Viterbi algorithm for high-speed tokenization, especially for large dictionaries.

A collection of autonomous behavior demonstrations for TurtleBot3 and TurtleBot 4 using behavior trees in ROS 2, featuring both Python and C++ implementations.

A Docker and Podman wrapper for ComfyUI that provides pre-configured NVIDIA CUDA environments to simplify installation and GPU hardware compatibility.

SPDL is a library for scalable and performant data loading, providing pipeline abstractions and operations for processing array data efficiently.

rocBLAS is a Basic Linear Algebra Subprograms library implemented in HIP and optimized for AMD GPUs to provide high-performance linear algebra operations.

A self-hosted AI-powered second brain for Android that archives, summarizes, and organizes content from Instagram, YouTube, and the web.

A matrix manipulation and computation library for JavaScript that provides essential linear algebra operations and decompositions.

A high-performance ocean simulator written in pure Python that supports JAX for GPU acceleration and MPI for distributed computing to model everything from toy models to global oceans.

A computer vision program that uses two webcams to calibrate stereo vision and measure the distance to objects using disparity maps and regression.

A high-performance scientific computing library for the V language providing linear algebra, numerical methods, and GPU acceleration for AI and scientific research.

A Python-embedded, MLIR-based language and compiler for the modular design and programming of high-performance machine learning accelerators.

A browser extension that integrates a private DeepSeek-powered AI co-pilot into any webpage, allowing users to interact with AI via text selection and floating chat windows.

An AI-powered quantitative trading toolset that integrates with AI agents via MCP to help users discover and backtest trading strategies for the Taiwan stock market.

ReceiptHero is an open-source receipt management app that uses AI-powered OCR to automatically extract and categorize expense data from uploaded receipt images.

A VitePress plugin that automatically creates LLM‑friendly Markdown files (`llms.txt` and `llms‑full.txt`) and optional UI buttons for copying/downloading pages as Markdown, with support for custom labels, multilingual configs, and special `<llm-only>` / `<llm-exclude>` tags.

A CLI tool that aggregates directories, source code, and web pages into a single Markdown file optimized for LLM ingestion, featuring code compression and token counting.

An OSINT intelligence system that scrapes global news, uses AI to analyze and score its value, and leverages a vector database for correlation and similarity search.

A Julia package that provides structured, named access to flat vectors, allowing complex scientific models to be composed without manual index tracking.

A Python-based analysis kit for neuroscience research, focusing on the processing and analysis of functional Magnetic Resonance Imaging (fMRI) data.

An AI agent that uses LLMs and image recognition to automate daily tasks, navigation, and activities in the game Infinity Nikki via screen capture and input simulation.

A world model framework and dataset for autonomous driving that uses VQ-VAE for video compression and a GPT-based model to predict future driving scenes.

Tournesol is a collaborative platform for identifying public-interest videos to build an open database for AI ethics and recommendation system research.

A persistent, embedded graph database for Python that uses a fluent API for queries and supports SIMD-optimized vector similarity search.

A VS Code extension that gives AI assistants live access to SAP systems, enabling autonomous code analysis, debugging, and development workflows using natural language.

An open-source cloud hosting platform that enables one-click deployment and management of dedicated VPS instances for AI agent runtimes like OpenClaw and Hermes.

InternAgentHarness (InternBootcamp) is an open‑source framework for creating, running, and evaluating multi‑turn, tool‑augmented LLM agents. It lets researchers define synthetic tasks, expose verified external tools, manage multi‑round interactions, compute rewards, and log full trajectories for data generation or RL training.

An open-source toolkit by Google Cloud for deploying and managing AI/ML and high performance computing (HPC) environments using customizable blueprints.

A CLI tool that transcribes YouTube videos or local media files using Whisper, with optional AI-powered summarization and translation.

A Kubernetes-native API for managing groups of Jobs as a single unit, specifically designed to simplify the deployment of distributed AI/ML training and HPC workloads.

A high-performance PyTorch optimizer library that uses compiled, composable building blocks to fuse operations into Triton kernels for faster training and lower memory usage.

A Python implementation of Monte Carlo Tree Search (MCTS) used to experiment with decision-making in a state-based game environment.

A niche computer vision toolkit providing utilities for 3D vision, torch-native mesh handling, and pre-built PyTorch neural network blocks.

OSSIM is an open-source C++ geospatial image processing library that provides tools for orthorectification, reprojection, and analysis of geospatial imagery.

A Python interface for openSMILE that enables the extraction of standardized audio features for machine learning research.

A pure-Python desktop application and library for chemistry and cheminformatics that implements molecular visualization, SMILES parsing, and MMFF94 optimization from scratch without external C++ dependencies.

A resiliency framework for PyTorch-based AI training that maximizes goodput by providing automatic fault detection, in-process restarting, and efficient checkpointing.

An AI-powered R package that translates natural language queries into executable R code for data analysis, allowing users to to analyze data without writing code.

A scalable, block-sparse tensor framework for high-performance tensor arithmetic that allows users to compose complex expressions using math-like C++ syntax.