A high-performance serving system for machine learning models designed to manage model lifetimes and provide versioned inference via gRPC and HTTP in production environments.

A TensorFlow 2 library from DeepMind that provides simple, composable abstractions for building neural networks for ML research.

A distributed deep learning training framework that makes it is easy to scale single-GPU training scripts to multiple GPUs and hosts across TensorFlow, PyTorch, Keras, and MXNet.

SlideRule is a product rehearsal engine that transforms a one-sentence idea into a gated, runnable application preview by generating a comprehensive business structure.

A multi-agent collaboration system based on the OpenClaw framework that organizes AI agents into a hierarchical government or corporate structure for efficient task delegation and execution.

A platform for structured feedback and evaluations for AI agents, allowing domain experts to review agent responses and turn those reviews into automated tests.

A Python library providing an Actor model framework to build scalable agent-integrated systems by connecting AI agents with software interfaces.

A full-scenario Java AI development framework for building LLM applications, RAG knowledge bases, and multi-agent systems with native integration into the Java ecosystem.

Kernel Memory is a multi-modal AI service for efficient dataset indexing and Retrieval Augmented Generation (RAG), providing tools for data ingestion pipelines and natural language querying with citations.

LiveKit Python SDK provides async client‑side tools to join LiveKit rooms, publish/receive video‑audio tracks, run RPC calls, and control hardware codecs. The companion `livekit‑api` package wraps LiveKit’s server REST endpoints for room creation, token generation, SIP, egress, etc. It also integrates with LiveKit Agents for voice‑AI bots that combine STT, LLM, and TTS models.

A modular framework of building blocks for rapidly developing GenAI applications, featuring tools for RAG, multi-agent workflows, and full-stack chat infrastructure.

GPTeam is a multi-agent simulation where AI agents collaborate, communicate, and move through a simulated world to achieve common goals.

Shippie is an extendable code-review agent that analyzes diffs and explores codebases to identify bugs, secrets, and inefficiencies during the pull request process.

An open-source AI orchestration framework that implements an agentic agile workflow to prevent context loss and planning inconsistency in AI-assisted software development.

A low-code development tool for building multi-agent LLM applications that simplifies the process of prototyping, deploying, and iteratively optimizing AI workflows.

A Python framework for producing structured outputs and building agentic AI workflows using tasks, specialized agents, and type-safe results.

A decentralized P2P network where autonomous AI agents collaboratively conduct ML research, pool compute for distributed training and inference, and share discoveries via a global leaderboard.

KerasHub is a pretrained modeling library that provides multi-framework implementations of popular AI models for text, image, and audio, supporting JAX, TensorFlow, and PyTorch.

An open-source project providing Chinese-enhanced LLaMA and Alpaca models through vocabulary expansion and instruction fine-tuning for improved Chinese NLP tasks.

A browser extension that automatically detects and solves various types of CAPTCHAs in the background using an API key.

Bot Framework Web Chat is a Microsoft‑provided, embeddable web UI for Azure Bot Framework bots. It connects via Direct Line (or Direct Line Speech), renders adaptive cards, supports livestreaming, speech, theming (including a Fluent UI pack), and can be customized through a CDN script or a React component.

Apache SINGA is a distributed deep learning system that enables the training of large-scale neural networks across multiple machines.

A Split-Attention Network variant of ResNet that improves performance for computer vision tasks like object detection and semantic segmentation.

A web-based AI platform interface that allows users to quickly deploy a multi-model chat UI using Cloudflare Workers AI and AI Gateway.

A distributed runtime for reproducible and isolated executable evaluation of AI agents and code-generation models, ensuring safety and provenance.

A collection of PyTorch scripts and tools for speech processing, focusing on neural vocoders and speech spoofing countermeasures.

A framework for running specialized oversight agents alongside a main AI agent to independently review architecture, verify claims, and maintain documentation in real-time.

codex‑shim is a cross‑platform Python/aiohttp shim that makes Codex Desktop think it’s talking to the official OpenAI Responses API, while actually routing each request to any user‑provided LLM (OpenAI, Anthropic, Ollama, OpenCode Go, etc.) or to ChatGPT’s Codex backend. It lets you add BYOK models to Codex’s picker, keep all Codex UI features (function calls, streaming, images), and optionally auto‑route tasks to the cheapest capable model.

A hypothesis-driven red teaming framework for Claude Code that replaces linear pentest pipelines with a state machine to automate complex penetration testing.

A software development kit for Orbbec 3D cameras that enables developers to capture data streams and control hardware across various device series.

A Windows utility that converts images to a 40-color palette and automatically fills 24x24 pixel art canvases in Arknights via computer vision and mouse automation.

A GenAI-powered, codeless test automation platform that enables QA teams to generate and maintain tests for web, mobile, and desktop apps without writing code.

A Python implementation of a Genetic Algorithm to solve the Vehicle Routing Problem with Time Windows (VRPTW), supporting Solomon's benchmark problems and custom data.

An open, SQL-native time-series database for telemetry that uses Parquet storage to enable high-throughput ingestion and long-term retention of full-resolution history.

GeoStats.jl is an extensible Julia framework for geospatial data science and geostatistical modeling, offering tools for geometric processing and data visualization.

A dashboard for GitHub Organization and Enterprise admins to visualize Copilot usage metrics, track adoption, and monitor AI credit billing costs.

Ara is an open-source RISC-V vector processor designed as a coprocessor for the CVA6 core to efficiently handle data-parallel workloads.

A set of Unity samples demonstrating how to use the Passthrough Camera API to access raw camera data and metadata from Quest 3/3S headsets for MR applications.

A web-based tool for browsing and comparing symbol, type, and syscall information of Microsoft Windows binaries across different OS versions to aid security research.

CARS is an open-source multiview stereo framework that uses photogrammetry to produce Digital Surface Models (DSM) from satellite imagery.

A cross-platform C/C++ library for detecting detailed CPU hardware information, such as instruction sets and cache topology, to enable performance optimizations.

A utility library that extends Python's core functionality with features inspired by Ruby and Haskell, providing enhanced data structures and functional programming tools.

An open-source documentation platform that converts Markdown and MDX into professional docs sites with built-in AI chat and OpenAPI API references.

A compact, schema-capable widget renderer for chat UIs that allows AI agents to generate interactive UI components using a strict template language and a large library of pre-built components.

A community-maintained PHP API client that integrates OpenAI's capabilities directly into the Laravel framework.

HeavyDB is a GPU-accelerated, SQL-based columnar database engine that enables millisecond queries on multi-billion row datasets without needing indexes or pre-aggregation.

A set of Jupyter extensions that accelerate Python data analysis by providing an interactive spreadsheet that generates Python code and integrated AI assistance.

A C++ API wrapper for Rviz that simplifies the visualization of shapes, meshes, and transforms for debugging robotics data.