A Kubernetes-native distributed dataset orchestrator and accelerator that optimizes data access for AI and big data applications by providing dataset abstraction and elastic caching.

An AI constraint solver for Java and Kotlin that optimizes complex planning problems like vehicle routing and employee rostering.

A framework for robot learning from demonstration that provides standardized datasets and offline learning algorithms to make robot manipulation research accessible and reproducible.

Agentic Coding Flywheel Setup (ACFS) is a Bash installer that turns a fresh Ubuntu/Arch VPS into a fully‑configured AI‑coding workstation. It installs a modern shell, language runtimes, cloud CLIs, and three AI coding agents (Claude, Codex, Antigravity) via a single, idempotent `curl | bash` command. The toolchain is defined in a YAML manifest, from which TypeScript code generates the installer scripts. A companion Next.js wizard guides beginners through VPS provisioning and SSH setup. Security is handled with HTTPS‑only downloads and SHA‑256 checksum verification. The project is MIT‑licensed and targets both individual developers and teams needing reproducible agentic environments.

An AI-powered notebook that integrates local files and web resources into a single workspace for simultaneous research and synthesis.

CCManager is a terminal UI that lets developers run, monitor, and organise multiple AI coding‑assistant sessions (Claude, Gemini, Codex, etc.) across one or many Git worktrees. It creates and deletes worktrees, can copy ignored files and Claude conversation data, persists session state across restarts, offers visual status indicators, configurable keyboard shortcuts, automation hooks, devcontainer support, and a multi‑project mode. Install with `npm i -g ccmanager` and launch via `ccmanager`.

A centralized library of shared workflows and helper scripts for AI coding agents to ensure consistent behavior across multiple repositories.

A cross-platform Go wrapper for the onnxruntime library, allowing Go developers to load and execute ONNX-format neural networks with hardware acceleration support.

An open-source machine learning framework for building contextual AI assistants and agents that automate text and voice-based conversations.

A Python package for uplift modeling and causal inference that estimates the causal impact of interventions on individual users to optimize targeting and personalization.

A flexible RL framework for training reasoning LLM agents using multi-turn reinforcement learning and the StarPO algorithm to prevent reasoning collapse.

An open-source operating system for smart glasses that allows developers to build a single app that runs across multiple hardware brands via a smartphone runtime.

Apify Agent Skills is a set of plug‑in style “skills” that let LLM agents (Claude, Cursor, Gemini, etc.) invoke Apify’s web‑scraping/automation platform. Five core skills cover universal scraping via 130+ curated Actors, creating new Actors, turning existing code into Actors, auto‑generating output schemas, and building Apify integrations. Install with a single `npx skills add …` command, then prompt the agent to scrape sites, generate leads, do market research, etc. Requires an Apify account, the Apify CLI, and Node 20+. Licensed Apache‑2.0.

KaTrain is an AI-powered tool for analyzing Go games and playing against AI with real-time feedback and calibrated skill levels based on the KataGo engine.

Trackio is a free, lightweight experiment‑tracking library (compatible with wandb) that stores logs locally in SQLite, offers a fast non‑blocking API, a Gradio‑style dashboard, CLI/SQL query tools, alerts, and optional free hosting on Hugging Face Spaces or self‑hosting.

An open-weights model and inference engine for real-time music generation, optimized for streaming audio on Apple Silicon.

An official Model Context Protocol (MCP) server that enables LLMs to use Qdrant as a semantic memory layer for storing and retrieving information.

A learning-based one-stage planner for autonomous drones that integrates perception and trajectory optimization into a single network for agile navigation in dense obstacles.

A tooling and infrastructure framework for protein design, providing a unified interface for generative models like RFdiffusion3 and structure prediction models like RosettaFold3.

An agentic AI system that integrates into AI runtimes to provide a structured workflow for physics research, from problem scoping to manuscript writing.

A Next.js application that integrates E2B's desktop sandbox with OpenAI's Computer Use API to create an AI agent capable of operating a virtual computer via natural language.

genai is a Rust crate that provides a single, ergonomic async API for chatting with over 200 LLM models from 26+ providers (OpenAI, Anthropic, Gemini, Ollama, Bedrock, etc.). It selects the correct native protocol automatically, supports custom OpenAI‑compatible endpoints, streaming, tool calling, image analysis, and offers extensive configuration via ChatOptions. The library is actively maintained (v0.6 released, v0.7 beta upcoming) and includes many examples and docs.

A toolkit for building robust web integrations that provides coding agents with a live browser and CLI to automate scraping, API reverse-engineering, and script maintenance.

An open-source AI agent for Unity that automates C# coding, asset modification, and editor UI creation with built-in hot reload and semantic analysis.

A self-hosted AI workspace that transforms chatbots into digital teams by providing a governed runtime for humans, AI actors, and remote agents to collaborate in shared conversations.

An open-source AI trading agent that automates Wyckoff volume-price analysis and market screening for A-shares, HK, and US stocks using natural language.

ICM (Infinite Context Memory) is a Rust‑based, zero‑dependency binary that provides a shared, searchable SQLite memory store for AI agents. It supports episodic memories with importance‑based decay, permanent knowledge‑graph memoirs, feedback recording, and verbatim session transcripts. Integrated via MCP hooks or a CLI, it works with many popular assistants (Claude, Gemini, Codex, Copilot, etc.) and offers optional ONNX‑Runtime semantic search. Install via Homebrew, a one‑liner script, or Cargo; configure globally or per‑project, then store/recall context across tools without re‑explaining. Experimental (pre‑1.0) but usable today.

A deterministic MoE training megakernel for NVIDIA Blackwell NVL72s that fuses computation and communication to eliminate CPU-GPU synchronization and accelerate training.

An open-source AI super app that integrates coding, email, research, and document creation into a single workspace with support for multiple AI providers.

A deployment framework for running a persistent, 24/7 Claude Code agent with a real browser on your own VPS, controllable via Telegram.

An open-source parallel coding agent harness that provides a single web portal to run and control multiple AI coding agents simultaneously.

A Swift and Metal runtime that enables large MoE models like Qwen to run on Apple devices by streaming experts from storage to RAM on demand.

A minimal chatbot template built with Next.js and the Vercel AI SDK, featuring streaming chat, tool calling, and a polished shadcn/ui interface.

xDiT is an open‑source inference engine for diffusion‑transformer models (e.g., Flux, Stable Diffusion 3, CogVideoX). It provides multiple parallelism methods—Unified Sequence Parallel (USP), PipeFusion, data‑parallel, and CFG‑parallel—that can be combined to scale across many GPUs or machines. Single‑GPU speed‑ups come from kernel optimisations, torch.compile, and cache tricks. The project ships a CLI model runner, example scripts, Docker images, and a ComfyUI plugin (TACO‑DiT) for easy integration. It supports a wide range of DiT models and many attention back‑ends (FlashAttention, cuDNN, NVIDIA TransformerEngine, AMD AITER, etc.).

A speaker diarization pipeline that combines OpenAI Whisper for transcription with NVIDIA NeMo for speaker identification to determine who spoke which words in an audio file.

An open-source AI coding agent that lets users edit frontend source code directly from the browser by clicking elements and describing changes in plain English.

An Unreal Engine 5 plugin that integrates the MuJoCo physics engine to provide high-fidelity robotics simulation with photorealistic rendering.

MIRA is a real-time world model of Rocket League that uses a 5B parameter latent diffusion model to simulate 2v2 matches based on player actions.

An open-source durable execution platform for microservices and AI agents that turns complex workflow graphs into persisted, inspectable, and recoverable executions.

An AI agent workforce platform that allows a single operator to deploy, monitor, and coordinate hundreds of isolated AI agents across a fleet of self-hosted runners.

An MCP server that provides isolated, containerized environments for coding agents, allowing multiple agents to work in parallel safely and independently.

A cloud cost intelligence tool that provides real-time cost estimates and FinOps policy enforcement for infrastructure-as-code before deployment.

A curated collection of agentic skills based on an open standard that provides AI coding assistants with expert-level, production-ready knowledge of Azure services.

A desktop application that uses computer vision to let users perform mouse actions via their keyboard, reducing the need for a physical mouse.

OpenClaw.NET is a .NET‑native AI‑agent runtime and gateway. It provides a NativeAOT‑compatible executable, a web‑based chat/admin UI, OpenAI‑compatible APIs, 80+ built‑in tool adapters, multi‑channel support (Slack, Telegram, etc.), and first‑class integration with cloud and local LLM providers (OpenAI, Claude, Gemini, DeepSeek, Ollama, embedded Gemma‑4). Optional governance features let you audit and approve high‑risk tool actions. The project is aimed at developers who want a self‑hosted, observable AI‑agent platform that runs on Windows, macOS, or Linux.

An open-source agentic telemetry system that ingests OpenTelemetry data and groups noisy signals into incidents for easier production debugging.

An inference engine for Hugging Face-compatible language and multimodal models that provides continuous batching, paged KV-cache management, and distributed serving.

A structural code navigation tool and MCP server that helps AI agents read codebases more efficiently by providing outlines, definition-first search, and call-chain tracing.