A full-stack AI agent platform for building, orchestrating, and publishing AI applications with visual workflows, RAG integration, and OpenAPI delivery.

A durable runtime for AI agents that prevents execution loss during process crashes and supports long-running, event-driven workflows with human-in-the-loop approvals.

A fast and generic Julia implementation of the AlphaZero algorithm that enables training AI agents for combinatorial games using self-play on standard desktop hardware.

A Claude Code plugin that provides persistent memory across sessions by compressing conversations into curated logs and automatically restoring context.

A collection of implementation samples and end-to-end applications for .NET developers to integrate machine learning into their apps using the ML.NET framework.

A model-agnostic inference-time control system that enhances AI agent reasoning and long-horizon task performance through selective workspace management and state externalization.

A management platform and optimized user interface for Dify applications, providing a professional front-end for Chatflow and Workflow AI agents.

A Python library for embedding and detecting imperceptible watermarks in audio files, utilizing neural network-based approaches to ensure robustness against manipulation.

An MCP server that enables AI agents to perform binary analysis and reverse engineering using the radare2 framework.

ROCm / legacy‑rocm‑build is the (now‑deprecated) repository that assembles AMD’s open‑source GPU compute stack—drivers, HIP runtime, math libraries, profiling tools, and more—so developers can run AI/ML workloads on AMD GPUs. It points users to install guides and to the newer TheRock monorepo.

A lightweight Android VPN proxy tool based on tun2socks that supports HTTP and SOCKS5 protocols, featuring per-app proxying and remote control via the Model Context Protocol (MCP).

An AI workflow orchestration system for web coding that replaces single-AI execution with a collaborative team of AI agents for planning, reviewing, and implementing code.

An open-source platform that turns WordPress into a unified business intelligence hub, integrating omni-channel data into a Knowledge Graph for AI-driven CRM and automation.

A lightweight C++20 interface for GPU compute via WebGPU that simplifies shader dispatch and data movement across native and browser environments.

A suite of model and data exploration tools that enable developers to identify errors, assess fairness, and interpret AI model predictions for more responsible deployment.

FuxiCTR is an open‑source Python library (PyPI package) for click‑through‑rate prediction. It bundles more than 40 modern CTR models—both classic factorization‑machine style and recent sequence‑aware architectures—implemented for PyTorch and TensorFlow. The library emphasizes configurability, automatic hyper‑parameter tuning, reproducible benchmarks, and easy extensibility, making it useful for researchers and engineers working on advertising, recommendation, or sponsored‑search systems.

A flexible and extensible gait analysis framework for human identification and health screening, supporting multiple modalities like silhouettes, skeletons, and LiDAR point clouds.

A local-first document anonymization workbench that uses semantic NER and visual grounding to redact sensitive text and visual elements from unstructured files.

A set of APIs that allow developers to easily move TensorFlow and Keras model training from local environments to distributed training and tuning on Google Cloud Platform.

Arkloop is an open‑source, local‑first AI agent platform. It bundles a Go backend, SQLite storage, and an Electron‑based desktop app (with a React web UI) that supports multi‑model routing, tool calling, persistent or semantic memory, and integration with Telegram, Discord, QQ, Feishu, and WeChat. Installable via GitHub releases, Homebrew, or AUR, it runs entirely on the user’s machine, avoiding any cloud infrastructure.

A research‑level router preset for DeepSeek Harness that automatically classifies the first user request and injects the appropriate persona and tool set (spec/react/weak) for the DeepSeek V4 model. It runs as a zero‑dependency Cord‑is plugin, integrates with the dsh‑super‑injector for hot‑reloading, and provides CLI diagnostics. Currently in development (v1.19.1, Aug 2026).

A local, database-first code intelligence and SAST platform that turns codebases into queryable facts to reduce token costs for AI agents and security teams.

A collection of structured skills and plugins that enable AI agents to use Oxylabs' proxy and web scraping services for automated data extraction.

A fast and numerically robust constrained nonlinear optimal control problem solver designed for robot trajectory optimization and control.

A Next.js‑based web UI for Azure Cognitive Services Text‑to‑Speech, offering voice selection, speed/intonation controls, SSML editing, audio download, and one‑click Vercel/Docker deployment.

An open-source platform for biology lab robots that provides an API and tools to automate pipetting and experimental protocols.

An automation bot for Clash Royale that uses an advanced state generator and object detection for educational and research purposes.

A unified interface for calling frontier LLMs that simplifies prompt management, structured output parsing, and the creation of tool-calling agents.

A collection of custom skills, sub-agents, and configuration templates to extend Claude Code with capabilities like deep research, image generation, and GitHub automation.

A simple probabilistic programming language that allows users to define models as programs and manipulate their computation for flexible training and inference.

A local-first workspace client for OpenClaw that replaces chat-based agent interfaces with a structured, task-oriented environment for managing parallel AI agent sessions and artifacts.

A decentralized, privacy-preserving machine learning framework that enables collaborative model training across distributed data sources using blockchain for coordination without sharing raw data.

An AI agent workspace for developers to run multiple parallel AI-powered workflows and automate development tasks from a single environment.

A high-performance Swift-based ML runtime for macOS that enables local inference of LLMs, VLMs, and audio models using Apple's MLX framework.

A RAG system specialized for Cyber Threat Intelligence that combines vector search and knowledge graphs to enable multi-hop analysis of attack organizations and malware.

Ollama4j is a Java library that wraps the Ollama local LLM server, providing text generation, chat, tool calling, embeddings, image inputs, model management, and Prometheus metrics. It is distributed via Maven Central/Gradle and integrates with any Java project.

biniou is an open‑source, self‑hosted web UI that bundles dozens of generative‑AI modules (text, image, audio, video, 3‑D, translation, speech‑to‑text, etc.). It runs on Linux, Windows and experimental macOS, works on modest hardware (8 GB RAM, CPU‑only) and can optionally use CUDA/ROCm. One‑click installers, Docker images and a Gradio interface let users download models from Hugging Face, generate content, and chain modules together, all offline.

A high-performance codebase for experimenting with large diffusion models, implementing advanced flow-matching and distillation techniques for efficient few-step image generation.

A library for the accessible training and fine-tuning of diffusion models, focusing on memory-efficient text-to-video and text-to-image generation.

A compiler that converts classical ML models and robot URDF descriptions into optimized, standalone C99 binaries for microsecond-latency inference on edge and embedded hardware.

A prompt engineering platform that provides a unified proxy for multiple LLM providers and local models, featuring a playground UI and monitoring tools.

memory‑lancedb‑pro is a production‑grade OpenClaw plugin that gives AI agents persistent, searchable memory. It auto‑captures conversation snippets, classifies them with an LLM, stores them in a LanceDB vector+BM25 index, and automatically injects the most relevant memories into prompts. Features include hybrid retrieval, cross‑encoder reranking, Weibull‑based forgetting, per‑agent/user/project scopes, and support for any OpenAI‑compatible embedding provider. Install via a one‑click script or the OpenClaw CLI, configure with a short JSON block, and manage the store with a built‑in CLI.

An open-source context retrieval layer for AI agents and RAG systems that syncs data from 50+ integrations into a unified, LLM-friendly search interface.

A programmable, modular AI agent runtime platform that enables deep customization of agent logic and seamless integration into IDEs, browsers, and P2P networks.

A unified, tileable workspace that integrates AI agents, code editors, web browsing, and document editing to eliminate context switching for complex workflows.

A self-learning browser infrastructure for AI agents that remembers website navigation to reduce token costs and increase automation reliability.

MIRA is a continuous digital entity that uses first-person memory, autonomous context management, and behavioral adaptation to maintain a persistent, long-term relationship with the user.

A music discovery tool for Lidarr users that blends Last.fm, ListenBrainz, and AI to suggest new artists and sync them directly to their library.