An Android application that acts as an MCP server, allowing AI models to remotely control a device via accessibility services and screenshot capture.

A macOS menu bar app that provides live, bilingual subtitles for meetings and videos by transcribing and translating audio from microphones or specific apps using on-device Apple frameworks.

okf‑skills is a Claude‑Code‑native toolkit that lets AI coding agents create, validate, consume and visualise knowledge bundles written in the Open Knowledge Format (OKF v0.2). It ships as a Claude plugin, as skills.sh‑discoverable agent skills, as a GitHub Action for CI validation, and as a read‑only MCP server for agents without file access. The bundle is just a directory of markdown files with tiny YAML front‑matter; the tool provides deterministic validation, automatic scaffolding, and an interactive HTML graph visualiser. Ideal for teams that want portable, version‑controlled system knowledge that both humans and AI agents can read and update.

A multi-modal, autonomous AI persona framework that creates a proactive voice assistant with vision, long-term memory, and a low-latency response pipeline.

A cross-platform, Rust-based terminal multiplexer engine that provides tmux-compatible commands and typed SDKs for programmatic terminal automation and orchestration.

A comprehensive simulation benchmark for testing embodied AI agents on 1,000 everyday household activities based on real human time-use surveys.

Pinocchio is a high‑performance C++ library (with Python bindings) for rigid‑body dynamics, offering analytical derivatives, contact solvers, closed‑loop handling, and AD support. It powers many robotics and simulation tools and can be installed via Conda or pip.

Drake is an open‑source library for model‑based design, simulation, and formal verification of robotic systems, offering high‑performance dynamics simulation, controller design tools, and safety analysis capabilities.

An official MCP server that integrates Perplexity's real-time web search, reasoning, and research tools into AI assistants and IDEs.

A tool that simplifies local AI model inference by packaging models and their environments into OCI containers, automating GPU acceleration and host configuration.

Nova3D is a code-native 3D generation system that creates assets as executable Blender Python scripts, enabling the production of structured, editable, and animatable 3D models with named parts.

An AI-driven knowledge base system that converts Git repositories and local directories into structured documentation, searchable wikis, and MCP-enabled chat assistants.

An agent-first e-reader for multiple platforms that integrates an AI assistant to remember annotations and provide in-context help while reading.

A self-hosted meme search engine that uses AI vision models to index images by content and text for semantic and keyword retrieval.

A lightweight 2D digital human engine that enables real-time animation and dialogue on mobile browsers and low-power devices without requiring a GPU.

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 Codex skill that analyzes photographs to create sparse editorial abstractions by mapping visual evidence like shapes and spatial rhythm to minimal abstract marks.

A cognitive-driven autonomous security agent for authorized penetration testing that uses causal graph reasoning and a Planner-Executor-Observer architecture to ensure traceable, evidence-backed security research.

A plugin marketplace that teaches AI coding agents like Claude Code and GitHub Copilot how to develop, audit, and optimize Power BI and Microsoft Fabric projects.

A local-first workbench for managing prompts, skills, and AI programming assets, featuring one-click distribution to multiple AI coding tools and built-in version control.

A high-performance A2UI SDK for building native generative UI experiences on iOS, Android, and HarmonyOS, enabling LLMs to render interactive components in real-time.

An autonomous DevOps agent that manages infrastructure and applications 24/7, providing PaaS-like automation with security guardrails to prevent production mishaps.

Qiushi‑Skill is a plug‑in library that adds nine philosophically‑derived reasoning methods (e.g., contradiction analysis, investigation‑first, mass‑line) to AI agents such as Claude Code, Cursor, and Codex. Installed via `npx qiushi-skill` or the Claude Code marketplace, it injects a lightweight kernel that enforces the principle “seek truth from facts” and routes tasks to the appropriate skill. Each skill provides trigger rules, step‑by‑step actions, output templates, hard constraints, and hand‑off specs, plus reference texts and optional sub‑agents for investigation or self‑criticism. The project aims to make agents more evidence‑driven, self‑critical, and strategically focused.

ReachAI is an open‑source platform that adds AI assistants to existing Java enterprise systems (OA, ERP, CRM, etc.). It scans the app, registers annotated business methods as reusable capabilities, lets LLMs generate the integration code (AI‑Coding), and runs user requests through controlled, versioned workflows with full audit trails. The stack includes Spring Boot, AgentScope, LangGraph4j, Vue front‑end, MySQL/Redis/Milvus, and is MIT‑licensed.

A computer vision framework for pretraining, fine-tuning, and distilling SOTA models like DINOv3 and LTDETRv2 for tasks such as object detection and segmentation.

A molecular design tool that uses reinforcement learning and transfer learning to generate optimized small molecules based on user-defined property profiles.

A Python framework for building autonomous and traditional AI agents, featuring secure workspace execution, custom tool integration, and a unified OCR pipeline.

A unified runtime and workbench for AI agents that provides Desktop, Web, and TUI interfaces for managing local development tools and plugins.

A browser extension that provides instant translations of web text, images, and PDFs via tooltips using Google and Bing translation services.

An open tabular foundation model that uses in-context learning to provide high-performance classification and regression without requiring hyperparameter tuning.

tt‑metal (TT‑Metalium) is Tenstorrent’s open‑source stack for writing low‑level kernels (C++/Python) and high‑level neural‑network ops (TT‑NN) that run on Tenstorrent AI chips. It includes model demos, performance reports, and a suite of debugging/profiling tools, aimed at developers who want to run or optimise LLMs, vision models, and other AI workloads on Tenstorrent hardware.

A unified Python SDK that provides a single interface to communicate with multiple LLM providers, allowing developers to switch models without changing their code.

A low-latency, open-source time-series database that ingests millions of events per second and provides high-performance SQL queries over live and historical data.

A single-node launcher for DeepSeek V4 Flash on NVIDIA DGX Spark, enabling high-throughput serving with speculative decoding and context windows up to 384k tokens.

A native local development runtime for Apple Silicon Macs that integrates Docker, Kubernetes, and full Linux virtual machines into a single open-source system.

A proxy server that exposes an Anthropic-compatible API backed by Antigravity's Cloud Code, enabling the use of Claude and Gemini models with the Claude Code CLI.

A proxy that enables MCP clients supporting only local stdio servers to connect to remote MCP servers with full OAuth authorization support.

A cross-platform terminal workspace written in Zig that integrates high-performance terminal emulation with AI agent workflows, SSH management, and an embedded browser.

PyMC is a Python package for Bayesian statistical modeling that uses MCMC and variational inference algorithms to estimate parameters in complex probabilistic models.

A serverless AI paper discovery and reading system that automates personalized paper tracking and AI-powered summarization using GitHub Actions and Pages.

A tool that lets AI agents control a user's existing Chromium-family browser using Playwright, allowing them to leverage active sessions and extensions.

An AI residency runtime for Kelivo companions that enables proactive wake-ups and mobile notifications, giving AI characters a continuous sense of time and time-aware autonomy.

A comprehensive suite of Claude Code skills and agents for AI-powered penetration testing, bug bounty hunting, and AI threat testing.

An AI-native terminal and infrastructure agent that allows engineers to manage cloud resources and servers using natural language instead of complex commands.

WhatDreamsCost‑ComfyUI is a collection of custom ComfyUI nodes that add video‑ and audio‑editing capabilities (timeline editor, load/trim nodes, IC‑LoRA support, audio in‑painting, etc.) for AI‑generated media workflows.

An autoresearch orchestrator that automates code optimization by running parallel AI-driven experiments in a loop to iteratively improve codebase metrics.

A family of parametric statistical 3D human models, starting with GNM Head, for high-fidelity representation of human geometry and appearance.

An application that automates the creation of Anki flashcards from video games by capturing text, audio, and screenshots in real-time.