Enables structured learning with a verified loop: define goals as observable claims, learn through teach-lab-test-gate per claim, and get independently graded by an adversarial examiner to ensure genuine progress.
Enables AI agents to autonomously operate web browsers through the Model Context Protocol, including navigating pages, clicking, typing, filling forms, and extracting structured data.
An open-source MCP server that lets any coding agent operate your computer like a person does—reading the UI through accessibility trees, clicking and typing in the background, showing an agent pointer, zooming into regions, and driving your signed-in Chrome on macOS, Windows, and Linux.
Enables an agent to see and operate a GNOME Wayland desktop like a human, including screenshots, mouse/keyboard control, accessibility tree access, OCR, clipboard, and audio listening.
MCP server for The Commons (jointhecommons.space), a persistent, noncommercial space where AI voices from different models post and reply to each other with persistent identities. 48 tools; reading needs no token, writing uses a facilitator-issued token.
Enables Claude to see and control a real Android phone via MCP, reading the accessibility tree to tap, type, navigate, launch apps, and diagnose connectivity over ADB or cellular.
Exposes Anthropic's computer-use action surface (screenshot, click, move, keyboard, clipboard, batch) against a persistent desktop display via MCP stdio protocol. Enables AI agents to control a virtual desktop environment through natural language instructions.
Enables agent-native desktop control by driving mouse, keyboard, and interface elements through accessibility-first semantic operations, with fallback to screen coordinates when accessibility cannot reach a target.
Enables MCP-capable agents to run TypeSafe's Jev judgment model as typed yes/no, choice, and score tools, with calibrated probabilities, confidence thresholds, escalation for uncertain or non-judgment tasks, and an optional action gate that fails open.
Enables an agent to run a single planning request past seats drawn from multiple AI labs, which ask clarifying questions, propose independently, debate each other's anonymised proposals, and panel-review a draft against yes/no acceptance criteria until it passes or hits the round cap. Each run writes a local folder with the deliverable, the full debate board, a handoff document, per-lab scores, and real token/cost accounting, all driven with your own API keys.
Connects AI agents to The Agents Hub, visualizing them as pixel characters on a tile-based property with tools for state, assets, inboxes, and multi-agent orchestration.
Restores OpenAI Codex Computer Use on macOS 13 by building a clean-room MCP backend that adapts to the bundled sky interface, enabling screen interaction and app control without modifying system libraries.
Enables Claude Code to control a Windows desktop via screenshots, mouse, keyboard, and window/display enumeration, reusing the native binding from the Claude desktop app.
A framework-agnostic computer-use MCP server that exposes core desktop operations (screen capture, mouse, keyboard, and file access) as standard MCP tools, enabling any MCP-compatible agent to drive a computer.
Enables Windows desktop automation via MCP, allowing AI agents to control mouse, keyboard, and screen capture with the same interface as Anthropic's computer-use tool.