Pi Computer Use
FreeNot checkedPi extension for desktop automation via cua-driver-rs with computer_use_ prefixed tools
About
Pi extension for desktop automation via cua-driver-rs with computer_use_ prefixed tools
README

Shared TypeScript packages for Pi runtime applications.
This repository contains the open-source runtime contracts, adapters, and orchestration helpers that are consumed by Pi Agent and related applications. The packages are intentionally small and composable: host applications provide HTTP routing, authentication, model runtime setup, deployment configuration, and product-specific UI.
Packages
| Category | Package | Purpose |
|---|---|---|
| Core | @amaster.ai/pi-shared |
Shared runtime types and contracts: settings loader, session/event/artifact types, turn and subagent types. |
| Core | @amaster.ai/pi-storage |
JSON-file and MySQL/Prisma persistence adapters for sessions, transcripts, events, memory, artifacts, subagents, and scheduled tasks. |
| Extension | @amaster.ai/pi-attachments |
Attachment normalization, local/remote upload handling, document parsing, and model-readable attachment prompts. |
| Extension | @amaster.ai/pi-telemetry |
Runtime telemetry with Langfuse and OpenTelemetry exporters. |
| Extension | @amaster.ai/pi-task-scheduler |
Cron-based scheduled task management with LLM-callable tools. |
| Extension | @amaster.ai/pi-browser-use |
Browser automation wrapping chrome-devtools-mcp with browser_-prefixed tools. |
| Extension | @amaster.ai/pi-web-access |
Web search and URL content extraction across configurable providers. |
| Extension | @amaster.ai/pi-computer-use |
Computer-use extension for CUA computer-server with desktop automation tools. |
| Extension | @amaster.ai/pi-channels |
Native messaging channels: Feishu, WeCom, and webhooks. |
| Extension | @amaster.ai/pi-memory |
Persistent curated memory (MEMORY.md + USER.md) injected into the system prompt as a refreshed prompt snapshot. |
| Extension | @amaster.ai/pi-security |
Resource-aware security policy engine and tool authorization. |
| Extension | @amaster.ai/pi-teamwork |
Team collaboration and issue management via Multica. |
| Extension | @amaster.ai/pi-image-gen |
Image generation via OpenAI gpt-image, Google Nano Banana, Alibaba Qwen-Image, OpenRouter, and custom providers. |
| Extension | @amaster.ai/pi-lark |
Lark/Feishu workspace integration through lark-cli, including calendar, docs, drive, sheets, Base, tasks, mail, wiki, and IM skills. |
| Extension | @amaster.ai/pi-wecom |
WeCom workspace integration through wecom-cli, including contacts, messages, meetings, schedules, todos, docs, and smart sheets. |
| Extension | @amaster.ai/pi-dingtalk |
DingTalk workspace integration through dws CLI, including calendar, docs, chat, todos, sheets, AI tables, approvals, mail, wiki, and meeting minutes. |
Core packages provide types and persistence used by every host application.
Extension packages each register Pi runtime extensions via their ./extension
subpath entry point and are loaded on demand.
Every package is ESM-only and published under the @amaster.ai npm scope.
Extension Previews
@amaster.ai/pi-attachments![]() |
@amaster.ai/pi-telemetry![]() |
@amaster.ai/pi-task-scheduler![]() |
@amaster.ai/pi-browser-use![]() |
@amaster.ai/pi-computer-use![]() |
@amaster.ai/pi-channels![]() |
@amaster.ai/pi-memory![]() |
@amaster.ai/pi-security![]() |
@amaster.ai/pi-teamwork![]() |
@amaster.ai/pi-image-gen![]() |
@amaster.ai/pi-web-access![]() |
@amaster.ai/pi-memory-mem0![]() |
@amaster.ai/pi-lark![]() |
@amaster.ai/pi-wecom![]() |
@amaster.ai/pi-dingtalk![]() |
Requirements
- Node.js
>=24 - pnpm
10.18.3
Use Corepack when possible:
corepack enable
corepack install -g [email protected]
Development
Install dependencies:
pnpm install
Run the full local check:
pnpm run pr-check
Common commands:
pnpm build
pnpm typecheck
pnpm test
pnpm --filter @amaster.ai/pi-storage prisma:generate
@amaster.ai/pi-storage includes a Prisma schema at
packages/storage/prisma/schema.prisma. The root build and typecheck
scripts generate the Prisma client before compiling project references.
Consuming Packages
Install only the packages your application needs:
pnpm add @amaster.ai/pi-shared @amaster.ai/pi-storage
Most packages expose a root entry point. Some packages also expose focused subpath entry points:
import { createRuntimeStorage } from "@amaster.ai/pi-storage";
import { JsonRuntimeStorage } from "@amaster.ai/pi-storage/json";
import { loadPiSettings } from "@amaster.ai/pi-shared/settings";
import { createLangfuseExporter } from "@amaster.ai/pi-telemetry/langfuse";
import { createOtelExporter } from "@amaster.ai/pi-telemetry/otel";
import memoryExtension from "@amaster.ai/pi-memory/extension";
Extension packages register themselves through their ./extension subpath
entry point. Host applications import these and pass them to the Pi runtime
during setup.
See each package README for package-specific examples and public API notes.
License
Apache-2.0
Install Pi Computer Use in Claude Desktop, Claude Code & Cursor
unyly install pi-computer-useInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add pi-computer-use -- npx -y @amaster.ai/pi-computer-useFAQ
Is Pi Computer Use MCP free?
Yes, Pi Computer Use MCP is free — one-click install via Unyly at no cost.
Does Pi Computer Use need an API key?
No, Pi Computer Use runs without API keys or environment variables.
Is Pi Computer Use hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Pi Computer Use in Claude Desktop, Claude Code or Cursor?
Open Pi Computer Use on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
GitHub
PRs, issues, code search, CI status
by GitHubFilesystem
Secure file operations with configurable access controls.
Memory
Knowledge graph-based persistent memory system.
Template MCP Server
A CLI tool to create a new Model Context Protocol server project with TypeScript support, dual transport options, and an extensible structure
by mcpdotdirectCompare Pi Computer Use with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All development MCPs















