Skip to main content

A personal assistant that operates your computer. Just like you.

Project description

Operator

A personal assistant that operates your computer. Just like you.

Operator is an AI agent you message from anywhere — Telegram, Discord, or Slack — and it works on your computer. It reads files, browses the web, runs commands, clicks through apps, and remembers who you are. It runs locally, connects to any LLM, and gets smarter over time.

Inspired by nanobot by the Data Intelligence Lab at the University of Hong Kong.

Currently supported on Windows and macOS.


Install

uvx operator-use onboard

Or with uv:

uv tool install operator-use
operator onboard

Follow the setup wizard to configure your LLM and connect a channel (Telegram, Discord, or Slack).

Then start your assistant:

operator run

What it can do

  • Control your desktop — click, type, scroll, take screenshots, open apps
  • Run terminal commands and manage files
  • Browse and search the web
  • Respond through Telegram, Discord, Slack, or MQTT
  • Speak and listen via voice (STT / TTS)
  • Remember context across conversations
  • Schedule and run tasks on a schedule

Supported LLMs

OpenAI · Anthropic · Google · Mistral · Groq · Ollama · Azure · Cerebras · DeepSeek · LiteLLM · and more


License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

operator_use-0.2.7.tar.gz (563.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

operator_use-0.2.7-py3-none-any.whl (843.9 kB view details)

Uploaded Python 3

File details

Details for the file operator_use-0.2.7.tar.gz.

File metadata

  • Download URL: operator_use-0.2.7.tar.gz
  • Upload date:
  • Size: 563.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.0

File hashes

Hashes for operator_use-0.2.7.tar.gz
Algorithm Hash digest
SHA256 aaa1556798a32465f49999b078cc8079169e0ae47ef5664a42619c942667c891
MD5 56e1d4b45dfc3758f2bb769f1cbef20a
BLAKE2b-256 d54b9c97c6c35250f717a00dda69d340e25babe5c76750d610b5e11cc902218e

See more details on using hashes here.

File details

Details for the file operator_use-0.2.7-py3-none-any.whl.

File metadata

  • Download URL: operator_use-0.2.7-py3-none-any.whl
  • Upload date:
  • Size: 843.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.0

File hashes

Hashes for operator_use-0.2.7-py3-none-any.whl
Algorithm Hash digest
SHA256 03b5912e76837e603485cd6e7d5777a58ae4173807c718427bb92ae17873b66a
MD5 42651f292e4f1e0ebc353a97c6bfcef1
BLAKE2b-256 65df5f0ee955be7fce07473dbc470edfe39e0210d6d7182f786274b913adde52

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page