Skip to main content

OSAgent

OSAgent is a demo application designed to assist users through voice commands on their computers. It supports Ubuntu, Windows, and macOS systems, can run in the background, and integrates voice input. The application leverages advanced models based on the OSWorld benchmark for quick integration and efficient functionality.

Features

  • Cross-Platform: Works on Ubuntu, Windows, and macOS.
  • Background Operation: Continuously runs without disrupting other tasks.
  • Voice Input: Accepts and processes voice commands.
  • Advanced Model Integration: Utilizes OSWorld benchmark models for enhanced performance.

Installation and Running

To get started with OSAgent, follow these steps:

  1. Set your OpenAI API key:

    export OPENAI_API_KEY="YOUR_KEY"
    
  2. Install the OSAgent package:

    pip install osagent
    
  3. Run the main agent module:

    python -m osagent.agents.main
    

Note: On macOS, you may receive popups requesting network, screenshot, or accessibility permissions. Please grant these permissions for OSAgent to function correctly.

Usage

In default the program run in voice command feature, please press and hold the combination of shift + ctrl + x, then speak your instruction and release the keys to process the command.

For more detailed information, please refer to our documentation.

Metadata

Release files for osagent 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for osagent 0.1.1
File Size Uploaded Provenance Actions
osagent-0.1.1.tar.gz 106.4 kB Without provenance Details for osagent-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for osagent 0.1.1
File Interpreter ABI Platform Actions
osagent-0.1.1-py3-none-any.whl Python 3 none any Details for osagent-0.1.1-py3-none-any.whl

Total release size: 229.0 kB

Release files / osagent-0.1.1.tar.gz

Download URL osagent-0.1.1.tar.gz
Size 106.4 kB
Tags Source
SHA-256 checksum
How to use checksums
54ab4c2f869bc405ba95f7c5429fa4c38e4c41e25d011e4c625bb4251e3e4095
BLAKE2b-256 checksum
How to use checksums
466358f8d0a1c5707a35ae8c89c9fe03928323381e7d57b11ff4934ffffa2725
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via pdm/2.17.1 CPython/3.12.4 Darwin/23.5.0

Release files / osagent-0.1.1-py3-none-any.whl

Download URL osagent-0.1.1-py3-none-any.whl
Size 122.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
95c59cf41a072035bd32833c5dc802ae6c0d3556fcf0d6458a20efd0c51a134a
BLAKE2b-256 checksum
How to use checksums
f656d637ce9ea8dc9db08f81f8463548ee1b34bf973c06a43375f44bae417be1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via pdm/2.17.1 CPython/3.12.4 Darwin/23.5.0

Security for osagent 0.1.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page