Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

openworker

openworker: A desktop app and harness SDK for building and running AI coworkers that work across everyday tools.

What problem it solves

People need a way to delegate research, writing, code review, recurring tasks and work across connected tools to AI agents without giving up control over actions and data. They also need a foundation for embedding agent loops, tool calls, approvals, streaming and durable sessions into their own applications.

Key features

  • Everyday AI coworker — The desktop app supports research, writing, code review and task execution across connected tools. It can turn notes, files and research into briefs, documents, spreadsheets and reports.

    Source: README

  • Governed agent actions — Agents operate with approval gates, recorded tool activity and optional sandboxing. Dangerous and irreversible operations remain human-only, while other permissions can graduate into explicit, visible and revocable rules.

    Source: README

  • Choice of models — Users can connect supported cloud providers or use local models through Ollama, LM Studio, llama.cpp or vLLM, and switch models in the application settings.

    Source: README

  • Harness SDK for agentic applications — The SDK lets developers add agent capabilities to desktop, web or local applications. It provides the agent loop, tool calls, approvals, streaming and durable sessions, with TypeScript and Rust integration options.

    Source: README

  • Connected tools and recurring work — The app can work with GitHub, Slack, email, calendars and MCP integrations. It can delegate work from Slack and schedule repeatable tasks whose transcripts can be reviewed.

    Source: README

Quick start

Copied verbatim from the project's README.

npm install @openworkerai/harness-sdk

Who it may suit

This may suit teams and individuals who want to delegate everyday knowledge work to governed AI agents on their own machines. It may also suit developers building desktop, web or local utilities that need an embedded agent runtime.

Topics to discuss

  • Which integrations and specialist coworker workflows should be prioritized next?

  • How should approval rules and audit records evolve to balance useful autonomy with explicit control?

  • What examples would help developers build reliable desktop and web applications with the Harness SDK?


Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/andrewyng/openworker#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/andrewyng/openworker

Comments

…