# Abu-Cowork: Run an AI Desktop Assistant with Electron This repository profile is provided by osrepos.com, an open source repository discovery platform. Source: osrepos.com Repository profile: https://osrepos.com/repo/pm-shawn-abu-cowork Generated for open source discovery and AI-assisted research. Abu is an Electron desktop assistant inspired by Claude Code’s Cowork mode, built to plan and carry out file, command, and document tasks on your computer. It runs on macOS and Windows, using Anthropic- or OpenAI-compatible model APIs, including local Ollama models. GitHub: https://github.com/PM-Shawn/Abu-Cowork OSRepos URL: https://osrepos.com/repo/pm-shawn-abu-cowork ## Summary Abu is an Electron desktop assistant inspired by Claude Code’s Cowork mode, built to plan and carry out file, command, and document tasks on your computer. It runs on macOS and Windows, using Anthropic- or OpenAI-compatible model APIs, including local Ollama models. ## Topics - typescript - ai-agents - desktop-app - automation - office-automation - desktop-assistant - computer-use ## Repository Information Last analyzed by OSRepos: Wed Nov 04 2026 03:08:29 GMT+0000 (Western European Standard Time) Detail views: 1 GitHub clicks: 0 ## Safety Notice OSRepos shares public repositories for knowledge and discovery only. Review source code, dependencies, licenses, and security implications before running or installing anything. ## Content ## Overview Abu is an Electron desktop office assistant inspired by Claude Code’s Cowork mode. It uses a dual-protocol adapter for Anthropic and OpenAI-compatible APIs to plan and perform work on your computer, such as reading and editing files, running commands, and creating reports. It is designed for macOS and Windows, with local models available through Ollama as well as cloud providers. Rather than only answering questions, Abu can carry out multi-step tasks through tools, scheduled workflows, browser automation, and integrations. Its local-first approach keeps data and API keys on the user's machine, while permission controls ask for approval for consequential operations. This makes it most relevant to people who want an AI assistant to act on desktop work, not just draft responses in a chat window. ## Key Features - Agent planning and tool use for file operations, commands, and document creation, with a plan-and-confirm mode for high-risk steps. - Connects to Anthropic and OpenAI-compatible services, supports Ollama discovery, and allows custom endpoints. - Provides built-in skills for office documents, design, browser automation, and other workflows, with support for custom and self-evolving skills. - Runs up to five background agents in parallel and can group conversations, skills, and connectors into projects. - Supports scheduled tasks and event triggers, including cron, file changes, HTTP webhooks, and IM messages. - Offers MCP connectors, browser automation, and computer control, with permission settings and safety checks. - Integrates with Lark, DingTalk, WeCom, Slack, and D-Chat for team chat workflows. ## Use Cases - An office worker can ask Abu to extract PDF tables into a spreadsheet or draft a presentation, rather than manually moving content between apps. - A developer or analyst can delegate local file review, command execution, and report generation to an agent, using approval controls for sensitive steps. - A small team can use an IM integration to invoke tasks from a supported chat platform and set workspace or user restrictions. - Someone with recurring research or reporting work can schedule a workflow and have Abu produce a digest or other deliverable. ## Our Take Abu is an actively developed desktop agent with a broad set of automation features, but its concentrated development and the risks of granting an agent desktop access call for careful evaluation. **Good fit if:** - You want an Electron app on macOS or Windows that can act on local files and execute multi-step tasks, rather than only provide chat responses. - You already use, or are willing to configure, an Anthropic or OpenAI-compatible API, or Ollama for local models. - You need scheduled work, MCP integrations, or supported IM channels, and can configure permissions to match the task. **Look elsewhere if:** - Your deployment requires a strong OS-enforced shell sandbox on Windows. The project documents that Windows shell containment is advisory, not a security boundary. - You need a project whose development is not heavily dependent on one contributor. Recent activity is strong, but nearly all measured contribution comes from one person. - You need a Linux desktop build. The documented supported platforms are macOS and Windows. ## Project Health | Signal | Value | |---|---| | Status | **Active**: regular commits and releases | | Last commit | 2026-11-01 (2 days ago) | | Commits, last 90 days | 100+ | | Releases, last 12 months | 100+ (latest v0.61.0, 2026-11-01) | | Contributors | 4 (top contributor: 99% of commits) | | Issues closed, last 90 days | 0+ | | Pull requests merged, last 90 days | 87 (typically merged in 0 days) | | Project age | 8 months | Checked on 2026-11-04 with the GitHub API. ## Project Facts - Language: TypeScript - License: Apache-2.0 - Stars: 419 - Forks: 99 - Topics: agent-framework, agentic-ai, ai-agent, ai-assistant, ai-office-assistant, automation, claude-cowork, deepseek - Website: https://abuwork.com - Archived: no ## What You Need Detected in the repository: - Node.js (from package.json) - A test suite and automated checks on GitHub Actions ## Getting Started Download a macOS or Windows installer from the [GitHub Releases](https://github.com/PM-Shawn/Abu-Cowork/releases) page, then configure an AI service in Settings. For a local model, install [Ollama](https://ollama.com); Abu can discover local models. See the [README](https://github.com/PM-Shawn/Abu-Cowork) and [Installation Guide](https://github.com/PM-Shawn/Abu-Cowork/blob/main/docs/Installation-Guide.md) for details. ## License in Plain Words **Apache-2.0** (permissive). - Commercial use: yes - Modify and redistribute: yes - You must keep: the license, the NOTICE file and a note of your changes - Share your changes: no - Includes an explicit patent grant from the contributors A summary, not legal advice: the LICENSE file is what applies. ## Alternatives - [UI-TARS-desktop](https://osrepos.com/repo/bytedance-ui-tars-desktop): UI-TARS focuses on operating apps through visual computer control, while Abu plans and carries out broader file, command, and document tasks. - [craft-agents-oss](https://osrepos.com/repo/lukilabs-craft-agents-oss): Craft Agents centers on organizing customizable agent sessions and connected services, while Abu focuses on completing desktop file, command, and document tasks. - [Kun](https://osrepos.com/repo/kunagent-kun): Kun provides a shared desktop and terminal workspace for varied agent work, while Abu is focused on planning and carrying out tasks on the computer. - [goose](https://osrepos.com/repo/aaif-goose-goose): Goose is a general-purpose agent offered as a desktop app, CLI, and API, while Abu is an Electron assistant focused on desktop task execution. | Project | Language | License | Stars | Status | |---|---|---|---|---| | **Abu-Cowork** | TypeScript | Apache-2.0 | 419 | Active | | [UI-TARS-desktop](https://osrepos.com/repo/bytedance-ui-tars-desktop) | TypeScript | Apache-2.0 | 39.2k | Active | | [craft-agents-oss](https://osrepos.com/repo/lukilabs-craft-agents-oss) | TypeScript | Apache-2.0 | 7.2k | Active | | [Kun](https://osrepos.com/repo/kunagent-kun) | TypeScript | Other | 6.3k | New | | [goose](https://osrepos.com/repo/aaif-goose-goose) | Rust | Apache-2.0 | 54.9k | Active | ## Considerations The repository is active, with frequent commits and releases, but measured contribution is highly concentrated in one person. That concentration is a continuity risk for a desktop agent with many integrations and security-sensitive capabilities. Abu can read and modify files, run commands, and control a computer. Its safeguards are not equivalent across platforms: the README describes macOS Seatbelt confinement for shell commands, while Windows lacks an OS-enforced file-access sandbox. Network isolation also relies on proxy configuration rather than OS enforcement. Evaluate these boundaries against your data and threat model before enabling broad permissions. Building from source requires Node.js 24, Rust stable, and platform build tools. The project is licensed under Apache-2.0; its README notes that the Enterprise edition requires a separate license.