agent-desktop

1. Playwright

   Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

   

2. AppSignal

   www.appsignal.com sponsored

   Monitoring that respects your time & budget. APM, error tracking, and dashboards for modern web apps. Ten-minute setup, transparent flat pricing, and support from engineers who actually use the product.

   

3. agent-device

   CLI to control iOS and Android devices for AI agents

   

4. tauri-pilot

   Interactive testing CLI for Tauri v2 apps : lets AI agents inspect, interact with, and debug Tauri applications in real-time

   

5. agnix

   The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.

   

6. webclaw

   Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.

   

7. git-parsec

   Git worktree lifecycle manager — ticket to PR in one command. Jira, GitHub Issues & GitLab integration. Parallel AI agent workflows, CI monitoring, stacked PRs, conflict detection.

   

8. 

9. SaaSHub

   www.saashub.com sponsored

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

10. mcpls

    Universal MCP to LSP bridge - expose Language Server Protocol capabilities as MCP tools for AI agents

    

11. desktopctl

    GPU-accelerated CLI tool for AI agents, to control computer via screen, mouse, and keyboard.

    

12. agent-workspace-linux

    Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.

    

13. forge-orchestrator

    Forge Orchestrator: Multi-AI task orchestration. File locking, knowledge capture, drift detection. Rust.

    

14. skills

    LLM skills that assist with coding in the 4D language (by e-marchand)

    

15. claude-view

    10 Claude sessions running. What are they doing? Live dashboard — monitor, cost tracking, search, sub-agent visibility.

    

NOTE: The number of mentions on this list indicates mentions on common posts plus user suggested alternatives. Hence, a higher number means a better agent-desktop alternative or higher similarity.

agent-desktop discussion

agent-desktop reviews and mentions

Posts with mentions or reviews of agent-desktop. We have used some of these posts to build our list of alternatives and similar projects. The last one was on 2026-08-13.

• Show HN: I spent 3 months making desktop automation stop lying to AI agents
• I might have solved computer use
• Debugging is also clicking 🖱️

  4 projects | dev.to | 10 Aug 2026

  agent-desktop — a native CLI that exposes any app's accessibility tree as snapshot / click / type / press with structured JSON. No screenshots, precise element references. Its progressive skeleton mode drills down the hierarchy instead of dumping it whole, cutting prompt tokens dramatically (they cite 78–96% on dense apps). And it ships a C-ABI library, so Python, Swift, Go or Node can call it in-process instead of shelling out per action. (macOS today, more platforms in progress; needs Accessibility and Screen Recording permissions.)

• I built the Playwright for desktop apps. 80% token savings
• A note from our sponsor - SaaSHub

  www.saashub.com | 25 Aug 2026

  SaaSHub helps you find the best software and product alternatives Learn more →

lahfir/agent-desktop is an open source project licensed under Apache License 2.0 which is an OSI approved license.

The primary programming language of agent-desktop is Rust.