Find the open-source solution that fits.

Launch Chromium or attach to an existing Chrome session, then navigate, click, fill forms, inspect pages, and capture screenshots through the Playwright API while keeping pages alive across scripts. Dev Browser runs code in a QuickJS WASM sandbox without host access and restricts file operations to its own temporary directory, making it suitable for browser automation by coding agents.

Windows-MCP exposes Windows computer-use capabilities to MCP-compatible agents. Its tools cover clicking, typing, scrolling, dragging, shortcuts, screenshots, UI and display state, application and window control, and other system actions without requiring a particular vision model. It can run through uvx over stdio or an explicitly bound HTTP transport. Because the server operates with full system access and can perform irreversible actions, deployments should use authentication, IP and tool allowlists, and other restrictions; anonymized telemetry can be disabled.

Sigma File Manager helps Windows and Linux users work across many folders with typo-tolerant global search, tabs, and independent split panes. It can preview common media and document formats, organize items with tags, handle ZIP archives, and expose files over a local network. An extension marketplace adds further commands and tools, and Windows users can make it their default manager for many everyday actions. Support for remote network locations is still labeled alpha, so it should not yet be treated as a mature network-storage client.

Agora Flat provides web and desktop clients for creating, joining, and scheduling online classrooms. Teachers and participants can combine an interactive whiteboard with live audio, video, messaging, screen sharing, and course materials, then replay recorded classroom activity. The open-source client may be used commercially, but the project does not provide commercial customization, deployment assistance, or customer support.

Stretchly runs in the background and alternates short and long break reminders to help interrupt extended computer sessions. It supports macOS, Windows, and Linux with configurable preferences. On macOS, Gatekeeper may require the user to manually approve the app on first launch.

OpenChamber is a visual interface for OpenCode that presents chats, diffs, files, terminals, tool progress, and Git or GitHub workflows across desktop, browser, PWA, and VS Code surfaces. It can run multiple agents in isolated worktrees, continue sessions from another device, and connect through tunnels or SSH to remote instances. The desktop package bundles a matching OpenCode CLI, while the web, CLI, and VS Code editions depend on an existing OpenCode installation.

TagUI is an open-source RPA tool in which users write simple flows for clicking, typing, reading tables, and moving data through websites, desktop applications, or the command line. It runs on Windows, macOS, and Linux, supports many additional languages, and includes image, OCR, Excel, and Office-oriented options. AI Singapore has discontinued official maintenance and support, so current users depend on community maintenance.

Pulse provides one self-hosted workspace for monitoring Proxmox, Docker, Kubernetes, TrueNAS, and vSphere, with inventory, metrics, and alerts for homelabs and IT teams. Its scheduled Patrol checks can surface failures that were never covered by a hand-written rule, such as repeated backup failures, full storage pools, or restart loops, using a user-supplied AI provider or local model on community installs. Core monitoring is available in the free Community tier, while guided investigation and verified remediation are paid features.

YouTube Music Desktop App puts YouTube Music in a dedicated desktop application instead of a regular browser tab. The project publishes binaries for Windows, Linux, and macOS and supports common installation routes including Winget, Scoop, AUR, and Homebrew.

React NodeGUI is a React renderer for NodeGUI that builds Qt5-based desktop applications for Windows, macOS, and Linux. Developers can compose native widgets with React, style them with cascading CSS and Flexbox, and use Node.js APIs without bundling a Chromium runtime. The repository explicitly states that the project is no longer maintained, so adopting it now means accepting an aging stack or maintaining a fork yourself.

Everywhere is a desktop assistant for Windows and macOS that appears beside the active application when summoned by a shortcut. It uses accessibility and UI automation data, alongside screen context, to help explain errors, summarize pages, translate text, or act through configured MCP tools without requiring repeated screenshots and copy-paste. The application supports multiple model providers, so the available reasoning and actions depend on the LLMs, permissions, and tools the user configures.

CodePilot is a desktop agent client for coding and general assistant work, with configurable model providers, persistent workspace memory, MCP servers, reusable skills, scheduled tasks, and image generation. Telegram, Feishu, Discord, QQ, and WeChat bridges let you send requests from a phone. Claude Code CLI is optional for chat, but required for direct file editing, terminal commands, and Git operations.

DeepChat is a local-first desktop client for running cloud and local models alongside agent tools. It supports installable Skills, MCP services, and ACP-compatible agents as first-class session options, while its Tape and Trace views preserve context, tool calls, requests, and results for inspection or recovery. Users can also control sessions through messaging integrations such as Telegram, Feishu/Lark, Discord, and others, making it suited to longer-running agent workflows.

Trail of Bits Skills Marketplace packages reusable plugins for AI-assisted security analysis, vulnerability research, testing, and selected development workflows. Users can add the marketplace to Claude Code and install individual plugins through its menu, while Codex can load the same marketplace through Claude plugin compatibility. The collection is aimed at security researchers and engineering teams that want repeatable audit procedures available to their coding agents.

Kando is a cross-platform desktop pie menu that organizes app launching, file opening, keyboard shortcuts, and other actions into configurable radial menus. The menus can be controlled with a mouse, stylus, touch input, controller, or keyboard, giving frequent actions a single visual entry point. Kando runs on Windows, macOS, and Linux, although some Linux desktop environments require additional setup.

MoeKoe Music is an unofficial KuGou client for Windows, macOS, Linux, and the web. It supports account login, music and video playback, lyrics, recommendations, playlists, favorites, global shortcuts, desktop lyrics, themes, plugins, and layout customization. Desktop releases can be downloaded directly, while the web edition can be self-hosted with Docker. The repository restricts use to personal learning and research and asks users to observe copyright and local legal requirements.

Outerbase Studio is a lightweight browser interface for managing SQL databases. It supports SQLite and related services such as LibSQL, Cloudflare D1, and rqlite, with query, data, schema, and connection-management tools. MySQL and PostgreSQL support is currently beta with limited features. A Windows and macOS desktop wrapper is available when a database driver cannot run in the browser.

Livebook lets teams write Markdown and Elixir code cells together in a browser, then run queries, charts, and other data tasks on demand. Notebooks are stored as versionable .livemd files and can connect to a fresh runtime, an existing Elixir node, or a project. Because users can execute code and access files on the host, deployed instances should be carefully protected.