Control, automate, and operate Android devices or fleets from one integrated platform.
Project overview
FIRERPA combines Android remote desktop, UI automation, OCR and image matching, traffic capture, Frida, proxy networking, and device operations behind one on-device service and Python client. It can work with or without root and expose controls through a browser, APIs, MCP clients, or a natural-language agent. The platform targets automation engineering, mobile security work, and long-running device farms, so its breadth and deployment complexity go well beyond a simple phone mirroring utility.
Use a browser-based remake of classic Microsoft Paint
Project overview
JS Paint recreates the tools and menus of classic Microsoft Paint in a web application, with touch support, themes, extra file types, and accessibility-oriented controls. Users can load images from URLs, upload to Imgur, and create experimental multi-user sessions. Those sessions are explicitly not private and may interrupt each other or lose work, so they are unsuitable for dependable collaborative editing.
Create WebRTC video, voice, and data channels in JavaScript
Project overview
simple-peer wraps WebRTC in a concise Node.js-style API that runs in browsers and Node.js. It supports video and voice streams plus text or binary data channels, with a Node duplex-stream interface for server-side use. Advanced options cover trickle ICE, custom configuration, transceivers, and renegotiation, making it a small communication layer rather than a complete calling service.
Run a configurable, multi-channel AI assistant on resource-constrained devices.
Project overview
nullclaw packages model providers, messaging channels, memory backends, tools, and service management into a self-contained Zig binary for ARM, x86, and RISC-V systems. It can run as an interactive agent, one-shot command, gateway, or background service, with implementations selected through configuration. The project reports a roughly 678 KB binary and about 1 MB peak memory use.
Route each conversation to the most suitable specialized AI agent.
Project overview
Agent Squad selects the most suitable specialized agent from each request and preserves conversation context across agents and sessions. It provides Python, TypeScript, and Swift runtimes with replaceable classifiers, storage, retrievers, and tools. The Swift implementation can keep routing, MCP tools, voice, and chat history on Apple devices, while GroundedAgent separates data gathering from response writing so answers stay limited to actual tool results.
Calls Claude Agent from Python with async queries, in-process tools, hooks, and interactive sessions.
Project overview
Claude Agent SDK for Python exposes an async query function and ClaudeSDKClient for bidirectional, interactive conversations with Claude Code. Custom tools and hooks can run as in-process MCP servers, while external MCP servers can be used alongside them. The package bundles the Claude Code CLI by default, requires Python 3.10 or newer, and allows a custom CLI path.
Turn live screen and audio context into meeting notes and action items.
Project overview
Glass is a desktop meeting and context assistant that combines on-screen activity with live audio to produce notes, summaries, action items, and answers based on earlier screen and sound history. Keyboard shortcuts let users show the interface or ask a question on demand, and the project states that the window stays out of recordings, screenshots, and the Dock. A ready-to-run macOS app is available, while Windows support is beta. Users can connect OpenAI or Gemini, or use local Ollama and Whisper models.
Set up and operate OpenClaw agents without using a terminal.
Project overview
ClawX is a desktop interface that embeds the OpenClaw runtime and replaces command-line setup with a guided application experience. Users can configure providers, chat with agents, manage skills, workspaces, scheduled tasks, diagnostics, and selected memory tools through visual controls, while Developer Mode exposes more advanced settings. It is aimed at users who want OpenClaw capabilities without maintaining a separate terminal-driven installation, with Windows and multilingual operation explicitly documented.
Give AI agents an anti-detection browser API with stable element references.
Project overview
camofox-browser wraps Camoufox in a REST service built for agent browsing, using compact accessibility snapshots and stable element references for navigation, clicking, typing, and extraction. It isolates cookies and storage by user and supports proxies, imported login state, traces, and several deployment targets. The first install downloads roughly 300 MB, and anonymized crash telemetry is enabled by default but can be disabled.
Use terminal agents with a choice of models to understand, plan, and modify code.
Project overview
Forge brings an AI coding workflow to the terminal through an interactive TUI, one-shot commands, or a Zsh colon-prefix interface. Its built-in forge, sage, and muse agents separate implementation, read-only code research, and planning. Developers can retain conversation context, choose among many model providers, and connect MCP tools without leaving their command-line workflow.
Use an open-source messaging app across desktop and mobile platforms.
Project overview
HuLa is an instant-messaging application for Windows, macOS, Linux, iOS, and Android. It supports direct and group chat, contact and group management, file transfer, voice and video calls, and an integrated AI chat assistant. A complete deployment also requires the separate HuLa-Server repository. A web version is not currently supported, and direct macOS downloads may require handling certificate or quarantine warnings.
Build reusable agent skills from visual, versioned workflows.
Project overview
Refly turns business procedures and team SOPs into reusable, versioned Agent Skills through a visual workflow builder. Skills can be installed, published, and shared through a registry, then exposed to other systems as APIs, webhooks, MCP services, or portable SDKs. It is aimed at teams that want durable agent capabilities rather than one-off prompts or copied automation templates.
Manage Markdown and plain-text notes across macOS and iOS.
Project overview
FSNotes is a Markdown-first notes manager for macOS and iOS that also works directly with ordinary text files. Notes can live across multiple folders and sync through iCloud Drive or Dropbox, while tags, double-bracket cross-note links, code highlighting, and inline images support organization and writing. Encryption, optional Git versioning, and backups are available for users who want more control over stored files.
Use Facebook Messenger in a dedicated, privacy-focused desktop client.
Project overview
Caprine is an unofficial Facebook Messenger desktop client for macOS, Linux, and Windows. It separates conversations from the browser and adds options such as dark themes, keyboard shortcuts, custom styling, silent updates, and adjustable text size. Some integrations, including menu-bar mode, Touch Bar support, and system Do Not Disturb behavior, are available only on macOS.
Collection or directoryDesign and creative workClaude Code
stitch-skills↗
@google-labs-code·TypeScript
Generate and manage Google Stitch designs, then turn them into frontend components.
Project overview
Use compatible coding agents to create or edit Google Stitch screens, import existing frontend code into a design, manage design systems, and generate implementation assets. The collection includes workflows for React, React Native, and other build targets, but the design operations depend on the Stitch MCP server and selectively installed skills may require companion skills.
Connect to Mullvad VPN and configure privacy controls across desktop and mobile devices.
Project overview
This is the official client for the Mullvad VPN service across desktop and mobile platforms. It supports WireGuard connections and options such as multihop routing, traffic obfuscation, custom DNS, content blocking, and controlled local-network access, while split-tunneling availability varies by platform. Mullvad publishes signed builds and external audit reports for the app. A Mullvad VPN service account is required to use it as a VPN client.
Run programmable browser sessions and web actions for AI agents and applications.
Project overview
Steel exposes a browser API that manages Chrome sessions, pages, processes, cookies, local storage, proxies, extensions, and cleanup for AI agents or automation applications. Developers can connect with Puppeteer, Playwright, or Selenium, or call quick endpoints for scraping pages, taking screenshots, and producing PDFs. It can be used through Steel Cloud or deployed locally with Docker and other supported setups. The project is still described as a public beta.
Generate prototypes, slide decks, and marketing assets with your chosen model.
Project overview
Open CoDesign is a local-first desktop app that turns prompts into interactive prototypes, slide decks, and marketing assets, with live preview, pinned comments, and targeted visual adjustments. It supports Claude, GPT, Gemini, Kimi, GLM, Ollama, and OpenAI-compatible providers, and can import existing Claude Code or Codex configurations. Projects can be exported as HTML, PDF, PPTX, ZIP, or Markdown. Cloud providers require the corresponding API key or subscription, while a local model can support offline use.