Desktop tools

Free / OSS · OSS/MIT · 4.2k GitHub stars

VerdictMIT Codex desktop/CLI companion. Handy for visual MCP and skills configuration; audit auth, relay endpoints, and unrestricted templates before trusting it.

CatchVs T3 Code: Codex-X is Codex-specific visual configuration plus MCP/skills, not a broad remote coding environment or an independent coding model. It handles `auth.json`, supports third-party relays, and allows unrestricted prompt templates — review where credentials go, which endpoint receives requests, and what instructions can execute before using a release. Treat relays as a trust decision, not a convenience toggle.

Free / OSS · OSS/MIT · 3.3k GitHub stars

VerdictMIT human+agent canvas when specs and decisions need to live beside the coding agent — not another Excalidraw clone.

CatchVs Excalidraw: this is a human+agent design/decision workspace wired to coding agents, not a general hand-drawn whiteboard. Extreme overnight star fill (~589) is discovery noise; a hosted team product is planned — keep the self-hostable OSS desktop as the free bar until that SKU is real.

Free / OSS · Apache-2.0 · 39.3k GitHub stars

VerdictApache-2.0 GUI-agent desktop when you want vision operators — budget a VLM path; do not expect the ended Remote Operator trial.

CatchVs Browser Use: LLM-DOM browser agents; UI-TARS is vision/GUI-agent first. Vs Cua: Cua is computer-use drivers/sandboxes/models; UI-TARS ships the desktop GUI-agent product. Needs a VLM (HF Apache-2.0 weights or VolcEngine/Doubao cloud); Remote Operator free trial ended 2025-08-20.

Free / OSS · Apache-2.0 · 1.8k GitHub stars

VerdictApache desktop computer-use when agents must drive native macOS apps by a11y refs — not agent-browser’s web CDP lane; Win/Linux still catching up.

CatchProduction a11y drive is macOS-first — Windows/Linux a11y and input still Planned in the support matrix (cdylib ships wider). Vs agent-browser (Vercel Labs browser CDP/a11y refs): agent-browser is the web/browser CLI; agent-desktop is native desktop apps via OS accessibility. Needs Accessibility (+ Screen Recording/Automation for some features); do not hand it a logged-in machine without a sandbox story.

Free / OSS · OSS/MIT · 9.5k GitHub stars

VerdictMIT Windows computer-use MCP when an agent must operate real Windows apps — run it on a disposable machine, never on a desktop you cannot afford to hand over.

CatchWindows only (7 through 11). It drives your real desktop session with full system access — it is not a sandbox, so run it on a machine or VM you are happy to let an agent control, and keep secrets out of reach. The first install can take a minute or two while dependencies resolve, and the very first start may time out once. Vs cua (sandboxed computer-use VMs and SDK) and agent-desktop (desktop automation agent): Windows-MCP is the plain MCP server on the Windows host itself.

Free / OSS · OSS/MIT · 6.5k GitHub stars

VerdictIf you run more than two coding agents and your skills folder has become a mess, this is the free fix.

CatchA single-maintainer project on a fast release cadence, so expect UI churn. Presets are a one-time copy, not a live sync, so a skill applied by preset will not follow later edits unless you re-apply. Installing marketplace skills in bulk is still installing other people's instructions into your agents — read them, especially ones that run scripts. GitHub sync means signing the app into GitHub. Vs cc-switch (provider switching with skills management on the side) and vercel-skills (the `npx skills` CLI): this is the dedicated GUI for people juggling many agents.

Free / OSS · Apache-2.0 · 91.1k GitHub stars

VerdictThe free standard for looking inside binaries — expect a learning curve, and pair it with an MCP bridge if your agent should help.

CatchA heavy Java desktop app — the 12.1 release needs a 64-bit JDK 21, and Python 3 for the debugger and PyGhidra. The UI is dense and the learning curve is steep. Check that you are allowed to reverse-engineer the target before you start.

Free / OSS · Apache-2.0 · 7.8k GitHub stars

VerdictWorth a weekend if you want a truly native desktop app from TypeScript — not yet for a product you must support for years.

CatchLabeled a Vercel Labs experiment, and nearly all commits come from one person. App cores are a checked subset of TypeScript, not the full language, and the core's frame arena and model heap default to a fixed 1 MiB each (overflow is a runtime panic). It needs Node.js 24+ and a pinned Zig toolchain. iOS and Android are experimental. Vs Tauri or Electron: far fewer components and libraries to lean on, so expect to build more yourself. Stars have grown fast (about 330 a week since the repo opened in May 2026), so judge it on a trial run, not the count.