Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI agent power users who run multiple coding agents (Claude Code, Codex, OpenCode, Pi Agent, Gemini, Copilot) and need one persistent workspace to keep them all alive at once: a native Ghostty terminal surface with split-pane hotkeys, a T3code GUI pane layer, and a Chromium browser pane with Chrome DevTools MCP and a `/ghostex-browser-use` command that lets the agent control the user's
Who should use it
Who should skip it
Skip maddada/Ghostex if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
maddada/Ghostex is tracked by RepoRadar as a native macos ghostty workspace f in the MIT native macOS desktop workspace built on Ghos section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Gold tier and easy setup difficulty. maddada/Ghostex leads on workflow potential (9.1) and maturity (8.8); its lowest signal is momentum (7.0), so factor that in before investing setup time. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned maddada/Ghostex a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 461.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Risk explanation
**The `/ghostex-browser-use` slash command lets the agent control open browser tabs without an approval prompt.** The README explicitly advertises this as a feature ('/ghostex-browser-use to let the agent control your browser tabs without an approval prompt'); this is the same browser-control trigger as the cycle 145 session-cookie reject, but in Ghostex's case the feature is opt-in (the user has to invoke the slash command in an active agent session, and the browser pane is a separate pane the user has to open), and the maintainer is not advertising it as a credential-exfiltration primitive — a RepoRadar reader who turns this on should know that the agent will be able to drive their open tabs (read DOM, click, type, scroll) without per-action confirmation, so any logged-in sessions in those tabs (Gmail, GitHub, banking, internal SaaS) are exposed to the agent's actions for the duration of the session; **The mobile companion app is in TestFlight on iOS, not in the public App Store.** The README says 'Join discord for iOS app testflight,' which means the iOS build is a TestFlight beta that requires a Discord invitation to enroll; users who cannot or do not want to install a TestFlight beta cannot use the iOS companion, and the TestFlight beta is bound to the maintainer's Apple Developer account, so it will not survive a maintainer-account change; **Windows and Linux ports need contributors.** The README is explicit that Ghostex is currently macOS-only and the maintainer is calling for contributors on Windows and Linux ports; non-macOS users should not expect a working build until those ports land, and the macOS-specific pieces (Accessibility API integration, SwiftUI, the Homebrew cask, the ASAR patch for the Desktop picker) are the part of the codebase that needs cross-platform work.