Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for advanced agent operators who want an inspectable, self-run computer-use layer for desktop automation experiments, but only if they can evaluate it inside a tightly sandboxed environment.
Who should use it
Who should skip it
Pass on iFurySt/open-codex-computer-use if your environment cannot support the access controls and sandboxing this risk profile requires.
About this signal
iFurySt/open-codex-computer-use is tracked by RepoRadar as a computer use mcp in the Automation section. It was first seen on 2026-06-28 and last updated on 2026-06-28. The current verdict is 'worth watch' with a Silver tier and moderate setup difficulty. iFurySt/open-codex-computer-use leads on workflow potential (8.7) and open-source/build quality (8.4); its lowest signal is maturity (5.8), 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 iFurySt/open-codex-computer-use a composite score of 7.9 out of 10, placing it in the Silver 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 1.0 and never affects the composite score or tier. The risk label of 'high' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Computer use grants an agent direct control over the desktop and visible apps, so first evaluation should stay on a disposable machine with non-sensitive accounts only; On macOS the setup asks for Accessibility and Screen Recording permissions, which materially widens what a connected agent session can observe and do.