Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI engineering teams and platform teams who need a real MIT Go-runtime to turn Claude Code / OpenClaw / Hermes / Codex into a coordinated agent team (not a chat box), for organizations that need a real browser-based supervisor + shared project memory + parallel loops without paying per-agent-hour tax to a managed agent PaaS, and for teams evaluating a single-Go-runtime MIT alternative
Who should use it
Who should skip it
Skip compozy/compozy unless the captured evidence suggests it solves a problem you are actively working on.
About this signal
compozy/compozy is tracked by RepoRadar as a framework in the Agent Infrastructure section. First seen 2026-08-13; the source record was last checked on 2026-08-13. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for compozy/compozy are workflow potential (9.9) and practical usefulness (9.0), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The compozy/compozy record combines a 8.4/10 composite score with separate popularity (2.5), risk (low), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
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
It wraps Claude Code / OpenClaw / Hermes / Codex and exposes a browser supervisor that can drive all four agent CLIs against your codebase; pin the supervisor to a private network, audit the browser session before granting production credentials, and confirm the shared-memory scope before pointing it at sensitive data.