Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for advanced developers who want to experiment with a fully inspectable coding-agent harness, especially if they care more about editing the loop and audit trail than about matching a vendor's default UX.
Who should use it
Who should skip it
Avoid running griffinwork40/agent-afk in production until you have reviewed its permissions, data-access scope, and failure modes in a sandbox.
About this signal
griffinwork40/agent-afk is tracked by RepoRadar as a agent system in the Coding Tools section. It was first seen on 2026-06-27 and last updated on 2026-06-27. The current verdict is 'worth watch' with a Silver tier and moderate setup difficulty. Across RepoRadar's eight signals, griffinwork40/agent-afk is strongest on open-source/build quality (8.4) and novelty (8.0) and weakest on momentum (5.0) — a profile worth weighing against your own priorities. 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 griffinwork40/agent-afk a composite score of 7.6 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 37.0 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
New installs default to bypassPermissions and the README says the agent can read and write anywhere without per-tool approval, which is a large blast radius for unattended runs; Daemon and Telegram workflows extend the agent outside the terminal, so limit it to disposable workspaces until you verify the guardrails and trace review flow; The README's model table includes forward-looking names like GPT-5.5 and Claude Opus 4.8, so treat provider-specific capability claims as maintainer guidance rather than verified compatibility.