An agent OS with interview-gated, staged evaluation and a budgeted self-evolution loop, exposed as an MCP server.
L5 gold
Scanned
5.8k Python 2d ago
Use cases
Architecture awareness, drift checks and evidence-based review passes.
Review plugins aim to make an agent a better reviewer: establishing a baseline of intended architecture, checking whether a change drifted from it, requiring evidence before a claim of success, and summarizing risk in a diff.
Prefer plugins that produce a reviewable artifact, such as a written report or a check that fails loudly, over ones that only assert the code looks fine. A review that cannot fail is not a review.
An agent OS with interview-gated, staged evaluation and a budgeted self-evolution loop, exposed as an MCP server.
GanyuanRan
Makes coding agents architecture aware: baseline first, evidence verified, drift checked, safe across long tasks.