Quality is the
New Currency
Agents write code at machine speed; we still review it at human speed. Topos reads the structure of agent-generated code — not just whether it runs — and returns an auditable verdict.
Four lenses on one file.
Topos provides structural code quality metrics that allow AI coding agents to autonomously evaluate, iterate on, and optimize the code they generate.
Beyond pass/fail.
A Code Quality Medal per file — concrete tiers an agent can target, not a vague “make it better.”
Toggle pillars to see the verdict
NONE
Passes none (or fails to parse)
PLATINUM
Passes all 4 pillars
GOLD
Passes 3 of 4 pillars
SILVER
Passes 2 of 4 pillars
BRONZE
Passes 1 of 4 pillars
NONE
Passes none (or fails to parse)
Set preferences to tell agents which medal — or pillar mix — to target under time and token budgets.
See how packages score on the leaderboard→It's open source, and we want you to break it.
Topos is in active development. Run it in your editor or wire it into your agent — then tell us where the verdict is wrong.
MCP Server
Wire Topos into your agent so it optimizes toward the verdict.
Open→GitHub
Read the engine and run it yourself. BSD-3, open source.
Open→Leaderboard
See how open-source packages score across the four pillars.
Open→