ANC 100 — Agent-Native CLI Leaderboard
Automated agent-readiness scores for real CLI tools, scored against the eight principles. See the methodology for how scores, audience signals, and audit profiles work.
Curated CLIs, ranked by credit-weighted agent-readiness.
Public sites, ranked by agent-readiness on the checks that apply to each.
Scored against the eight principles. Run anc audit <tool> locally for source + project depth.
Scored against the emerging agent-web standards: MCP, llms.txt, OpenAPI, JSON Schema, discovery. anc audits; it doesn't own them.
Claim the badge
Tools at or above 70% can embed the agent-native badge on their README — a live link to their scorecard, not a static stamp. 71 of 98 listed tools currently qualify.
Methodology
Every score is the output of anc audit <binary> against a real CLI tool. The score column is the behavioral-layer compliance score: requirement checks, credit-weighted by outcome (a met requirement counts full, a missed SHOULD or MAY counts half); the principles met column counts how many of the eight principles have every check passing. The audience classification — when present — is informational, not authoritative; the per-tool page's evidence list is the ground truth.
For the full explanation of scoring, audience classification, audit profiles, and how to request a re-score, see the methodology page.
To reproduce any row locally, install anc and run anc audit <binary>.