← graph·atlas · published on Geo Protocol
A field guide to the AI agent ecosystem — built like a specimen catalog, verified like a scientific record. Every capability claim carries its evidence; every risk is derived, not assumed.
01 · why
Vendor pages overclaim. Leaderboard numbers arrive without harness or date. Directory sites copy-paste the same risk warnings onto every tool. When we audited our own early data, 82 of 133 agents shared one of just three identical risk lists — decoration, not analysis.
ATG's answer is structural: separate what is claimed from what is verified, and never let a completeness score masquerade as a quality score.
02 · what's inside
Agents link to 45 core capabilities, 25 production controls, 14 protocols, 38 models, 24 runtimes, 11 risk types, and 19 benchmarks — through typed, weighted, evidenced edges.
03 · methodology
A claim enters the graph only through the pipeline. Official docs are fetched and content-hashed, snippets extracted with character offsets, decisions logged with rationale — and every change lands in an append-only audit log.
Rule-seeded from metadata. Visible, but styled as unproven.
Taxonomy analysis, no direct excerpt yet.
Backed by an official-source excerpt with URL and date.
03b · loop engineering
A static label degrades silently. ATG runs a verification loop: claims enter as inferred, earn evidence through a critic pass, and are re-checked on a schedule — so a verified edge means "verified as of the last audit," not "verified once and forgotten."
The three gates — fact-check on entry, evidence-quality on assignment, calibration on schedule — are what separate a loop with gates from an agent agreeing with itself at speed. The 127 pending evidence decisions aren't a backlog; they're the active queue of this cycle.
04 · risk model
A rules engine computes each agent's risk surface from its documented behaviors, then subtracts evidenced controls. An agent that ships approval gates genuinely scores safer than one that doesn't — 952 risk edges, all explainable.
05 · benchmarks
No score enters ATG without model, harness, source, and date. Vendor-reported and independently-standardized runs are labeled differently — because they differ by 10–30 points in the wild.
Frameworks (LangChain, CrewAI, …) carry no score by design — a library is not an end-to-end product.
06 · where it lives
ATG ships as a public knowledge graph on Geo — 5,896 graph operations, 337 comparison blocks, 280 support entities. Anyone can browse it, cite it, or challenge an edge through community governance.
Confidence levels map to visual styles in the published graph: verified edges render solid, reasoned dashed, inferred faint. What you see is what we can prove.
07 · next
Next milestones: close the verification loop on 127 pending evidence decisions through scheduled fact-gate and drift-detector passes, expand the verified core beyond 30 agents, self-run Terminal-Bench evaluations via Harbor, and independent scoring axes — completeness, task-fit, benchmark, risk — that never collapse into a single misleading number.