Beta catalog · unsigned

HiQS AI Resolve

Find any model, harness, or AI-enabled service.

Give your agents a few precise commands to discover capabilities, inspect the evidence, and resolve a usable route.

Agent commandcatalog / discover
hiqs-registry lookup <capability>

The ambition is broad discovery. Every current result remains explicit about coverage, evidence, and unknowns.

Three commands between a name and a decision

01

Find broadly

Search across models, harnesses, gateways, services, and runtimes without collapsing them into one ambiguous kind.

02

Verify precisely

Inspect the source, revision, digest, observation time, and verification state behind every useful claim.

03

Resolve deterministically

Apply your written policy and receive one reproducible execution route — or a refusal that explains what is missing.

A short path from discovery to a decision

$ hiqs lookup "apex" --catalog fixture:synthetic

$ hiqs explain --claim c-apex1-release --catalog fixture:synthetic

$ hiqs resolve "model:fixture/apex-1@r1" --harness harness:fixture/forge-cli@1.4.0 --policy fixtures/strict-ranked.policy.json --catalog fixture:synthetic

→ one evidenced harness + gateway + model route, or a structured refusal

One discovery surface. Five distinct kinds.

Model

An identity, not an endpoint. Family, release, and how strongly it is pinned — artifact digest down to a floating alias, each with evidence for that classification.

$ hiqs lookup <model> --catalog fixture:synthetic

Harness

The thing that executes: an exact package revision, its execution mode, adapters, and the capabilities someone evidenced.

$ hiqs lookup <harness> --catalog fixture:synthetic

Gateway

A serving path: operator, API revision, transports, and concrete bindings to the models it actually serves.

$ hiqs lookup <gateway> --catalog fixture:synthetic

Service

An AI-enabled product that may invoke models you never chose — with operation-scoped disclosure of which ones, including honest unknowns.

$ hiqs lookup <service> --catalog fixture:synthetic

Runtime

A local inference scaffold: the software that loads and serves models on your own machine or cluster, with its distribution and API dialects.

$ hiqs lookup <runtime> --catalog fixture:synthetic

One route, or a specific refusal

Success means exactly one harness + gateway + model triple with its binding, adapter configuration, evidence references, and a deterministic trace. Anything less refuses, and says exactly why:

AMBIGUOUS_ALIASa colloquial name maps to two models your policy ranks equally
TIED_ROUTEStwo gateways serve the same model and no preference was declared
NO_SERVING_BINDINGthe model exists but this snapshot records nobody serving it
UNVERIFIED_CLAIMthe route depends on claims nobody has verified
CONFLICTING_CLAIMStwo records contradict each other; the registry never picks a winner
INSUFFICIENT_PINthe identity is a floating alias and your policy requires a stronger pin

High-quality signal or no signal

Attested

Every decision-relevant field names a source, a recorder, and an observation time — or explicitly says it cannot.

Relevant

Claims are scoped to the exact claim digest they support. Editing a value invalidates its verification.

Fresh

Capture, verification, effective, and publication times are separate fields, always visible.

Structured

Unknown is a valid, displayable, refusable state. Guessing never is.

Honesty is the product

This is a beta. The catalog bytes are unsigned and not for production trust. Demo data is labeled Synthetic or Imported wherever it appears — fixture execution is never presented as verification of real vendors.

"Feasible per these claims" does not mean credentials, quota, live availability, or upstream behavior are guaranteed. The catalog reports facts and possibilities; your policy — written by a human, accepted explicitly — makes the choice.