AI Modelreg — Model Registry

• *rea:*Intelligence
• *ath:*services/ai/modelreg
• *ind:*Curated catalog of AI models (metadata, versions, benchmarks, curation tags)
• *tatus:*v0.0.1 — sector bootstrapping (20260509)

Role in the stack

modelreg is the Koder-side answer to "what models can we choose from, and what do we know about each?". It owns model *etadata* identity, version, license, weights URL, benchmark scores, capability tags. It is the missing trust layer that lets runtime/, gateway/, and product UIs pick models with full information instead of falling back blindly on whatever Ollama happens to have cached.

It is the Koder analog of HuggingFace Hub and MLflow Model Registry — scoped to Koder needs (curation + benchmarks + productfacing tags) and explicitly *eparated from runtime*(executor) and `kdbblob` (weight storage).

Boundary vs neighbors

• services/ai/runtime consumes slug → weights URL + min-VRAM; modelreg never serves weights.
• services/ai/eval produces benchmark rows; modelreg surfaces them per (model, version).
• services/ai/training registers fine-tunes as new versions but does not store weights here.
• infra/data/kdb-blob is the weight storage layer modelreg refers to.

Features (v1 target)

• CRUD API with multi-axis search (tag, license, family, modality, maxvram, mincontext)
• Model + version + tag entities backed by kdb-doc
• Curation flow: 2curator approval + benchmark gate for `kodercurated`
• Eval integration: ingest benchmark rows, query cross-model
• SDK helper engines/sdk/go/modelreg for runtime + gateway
• Cache invalidation via SSE event stream
• Web catalog UI at modelreg.koder.dev (deferred to v0.2)

Primary couplings

RFC and bootstrap

• RFC: modelreg-RFC-001-foundations.kmd — *ccepted*20260509
• Bootstrap ticket: services/ai/backlog/done/128-modelreg-bootstrap.md
• Implementation tickets: services/ai/modelreg/backlog/pending/{001..005}

Selfhostedfirst analysis (5 gates)