AIMS Compass · v1 · OSS reference toolkit

The best model for every call.

Multi-vendor LLM routing by cost, tools, inference, and adversarial-challenge.

AIMS Compass is the reference model router. Register your provider keys once; declare per-call requirements; Compass picks the cheapest model that meets each call's requirements.

Why Compass

Model choice shouldn't be hardcoded.

Cost and capability profiles vary by call. A code-completion call has different requirements than a contract-review call. Agents should declare what each call needs, not which model handles it. Compass is the router that makes that possible.

What you can declare

Per-call requirements.

Compass routes by what your call needs, declared per call:

  • Max cost per call (in cents or per-token)
  • Required tool / function call support
  • Inference time budget (max latency)
  • JSON-mode capability
  • Minimum context window
  • Required modality (text / vision / audio)
  • Adversarial-challenge round (for safety-critical calls)
  • Vendor exclusions or pinned-model overrides
Install

One line per language.

Exact package name and registry pending the AIMS-tools repo organization decision. Install command will be one of:

npm install @aims/compass
pip install aims-compass
go get github.com/Extended-Systems-Intelligence/aims-compass
AIMS registry integration

Every routing decision auditable.

Compass registers as a model-routing instrument with the AIMS agent registry. Each routing decision — which model served the call, which lost — is recorded to the registry audit log. The registry exposes the decisions for conformance review without exposing the prompts or completions themselves.