llms.txt

# TRACER - tracer-llm

> **TRACER** = Trace-Based Adaptive Cost-Efficient Routing.
> Turn LLM classification traces into routing policies. Surrogate handles easy traffic; teacher LLM handles hard. Formal quality guarantees.

## Install
pip install tracer-llm

## Core API (4 functions)
tracer.fit("traces.jsonl", embeddings=X) → FitResult
tracer.load_router(".tracer", embedder=e) → Router
router.predict("text" or embedding) → {label, decision, accept_score}
tracer.update("new.jsonl", embeddings=X_new) → FitResult

## Trace format (JSONL, one per line)
{"input": "user text", "teacher": "label_from_llm"}

## Embedder (for text-in routing)
Embedder.from_sentence_transformers("model-name")
Embedder.from_endpoint("https://api/embed", headers={...})
Embedder.from_callable(fn)

## Docs
- AGENTS.md - full integration guide for AI agents
- README.md - user-facing docs
- docs/api.md - Python API reference
- docs/cli.md - CLI reference
- docs/concepts.md - how it works
- docs/artifacts.md - .tracer/ directory schema
- docs/troubleshooting.md - common errors and fixes

## Paper
Published paper: TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification.
https://arxiv.org/abs/2604.14531

Pricing Capability research paper:
https://github.com/adrida/tracer/blob/main/research/pricing-capability.pdf
https://tracerml.ai/research/pricing-capability/
Current final submission: 21 pages, dated August 25, 2026.
Defines Capability Alpha under controlled evaluation, develops Price-Implied Uplift,
and places the Spirit case beside a public transaction panel.

## Repo
https://github.com/adrida/tracer