# adrida/tracer

TRACER: replace 90%+ of your LLM classification calls with a traditional ML model. Formal parity guarantees. Self-improving.

Repository: https://github.com/adrida/tracer
Canonical: https://ross.abutalabs.com/products/adrida-tracer
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2026-08-26T01:30:34+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 89, longevity 11
- inputs: {"age_days": 157, "days_push": 8, "days_rel": 75, "gap_med": 4.5, "n_releases_24m": 3}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1030, forks 76 (observed 2026-08-28T04:03:17.887651+00:00)

## What it is
TRACER is a Python library that learns a routing policy from LLM classification traces, fitting a lightweight traditional ML surrogate to handle easy inputs and deferring only uncertain ones back to the LLM. It claims 90%+ of classification calls routed to non-LLM models with formal parity guarantees and a self-improving policy as deferred calls generate new training traces.

## Use cases
- reduce LLM API costs for classification pipelines
- route easy classification inputs to a cheap ML model
- distill an LLM classifier into a traditional ML surrogate
- cut inference spend on high-volume text classification
- build a self-improving routing layer over an LLM classifier
- guarantee agreement between surrogate and teacher LLM outputs

## When to choose
- you run high-volume LLM classification and want to cut API costs
- most of your classification traffic is repetitive and easy
- you need formal guarantees that a cheaper model matches your LLM's outputs
- you want the routing policy to improve automatically over time

## When to avoid
- your inputs are diverse and genuinely require LLM reasoning on most calls
- you need generative outputs rather than classification labels
- you cannot produce labeled traces from your LLM pipeline
- your classification task changes frequently, invalidating learned boundaries

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-inference, rag
- domain: machine-learning, large-language-models, developer-tools
- platform: python, cli
- tags: llm-cost-optimization, model-routing, surrogate-model, classification, distillation, cost-reduction

## Member repositories
- adrida/tracer (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:17.887651+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:07:32.026396+00:00, confidence not recorded.
  - readme: https://github.com/adrida/tracer (fetched 2026-08-28T04:03:17.887651+00:00, sha f4393fb62a17)
- Data as of 2026-08-30T08:39:29.467469+00:00.