{"adoption": {"forks": 76, "observed_at": "2026-08-28T04:03:17.887651+00:00", "stars": 1030}, "canonical_url": "https://ross.abutalabs.com/products/adrida-tracer", "card": {"archived": false, "artifact_type": "library", "description": "TRACER: replace 90%+ of your LLM classification calls with a traditional ML model. Formal parity guarantees. Self-improving.", "domain": ["machine-learning", "large-language-models", "developer-tools"], "enriched": true, "function": ["machine-learning", "llm-inference", "rag"], "health_score": 99, "homepage": null, "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["adrida/tracer"], "name": "adrida/tracer", "platform": ["python", "cli"], "pushed_at": "2026-08-26T01:30:34+00:00", "repo": "adrida/tracer", "stars": 1030, "tags": ["llm-cost-optimization", "model-routing", "surrogate-model", "classification", "distillation", "cost-reduction"], "topics": [], "urls": [], "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"], "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.", "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"], "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"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/adrida-tracer", "repo": "adrida/tracer", "role": "main", "score": 78}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.887651+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:07:32.026396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f4393fb62a178f6a48e98fb8f3cc08fa7df508d9e2231eece38fb53c51c3e661", "fetched_at": "2026-08-28T04:03:17.887651+00:00", "kind": "readme", "missing": false, "url": "https://github.com/adrida/tracer"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 11, "rhythm": 89}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 157, "days_push": 8, "days_rel": 75, "gap_med": 4.5, "n_releases_24m": 3}, "score": 78, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}