{"adoption": {"forks": 67, "observed_at": "2026-08-28T04:03:32.964752+00:00", "stars": 1092}, "canonical_url": "https://ross.abutalabs.com/products/caveman-compression", "card": {"archived": false, "artifact_type": "library", "description": "Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.", "domain": ["large-language-models"], "enriched": true, "function": ["nlp", "llm-inference", "compression", "prompt-engineering"], "health_score": 53, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["wilpel/caveman-compression"], "name": "wilpel/caveman-compression", "platform": ["python", "cli"], "pushed_at": "2025-12-03T17:04:50+00:00", "repo": "wilpel/caveman-compression", "stars": 1092, "tags": ["semantic-compression", "token-reduction", "context-optimization", "text-compression", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["reduce token costs when sending long context to an LLM", "compress prompt text to fit more content in a context window", "shrink RAG retrieved documents before passing to a model", "compress verbose documentation for LLM consumption", "offline text compression without an API", "compress multilingual text for LLM contexts"], "what_it_is": "A Python tool that compresses text for LLM contexts by stripping predictable grammar while preserving factual content, reducing token usage by 15-58%. It offers three modes: LLM-based (best compression via OpenAI API), NLP-based (free, offline, multilingual via spaCy), and MLM-based (free, offline, predictability-aware).", "when_to_avoid": ["you need byte-perfect lossless reconstruction of original text", "your content is mostly facts with little redundant grammar", "you cannot tolerate LLM-based decompression ambiguity in critical data"], "when_to_choose": ["you pay per token and want 15-58% context reduction", "you need a free, offline compression option via spaCy or masked language models", "you want to fit more retrieved documents into a fixed context window"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/caveman-compression", "repo": "wilpel/caveman-compression", "role": "main", "score": 41}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.964752+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:49:04.659798+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f29d9d076842df98b63d152e3d2435af29a0d30dce3fb32064644f73bd106a44", "fetched_at": "2026-08-28T04:03:32.964752+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wilpel/caveman-compression"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 55, "longevity": 20, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 289, "days_push": 273, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 41, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}