{"id":"open-compress-claw-compactor","name":"claw-compactor","af_score":56.5,"security_score":32.8,"reliability_score":38.8,"what_it_does":"Claw Compactor is an open-source Python library/CLI that compresses LLM input text and workspace content using a 14-stage, content-aware “Fusion Pipeline.” It focuses on reversible compression (via marker-based rewind retrieval) and AST-aware code compression (tree-sitter when available), aiming to reduce token counts and estimated inference cost without using external LLM inference for the compression itself.","best_when":"You need local, offline, deterministic-ish token reduction for structured and code-heavy content (code/JSON/logs/diffs), and you want reversibility via markers for later retrieval.","avoid_when":"You require a networked service with standardized REST/GraphQL contracts, or you need strong confidentiality controls beyond local handling (e.g., multi-tenant environments without sandboxing).","last_evaluated":"2026-03-30T13:21:10.822162+00:00","has_mcp":false,"has_api":false,"auth_methods":["None (local library/CLI usage)"],"has_free_tier":false,"known_gotchas":["Reversibility depends on RewindStore/marker handling; agents must preserve marker IDs and have access to rewind retrieval in the same execution context/config.","Tree-sitter/token-count accuracy depend on optional extras; behavior and exact token estimates may differ without optional dependencies.","Because it’s content-aware, stage application can be skipped; agents should not assume all stages run for every input."],"error_quality":0.0}