Shypd.aiThe largest open index of AI toolsClaw Compactor is an open-source AI agent token compression engine that uses a 14-stage Fusion Pipeline to reduce LLM inference costs. It offers reversible compression, AST-aware code analysis, and intelligent content routing.
Trending
About
Claw Compactor is an open-source LLM token compression engine built around a 14-stage Fusion Pipeline, designed to significantly reduce LLM inference costs. It achieves 15–82% compression depending on content type, while maintaining reversibility and zero LLM inference cost. The pipeline incorporates specialized compressors, ranging from AST-aware code analysis for various programming languages to JSON statistical sampling and simhash-based deduplication. Its key design principles include immutable data flow, content-aware routing that auto-detects content types like code, JSON, logs, and diffs, and reversible compression via a hash-addressed RewindStore. This allows LLMs to retrieve original compressed sections when needed, making it ideal for developers and data scientists working with large language models.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
