Core Characteristics
In-Memory AST Pipeline
Runs entirely in volatile memory with sub-3ms latency. No network hops or secondary LLM calls.
Deterministic Token Pruning
Removes low-entropy filler words, conversational padding, and redundant determiners systematically.
Immutable Safe Vault
Guarantees 0.00% syntax drift by vaulting code fences, JSON structures, and interpolation tags before processing.
The Input Token Problem
Production prompts, multi-agent messages, and RAG document injections accumulate significant non-essential token overhead:- System Scaffolding: Instructions often contain repetitive guidance, politeness prefixes, and verbose role definitions.
- Retrieved Context Bloat: Document fragments, Markdown tables, and structured chunks contain redundant headers, excessive whitespace, and conversational transitions.
- Direct Impact: Input token volume directly dictates time-to-first-token (TTFT) and per-request inference cost across all downstream model providers.
Processing Pipeline
- AST Scan & Vaulting: Identifies code fences, JSON objects, mustache variables (
{{var}}), and regex expressions. Replaces them with atomic placeholder tokens in memory. - Scaffolding Simplifier: Condenses verbose system directives into direct instructions (e.g. role and task indicators).
- Density Pruning: Prunes low-entropy qualifiers, hedging, and filler adverbs while protecting logic anchors (
never,must,only). - Vault Rehydration: Restores the vaulted code and JSON contents into exact coordinates with complete byte-level fidelity.
Architectural Guarantees
- Zero Data Retention: Prompts and compressed outputs exist only in server RAM during active execution. No prompt text is written to persistent storage, cached in secondary layers, or used for model training.
- Structural Integrity: Fenced code blocks and JSON schemas remain unmodified, preventing parser errors in downstream tools.
- Reproducibility: The compression algorithm is deterministic. Identical input in the same mode produces identical output.