Compression Engine

Technical deep-dive into the OpenCompress compression pipeline.

Architecture

The compression engine runs a two-stage pipeline on every user message in your request:

User Message → Stage 1: Dictionary Aliasing → Stage 2: Semantic Pruning → Compressed Message

System messages and assistant messages are passed through unmodified.

Stage 1: Dictionary Aliasing

Repeated multi-token phrases are identified and replaced with compact aliases:

Before: "The retrieval-augmented generation system uses retrieval-augmented generation to..."
After:  "§A=retrieval-augmented generation. The §A system uses §A to..."

When it helps most:

• System prompts with repeated terminology
• RAG contexts with recurring entity names
• Tool schemas with verbose type annotations
• Multi-turn conversations with repeated context

Stage 2: Semantic Pruning

A distilled classifier (trained on 105K+ real agent conversations) scores each token by semantic importance. Tokens below the threshold are removed:

Before: "Could you please provide me with a detailed and comprehensive explanation of..."
After:  "Explain..."

The classifier preserves:

• Named entities and technical terms
• Logical connectors that affect meaning
• Numerical values and specific references
• Code and structured data

Training data: 105K agent conversations across coding, analysis, writing, and tool-use domains. Quality is validated by cosine similarity between original and compressed embeddings.

Compression rates by content type

Content Type	Typical Compression	Notes
Natural language instructions	40-55%	Highest savings
RAG / retrieved documents	35-50%	Good savings, preserves facts
Conversation history	30-45%	Repeated patterns compress well
Code blocks	10-20%	Minimal compression (already dense)
JSON / structured data	15-25%	Some key name shortening

Quality validation

Every compression is scored:

• Cosine similarity between original and compressed embeddings
• If similarity drops below 0.85, the original is sent unmodified
• Quality scores are logged and visible in your dashboard

Compression never modifies the model’s response. We only compress your input — the model generates its response normally from the compressed prompt.