SuperCompress MCP server

SuperCompress v2

Query-aware context compression for AI applications and coding agents. Cut your API costs by 65%.

~400M Neural Keep on the hosted API · coding-agent plugin via MCP Open weights (MIT) on Hugging Face

Cut API costs by ~65% · 64.1% mean context cut · 24/24 evidence passes · up to 96.6% @ ≥99% retention (B5 coding-agent suite · evidence containment metric — not downstream LLM completion)

Get API key · Arena · Install · Benchmarks · Docs

vs Headroom · vs RTK · vs LLMLingua

Why it exists

Every LLM call ships a pile of context: RAG chunks, chat history, tool dumps, logs, JSON. Most of it is irrelevant to the current question — but the model still reads it, and you still pay for it.

SuperCompress v2 compresses context against the query. It keeps answer-critical lines in their original wording and drops the rest — on our coding-agent benchmark (B5), 64.1% mean context reduction with 24/24 evidence-retention passes.

Product

SuperCompress is a compression layer in front of inference:

1. Takes a long context + the current query
2. Segments and scores blocks by relevance to that query
3. Keeps entities, errors, definitions, nearby dependencies
4. Returns a smaller prompt + token stats

The query is never compressed — only the surrounding context.

Two paths

Shortened. The full README is on GitHub.