SuperCompress

SuperCompress v2

Query-aware context compression for AI applications and coding agents.

Cut coding-agent context ~64% in our B5 benchmark.

~400M Neural Keep on the hosted API · coding-agent plugin via MCP

Open weights (MIT) on Hugging Face

64.1% mean context cut on B5 (24 coding-agent cases) · 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

Two products

Docs: coding agents (first 5 minutes checklist) · API quickstart

Repo map

Private marketing, outreach, and model training stay out of this repo (see .gitignore + docs/REPO_LAYOUT.md).

Benchmarks & stats

We measure whether required evidence survives (containment), not downstream LLM completion.

Neural v2 launch (hosted ~400M) — B5 coding-agent suite

Aggregate mean cut across all 390 cases is ~3.6% — the engine often refuses to over-cut dense needle/QA slices. The 64.1% figure is the coding-agent suite where dumps are noisy.

Raw JSON: launch-benchmark.json · writeup: benchmarks

Legacy compiler (separate product)

CPU / millisecond-class local path. Older held-out compiler numbers (≈58–66% cut, 99.4% gold containment) live under Legacy/compiler on /benchmarks. Do not mix with Neural v2.

Try it

Coding agents (recommended)

npm install -g supercompress-proxy
npx supercompress setup

Links your account, detects agents, installs MCP. Docs: coding agents

Python / HTTP

pip install supercompress
export SUPERCOMPRESS_API_KEY=sc_live_YOUR_KEY

from supercompress.client import SuperCompress

sc = SuperCompress()
result = sc.compress(
    context=long_context,
    query="What failed and how do we fix it?",
)
print(f"{result.original_tokens} → {result.kept_tokens} tokens")
print(result.compressed_text)

curl -X POST https://www.supercompress.dev/api/v1/compress \
  -H "X-API-Key: $SUPERCOMPRESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"context":"...","query":"What failed?"}'

Or paste a dump into the Arena — no integration required.

How it compares

More: vs truncation · vs summarization · vs alternatives

supercompress.dev · MIT License · Sponsor · built by Arjun Shah