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.

| Usual “fix” | What actually happens | |---|---| | Truncate | Deletes the middle. The answer is often in the middle. | | Summarize | Rewrites evidence. IDs, stack traces, and exact errors get soft. | | Hope | Ship the full dump. Watch the bill climb. |

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:

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

The query is never compressed — only the surrounding context.

Two paths

| | Neural v2 (recommended) | Compiler (fast/local) | |---|---|---| | Engine | ~400M query-aware cross-encoder | Lightweight local policy | | Runtime | Hosted Fly CPU (Neural Keep) | Local CPU · millisecond-class | | Best for | Highest-quality keep on agent dumps | Local preprocessing / speed | | Benchmarks | Launch / B5 | Legacy section |

Two products

| | Coding-agent plugin | API / Python | |---|---|---| | For | Cursor, Claude Code, Codex, and 40+ agent harnesses | Apps, RAG, agents, backends | | Install | npm i -g supercompress-proxy && npx supercompress setup | pip install supercompress | | What you get | MCP compress_context on big dumps | Compress before every model call | | Login | Keep your normal agent login | API key from the dashboard |

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

Repo map

| Path | What | |------|------| | packages/proxy | Coding-agent plugin (npm) | | api/ | Hosted API + billing | | web/ | Site + docs HTML | | supercompress/ | Python package | | docs/REPO_LAYOUT.md | What belongs in OSS vs private |

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

| Metric | Result | |---|---:| | Mean context cut | 64.1% | | Evidence passes | 24 / 24 | | Tokens | 16,647 → 5,148 | | Max cut @ ≥99% retention | 96.6% | | B5 latency p50 | ~5.8 s (hosted Neural Keep on Fly CPU) | | Public cases (full suite) | 390 | | Downstream LLM eval | Not yet run |

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

| | Truncate | Summarize | SuperCompress | |---|:---:|:---:|:---:| | Cuts tokens | ✓ | ✓ | ✓ | | Uses the query | ✗ | weak | ✓ | | Keeps original evidence | sometimes | ✗ | ✓ | | Auditable kept lines | partial | ✗ | ✓ |

More: vs truncation · vs summarization · vs alternatives