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.
Усильте агента
Собственный URL издателя. Не эндпоинт PlugMCP.
Host a copy with our keys and logs.
https://api.supercompress.dev/api/mcpКнопка Claude выше открывает Claude с заполненными названием и URL. Подтвердить добавление всё равно нужно там.
claude mcp add --transport http io.github.supercompress-supercompress https://api.supercompress.dev/api/mcpRun in a terminal.
{ "mcpServers": { "io.github.supercompress-supercompress": { "command": "npx", "args": [ "-y", "mcp-remote", "https://api.supercompress.dev/api/mcp" ] } }}claude_desktop_config.json
Удалённый URL или команда на вашем компьютере? Чем различаются два способа установки
Запустить на PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
ЗапускОт издателя
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.
Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.
| 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.
SuperCompress is a compression layer in front of inference:
The query is never compressed — only the surrounding context.
Private marketing, outreach, and model training stay out of this repo (see .gitignore + docs/REPO_LAYOUT.md).
We measure whether required evidence survives (containment), not downstream LLM completion.
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
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.
npm install -g supercompress-proxy
npx supercompress setup
Links your account, detects agents, installs MCP. Docs: coding agents
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.
More: vs truncation · vs summarization · vs alternatives
Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.
{ "mcpServers": { "io.github.supercompress-supercompress": { "url": "https://api.supercompress.dev/api/mcp", "headers": {} } }}Инструменты
Списка инструментов пока нет. У удалённых серверов он появляется после первой проверки состояния.
FAQ
Скопируйте на этой странице конфигурацию http для Cursor, Claude Desktop, Claude Code или VS Code. Она использует установку издателя, а не прокси PlugMCP.
Издатель указывает следующие переменные окружения: SUPERCOMPRESS_API_KEY.
SuperCompress доступен по HTTP.
Последняя проверка: 2026-11-09. Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.