SuperCompress

io.github.Supercompressv0.5.38Updated Oct 3, 2026

Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & MLProductivity & Workflow

Overview

AI-generated overview

Compresses bulky coding-agent context against the current question to cut LLM input tokens, exposing compression, account linking, and usage tools over MCP.

What it does
SuperCompress scores large context such as files, logs, tool dumps, and pastes against the current question and drops filler while keeping evidence-critical lines in their original wording. It exposes MCP tools including compress_context, connect_account, and usage_summary, and can also install hooks and MCP configuration across many coding harnesses. An optional localhost proxy can rewrite base URLs for OpenAI- and Anthropic-compatible clients.
When to use it
Worth adding when a coding agent regularly sends large files, logs, or tool output and you want fewer input tokens without losing answer-critical content. It suits Cursor, Claude Code, Codex, and similar harnesses that support MCP or hooks.
Requirements
Node.js 18+ for the npm package supercompress-proxy, run via npx or installed globally. A SuperCompress account is linked through the setup command or OAuth/device-link; the optional API key is passed as SUPERCOMPRESS_API_KEY. Network access to the SuperCompress API is required, and the optional local proxy listens on localhost:8080.
Before you install
Context text is sent to the SuperCompress API for hosted compression, so avoid sending secrets or regulated data through it. The service is metered: a free monthly token allowance applies, then usage is billed, so check quota with usage_summary. The setup command writes MCP and hook configuration for detected agents, and uninstall removes files under the user's home directory. Treat SUPERCOMPRESS_API_KEY as a secret.

Installation

In SourceWeft

  1. Open SuperCompress in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "supercompress": {
      "type": "http",
      "url": "https://api.supercompress.dev/api/mcp"
    }
  }
}

README

SuperCompress

SuperCompress v2 — cut ~64% of LLM input tokens for coding agents, without losing the answer.

~400M Neural Keep on the SuperCompress API scores bulky context (files, logs, tool dumps, pastes) against the current question and drops the rest. Your ask stays intact. This package wires Cursor / Claude Code / Codex / 60+ harnesses into that API via MCP + hooks.

Website · Benchmarks · Playground · Docs

Install

bash
npm install -g supercompress-proxy

Requires Node.js 18+.

Quick start (recommended)

One command links your account and auto-adds MCP + hooks across 60+ harnesses (25+ get a native auto MCP plugin — Cursor, Claude Code, Codex, Goose, Zed, OpenCode, fx, Hermes, OpenClaw, Grok, Gemini, Windsurf, Continue, and more):

bash
supercompress setupsupercompress doctor

Then restart your agent so integrations reload. That’s it.

Re-detect later (new agent installed, etc.):

bash
supercompress pluginsupercompress agentssupercompress doctor

Any other agent (custom harness, closed-source, DIY):

bash
supercompress agents connect

That prints a stdio MCP snippet and writes an Agent Plugins 1.0 pack you can drop into any compatible client.

Benchmarks

Same keep-budget (35% of tokens kept). Who still has the answer?

MethodAnswer-critical kept
FIFO / truncation24.8%
Summarization60.5%
H2O97.9%
SuperCompress100%
MetricResult
Oracle recall (fixed budget)100%
Mean token cut (real suite)~67%
Important lines kept (compiler)100%

Full methodology and charts: supercompress.dev/benchmarks

How it works

Your agent ──→ SuperCompress (hooks / MCP) ──→ smaller context ──→ model                      ↑                 query stays whole; only context is compressed
  1. You ask a question (never rewritten).
  2. Large context is scored against that question.
  3. Evidence-critical lines stay in original wording; filler drops.
  4. You pay for fewer input tokens.

Commands

CommandWhat it does
supercompress / tuiInteractive paper-branded UI (default in a TTY; Bun)
supercompress setupRecommended — link account, detect agents, install MCP + hooks
supercompress pluginRefresh agent integrations anytime
supercompress doctorPer-harness health matrix (account / MCP / hooks)
supercompress agents60+ catalog — auto-plugin vs recipe/connect
supercompress start / stop / statusOptional local proxy (setup --proxy)
supercompress usagePlan, quota, savings (--json ok)
supercompress uninstallRemove configs under ~/.supercompress

Optional localhost API proxy (base-URL rewrite) if you explicitly need it:

bash
supercompress setup --proxysupercompress start

Then point OpenAI/Anthropic-compatible clients at http://localhost:8080/v1.

MCP

setup / plugin registers the MCP server on every detected host. You can also run it directly:

bash
supercompress-mcp

Manual registration:

json
{  "mcpServers": {    "supercompress": {      "command": "supercompress-mcp"    }  }}
ToolPurpose
compress_contextCompress bulky context for a query
connect_accountLink this install to your dashboard
usage_summarySavings for the connected account

Account & pricing

Launch promo: 5M tokens/month free, then $0.10 / 1M from the dashboard.

Privacy

Hooks / MCP run on your machine. Provider API keys stay with your agent. Context text is sent to the SuperCompress API so the hosted compiler can compress it.

More

License

MIT — see LICENSE.

Source: packages/proxy/README.md at commit 08a34db

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.5.38LatestOct 3, 2026