FAQ · Updated 2026-10-09
SuperCompress FAQ
Short answers to the questions people ask most about SuperCompress, for coding agents and for apps.
npm install -g supercompress-proxy && supercompress setup.
What is SuperCompress?
Hosted context compression for coding agents and LLM apps. You send a large context (tool output, logs, diffs, file reads, retrieved documents) together with the current question, and our Neural Keep model keeps the original lines that answer it and drops the rest.
How do I install SuperCompress for my coding agent?
Run npm install -g supercompress-proxy && supercompress setup. Setup links your account in the browser, detects the coding agents on the machine and wires each one. Run supercompress doctor to check.
Which coding agents does it work with?
Claude Code, Cursor, Codex, Hermes Agent, Windsurf, Gemini CLI, Cline, Roo Code, Kilo Code, OpenCode, Zed, Goose, Continue and more. See the coding agent guides.
Is SuperCompress a summarizer?
No. It is extractive. Every kept line is copied from the original, so error messages, IDs, paths and code come through unchanged.
What does query-aware mean?
The same log or file can be compressed differently for different questions. SuperCompress scores each block against the current question and keeps what answers it. The question itself is never compressed.
Does SuperCompress change my agent's login or model?
No. It works through an MCP server, instructions and, for some agents, hooks. Your agent keeps its normal sign-in and talks to its own models.
Is SuperCompress a proxy or gateway?
No. It is not an LLM, a gateway, a router or a cache. It runs before your model call and returns plain text, so it works with any model provider.
What MCP tools does it add?
compress_context (arguments context and query), connect_account and usage_summary.
How do I see what was removed?
Every compress response reports original_tokens and kept_tokens, plus kept and dropped blocks. usage_summary shows totals per agent.
Can I call it from my own app?
Yes. Send POST https://www.supercompress.dev/api/v1/compress with context and query, and an API key from the dashboard in the X-API-Key header. There is also a Python client: pip install supercompress.
How is it different from RTK or Headroom?
RTK filters known shell commands before the agent reads them. Headroom is a proxy that rewrites requests on the way to the model. SuperCompress works on one bulky result at a time against the current question and keeps original lines. See approaches compared.
When should I not use it?
When the prompt is already small, when a file is about to be edited line by line, or when every byte must pass through unchanged for compliance.
How do I uninstall it?
Run supercompress uninstall. It removes only the entries SuperCompress added.
Where is pricing?
Current plans and your free allowance are shown in the dashboard.