SuperCompress vs Caveman

Side by side

	Caveman	SuperCompress
What it optimizes	Model output (replies)	Input context (tool output, logs, files, MCP results, RAG)
How it decides	Terse output style	Query-aware extraction of original lines
Where it runs	Locally, as an agent skill or prompt	Hosted API, plus an MCP tool and hooks for coding agents
Setup	Install the skill for your agent	npm install -g supercompress-proxy && supercompress setup
Licence	Open source	Hosted service

Caveman

A. Caveman

Best if your main goal is shorter model replies and you do not mind the terse register.

A skill for coding agents that switches the model's replies to a terse, telegraphic style, cutting output tokens.

• How it works: Terse output style
• Runs: Locally, as an agent skill or prompt
• Setup: Install the skill for your agent
• Licence: Open source

Strengths:

• Near zero setup and footprint
• Works across many agents
• Easy to try and remove

Limitations:

• Only touches output; agent spend is usually dominated by input context
• Terse replies are not to everyone's taste
• Does nothing about big tool results or file reads

SuperCompress

B. SuperCompress (our product)

Best if your agent keeps pulling big tool results, logs or retrieved docs and only a few lines matter for the question at hand, and you want those lines kept verbatim.

Hosted, query-aware context compression. Your agent or app sends a bulky block (tool output, a log, a diff, a file read, an MCP result, retrieved docs) with the current question, and the hosted Neural Keep model keeps the original lines that answer it, word for word, and drops the rest.

• How it works: Query-aware extraction of original lines
• Runs: Hosted API, plus an MCP tool and hooks for coding agents
• Setup: npm install -g supercompress-proxy && supercompress setup
• Licence: Hosted service

Strengths:

• Keeps original lines verbatim, so error messages, paths, IDs and code survive exactly
• Query-aware: what is kept depends on the current question, not only on the content type
• One setup command wires an MCP tool into each detected coding agent (Claude Code, Cursor, Codex, Windsurf, Cline, Gemini CLI, OpenCode and more), plus hooks where supported
• HTTP API returns original_tokens and kept_tokens so you can measure on your own traffic
• Works with any model provider because the output is plain text

Limitations:

• Hosted: the context you compress is sent to the SuperCompress API
• Compresses input only; it does not change how verbose model replies are
• Not a code index or retrieval system; it shrinks what is already being sent

How to test any of these fairly

Every tool here, including ours, publishes its own numbers. Fewer tokens do not always mean a smaller bill once prompt caching, retries and extra agent turns are counted. Run the same tasks with and without a tool, check the tasks still succeed, and compare cost per finished task on your provider bill.

Disclosure: SuperCompress publishes this page and is listed first because it is ours. Every claim about other tools comes from their own docs or repositories as of 2026-10-31; tell us if anything is out of date and we will fix it.

See also: Caveman alternatives, all comparisons.

FAQ

Is SuperCompress better than Caveman?

They solve different parts of the problem. Best if your main goal is shorter model replies and you do not mind the terse register. Best if your agent keeps pulling big tool results, logs or retrieved docs and only a few lines matter for the question at hand, and you want those lines kept verbatim.

What is the main difference between SuperCompress and Caveman?

Caveman works on model output (replies) and runs locally, as an agent skill or prompt. SuperCompress works on input context and is hosted.

Can I use both?

Usually, if they act on different tokens. Measure cost per finished task with each on and off.

Get API key Coding agents guide All comparisons