Skip to content
Cavemandocs

docs.caveman.so

Documentation for the parts of Caveman you run yourself.

Caveman is an efficiency stack for AI agents. Four layers sit between your agent and the bill it generates. Three of them run on your machine and are open. This site documents those, and says plainly what each one can and cannot prove.

The stack, bottom to top. Everything below the network boundary runs locally and needs no account.

in one picture

What happens to a request

The skill shapes what the agent writes. The engine reduces what leaves. The dashed path is the part that makes the rest safe: anything the engine removed can be fetched back exactly.

Your agentClaude Code, Cursor, yoursSkilldecides what to sendEnginecompresses the payloadProviderthe model APIthis is what you pay forthe agent asks for what was left outMemorywhat you never resend
One request, left to right. The dashed path is recovery: the agent can ask for anything the engine left out.

get going

First three pages

by layer

Everything, in stack order

Each layer is independent. Nothing above one is required by the one below it.

the part worth reading twice

What the numbers are allowed to say

Every local tool reports inferred, meaning a per-run estimate computed on your machine. Nothing here can emit verified, and no setting changes that.

for agents

This site is readable without a browser

Every page is also plain text. You do not need to parse the HTML, and there is no separate copy to go stale: the Markdown is generated from the same source the page renders from.

/llms.txt
Every page with a one-line summary, grouped by layer.
/llms-full.txt
The full text of the whole site in one file.
/docs/engine.md
Any page as plain Markdown. Append .md to the path.
/sitemap.xml
Machine-readable index of everything that exists.

the fine print, up front

Licensing and telemetry