Overview

Caveman makes agents cheaper to run. It is not one program and not a framework you commit to. It is a short list of separate things, each of which you can adopt on its own and remove on its own.

There are two repositories and one hosted plane. Knowing which is which is most of what you need to navigate this site.

caveman

Makes an agent you already use cheaper. The skill, the proxy and the compression engine inside it, memory, and the adoption surfaces: CLI, SDKs, MCP server.

agent-sdk

Builds a new agent that is efficient by construction. A separate repository and a separate install. It does not need the proxy.

Caveman Cloud

The managed plane, across a network boundary. The only paid part, and the only place a number can be verified against a bill.

caveman: make an existing agent cheaper#

Everything in this repository runs on your machine and needs no account. The four rows below are the operating stack, bottom to top. Each one answers a different question, and each fails on its own.

03CloudWhat a fleet can put in front of financeCommercial

network boundary

02MemoryWhat you never have to send twiceBSL 1.1

01ProxyWhat the payload weighs when it leavesBSL 1.1

00SkillWhat the agent does before it calls outMIT

your machine

00 Skill#

A skill is a persistent instruction set your coding agent reads before it answers. It cuts filler, narration and hedging out of the agent's own output, and it is explicit about what it must never touch: code blocks, function names, CLI commands and exact error strings stay byte for byte.

It costs nothing to run because it is not software. It is text your agent already reads.

01 Proxy#

The proxy is a reverse proxy on loopback. You point an agent at 127.0.0.1:8787 instead of the provider, it keeps your key, and it shrinks the context on the way out.

The compressor doing that shrinking is the engine. It detects what a payload is, routes it to a compressor built for that shape, and stores the original bytes under a content-addressed handle before it removes anything. If the agent needs what was dropped, it asks for the handle and gets the original back exactly. The engine is not a separate product and not a separate install; it is documented inside the proxy, because the proxy is how you actually run it.

02 Memory#

cavemem holds the context you would otherwise paste into every session. It stores text once, recalls the parts a question actually needs, and compresses each hit on the way out.

03 Cloud#

Caveman Cloud is the managed plane. It is where a fleet's numbers stop being local estimates and become something a finance team can read. It is in private development and the waitlist is open.

Build with it#

The same capabilities as a CLI, a TypeScript or Python SDK, an MCP server, and two standalone commands: caveman-shrink for command output and caveman-browse for web pages. These are the MIT adoption surfaces. Reach for them when you want the behaviour without a proxy hop.

agent-sdk: build a new agent#

The Agent SDK is the other direction. Rather than making an existing agent's traffic smaller, it is how you write an agent whose context, tools and budget are declared up front, so a turn cannot quietly exceed them.

An agent is one frozen definition: context, output schema, filesystem, tools, and subagents. You run a turn against it and get a receipt rather than a vibe. Evals gate the build, so a failed eval never produces a lock. Compaction is a fail-closed ladder inside a declared budget: recover, summarise, clamp, then stop.

It lives in its own repository, ships as its own package, and shares no runtime with the proxy. You can use either without the other.

What the numbers mean#

Every local tool on this site reports inferred. That word is load bearing. It means a per-run estimate computed on your machine from an offline token counter, and it is never turned into a monthly figure or a dollar amount.

No tool in either repository can emit verified. That label is reserved for hosted rollout systems that can compare against a real bill.

Where to go next#