Skip to content
Cavemandocs
MIT

Install

Build 0.2 from source, run doctor, and the gap with the npm 0.1 package.

The documented surface is @caveman-ai/agent 0.2 in source. npm currently publishes 0.1.0, which is an older API. Clone the repository if you are following these pages.

Node
22.19 or newer.
CLI binary
caveman-agent
Source
JuliusBrussee/agent-sdk
npm today
@caveman-ai/agent@0.1.0

Build 0.2 from source#

terminal
git clone https://github.com/JuliusBrussee/agent-sdk.git
cd agent-sdk
npm ci --prefix packages/pebble-protocol
npm ci --prefix packages/agent
npm ci --prefix packages/create-caveman-agent
npm --prefix packages/agent run build

The package binary is caveman-agent, from packages/agent. After the build you can run it with node packages/agent/dist/cli.js, or link the package into a project that depends on @caveman-ai/agent@0.2.0.

A full repository test pass is npm test at the repo root. Restricted macOS sandbox and loopback tests need host permissions before a failure counts as a product defect.

Check the machine before a provider call#

terminal
caveman-agent doctor
caveman-agent doctor --json

Doctor makes no model request. Human output prints verified savings: $0.

CheckPassWarnFail
node22.19 or newerolder Node
sandboxcontainment probe passedprobe failed
enginetransform registry loadedengine missing; observe-only still works
runtime_clicaveman CLI answers versionCLI missing; observe-only still works
gatewaylocal runtime reachablenot reachable; telemetry off, observe-only
projectcaveman.config.ts loadsno config in this directoryconfig, entry, eval, or context error
locklock is currentno lock; unlocked runs are finelock drift
providerselected model has a credentialno model, or several credentials and no CAVE_MODELbad CAVE_MODEL or provider.json

Missing engine, runtime CLI, or local runtime is a warning and doctor still exits 0, because observe-only runs still reach a real model. Broken sandbox containment, invalid config, or lock drift fails.

Optional local engine:

terminal
npm install -g @caveman-ai/cli
caveman start

The Agent SDK accepts a loopback runtime only after identity, process state, and executable ownership check out. An unrelated listener on the same port does not receive provider credentials; the run goes direct in observe-only mode.

CLI#

terminal
caveman-agent --help
caveman-agent --version
caveman-agent doctor [--json]
caveman-agent dev [entry] [prompt]
caveman-agent build [config] [--verbose] [--accept-prefix-shrink]
caveman-agent check [config]
caveman-agent register
caveman-agent connect

dev watches the project and reuses one staged source snapshot until source, config, eval, or file context changes. build and check own Cave Build execution. register is a separate command; it is not a substitute for build.

A generated project wires the same commands through npm scripts: npm run doctor, npm run dev, npm run build, npm run check.

npm 0.1.0#

terminal
npm install @caveman-ai/agent

That installs 0.1.0 today. These pages describe 0.2 source. Do not treat a registry install as the surface documented here until 0.2 is published.

What it will not do#

Doctor does not spend a provider call, and a green doctor is not a lock. Observe-only is a valid run mode, not a broken install. Linking @caveman-ai/cli is optional; without it the SDK still calls your provider.