Caprock

See, steer, and orchestrate every Claude Code session on your machine.

# macOS / Linux
brew install dspv/tap/caprock

# Windows
scoop bucket add dspv https://github.com/dspv/scoop-bucket
scoop install caprock

caprock up        # opens localhost:4173; offers to set up hooks + plan-limit status line

Have Go? go install github.com/dspv/caprock/cmd/caprock@latest — the dashboard is embedded, so it works with no Node build. No package manager? Grab a binary from Releases.

Coming from the old Python caprock? Remove it first.

There was an earlier, unrelated Caprock on PyPI — a command-line stats tool that read Claude Code usage from a proxy. This one is a Go binary with a dashboard and shares nothing with it: different data, different install, same name. Remove the old one so the two caprock commands don't shadow each other:

pipx uninstall caprock || pip uninstall -y caprock   # whichever you used
rm -rf ~/.caprock                                    # its old data
which caprock                                        # should now print nothing

Then install as above. Nothing is lost: this version reads the transcripts Claude Code already writes, so your whole history appears on first run — no migration, no import. (Only ~/.caprock/savings.jsonl from the old tool is dropped; copy it elsewhere first if you want to keep those numbers.)

On first run `caprock up` asks before adding its hook and status-line entries to `~/.claude/settings.json` (it backs the file up and never touches your other settings). Say no and it still reads your history from transcripts.

Left: what every session is doing, as it happens. Right: what each repo costs you. Real numbers from a real machine.

Updating

Use the command that matches how you installed it:

brew upgrade caprock                                    # Homebrew
scoop update caprock                                    # Scoop
go install github.com/dspv/caprock/cmd/caprock@latest   # go install

Then restart the daemon so the new binary is the one running:

caprock down && caprock up

caprock down stops the daemon and leaves your database alone — nothing is lost, and history from before the upgrade stays exactly where it was. Check what you ended up on with caprock status.

Caprock can also tell you when a release is out: turn on release checks from the banner on the Now screen, or on the status page. That is the only outbound call it makes, it is off until you switch it on, and it sends nothing about you. It never installs anything by itself — it shows the one command above for your install method, and you run it.

Downloaded the binary directly? Replace it with a fresh one from Releases and restart.

What it is

Claude Code runs in your terminal. Caprock is the window into it. One local binary. Your data never leaves your machine.

Why

• See it — live activity, tokens, cost, and loop alerts per session, plus what each repository costs you and who is working in it.
• Find what Claude said — the reasoning and the "here's what changed, here's what I still need from you" that otherwise lives only in terminal scrollback, searchable across every session.
• Know what it's worth — your measured usage priced at the API rate, against what your plan actually costs.
• Steer it — spawn, pause, and kill sessions from the dashboard.
• Trust it — orchestrate agents that finish only when the tests pass.
• Local-first — loopback only, no servers, no telemetry, no account. The one thing that can reach the network is an optional check for new releases, off until you turn it on.

What your usage is actually worth — the same work priced at the API rate, against what your plan costs. Nobody else tells you this number:

And everything you have ever run through it — measured, not estimated:

How it works

• Observe — watches every claude session via hooks + transcripts.
• Control — run and drive sessions from the browser.
• Orchestrate — a verified multi-agent team; a task is done only when green.

Nothing to change in your workflow — it starts by watching the sessions you already run.

Get involved

• ⭐ Star it if it's useful — it helps others find it.
• 🐛 Hit a bug? Open an issue.
• 🤝 Contribute — see CONTRIBUTING.md.

A team version (shared dashboards, multi-user orchestration) is on the roadmap. Star to follow along.

More

Docs · Changelog · Releasing · Code of Conduct · Security · Apache-2.0

_{Building with an AI agent? Start at CLAUDE.md.}

Project map

This repo (dspv/caprock) is the home of the Caprock binary and its docs. The rest of the project:

Where	What
caprock.dev	Website — landing, install guide, changelog
dspv/homebrew-tap	Homebrew formula (macOS / Linux) — brew install dspv/tap/caprock
dspv/scoop-bucket	Scoop bucket (Windows) — scoop install caprock
Releases	Prebuilt binaries for every OS/arch

The Homebrew formula and Scoop manifest are generated and pushed from here on each release (docs/RELEASING.md); the website lives in its own repo and deploys to caprock.dev.