caprock 0.1.13

Cut AWS Bedrock LLM spend from Claude Code — compression + prompt caching, on your machine.

caprock

Cut your Claude Code token bill — context compression + prompt caching, on your machine, with your own credentials. Works on AWS Bedrock (where it also fixes prompt caching that's silently broken) and on the direct Anthropic API. Nothing leaves your machine.

pipx install caprock         # macOS/Homebrew — smoothest (or: uvx caprock, or plain pip, Python 3.10+)
caprock wrap claude          # your Claude Code now runs through it
caprock stats                # see what you saved

Upgrades: pipx upgrade caprock / pip install -U caprock. Full install matrix + troubleshooting: https://caprock.dev/docs.

Which backend?

Say it explicitly and it always wins:

caprock wrap claude --bedrock                     # force AWS Bedrock (your AWS creds)
caprock wrap claude --bedrock --profile work      # …signing with a specific AWS profile
caprock wrap claude --anthropic                   # force the direct Anthropic API

--profile <name> picks which AWS profile signs Bedrock (it implies --bedrock); without it caprock uses your AWS_PROFILE / default profile — the startup line tells you which one it picked. --region picks the Bedrock region (default us-east-1 or your AWS_REGION).

With no flag, caprock wrap claude auto-detects from your environment:

Your setup	What happens
CLAUDE_CODE_USE_BEDROCK=1	signs Bedrock with your creds
ANTHROPIC_API_KEY set	routes to the Anthropic API
Plain Claude subscription (Pro/Max, no env key)	routes to the Anthropic API — detected via your Claude login
None of the above	Bedrock (the default)

Whichever way it's chosen, the session's first line states it explicitly — you never have to guess what you're running on:

Backend: AWS Bedrock — profile “work” · region us-east-1
Backend: Anthropic API — your ANTHROPIC_API_KEY (…1234)
Backend: Anthropic subscription — logged in as [e-mail]

The subscription line comes from Claude Code's own login (the account email in ~/.claude.json) — caprock never reads tokens or your keychain.

The backend and profile are baked in when the proxy starts. If a caprock proxy is already running (another wrapped session), your flags apply only once it's gone — exit the other session, or use a different --port.

Tip: alias claude='caprock wrap claude' — every session runs through caprock. Sessions started without wrap bypass caprock entirely.

Anything after caprock wrap claude that isn't a caprock flag (--bedrock, --anthropic, --profile, --region, --port) is passed straight through to Claude Code itself, so its normal flags work unchanged, e.g.:

caprock wrap claude --dangerously-skip-permissions
caprock wrap claude --bedrock --profile work --dangerously-skip-permissions
caprock wrap claude --resume

Never run caprock wrap with sudo — it doesn't need root, and running it once as root can leave ~/.caprock files owned by root that your normal user can no longer write to.

Every session ends with the money you saved:

💰 You've saved $19.20 with caprock
   6,400,000 tokens cut · −85% input cost · 40 requests
   this month: $19.20 so far → ~$74/mo at this pace

On a Claude subscription (Pro/Max) caprock is honest about the money: your plan is flat-rate, so the summary shows the real tokens cut plus an API-price comparison explicitly labeled notional — lighter usage against your plan's limits, not cash saved:

💰 caprock cut 6,120,000 tokens on your Claude subscription
   −90% input · 158 requests — easier on your plan's usage limits
   at API prices that's $20.40 → $2.04 (−$18.36) — notional: your subscription is flat-rate

Bedrock and API-key traffic keeps the real dollar line; a mixed history shows the two separately, never blended into one figure.

Measured live against real Bedrock: −48% billed input on a clean install, −59.7% re-confirmed on a six-turn agent session, up to −70% with the full pipeline. On the direct Anthropic API (compression only — caching already works there): up to −55% on tool-heavy JSON. Your number will vary with your workload — run caprock measure to see yours. How we got these: https://caprock.dev/methodology.

What it does

• Compression — shrinks tool outputs / logs / JSON before they reach the model.
• Prompt caching — makes Bedrock's prompt cache actually engage (stock Headroom's markers die in conversion → 0% on Bedrock; caprock fixes that).
• Savings meter — caprock stats and the end of every wrap session show what you saved, computed locally from real Bedrock cache tokens.
• Runs on localhost, signs with your Bedrock credentials. No caprock service in the request path — nothing leaves your machine.

Commands

Command	What it does
caprock wrap claude	Runs Claude Code through the local proxy on your own creds
caprock start	Starts the proxy on its own (point any client at it)
caprock stats	Shows what you've saved (cache + compression, all time)
caprock measure	Replays a workload direct vs through caprock — your own number
caprock dashboard	The team-tier dashboard (per-user & per-role spend, in your VPC)

Team?

Running Claude across a team? The managed tier is a shared in-VPC gateway with per-user / per-role cost attribution, a team dashboard, deployment and support — deployed inside your own AWS account, nothing leaves your VPC. Pricing and a 20-min call: https://caprock.dev/pricing.

Built on Headroom

caprock builds on the open-source Headroom project (Apache 2.0). It applies the general-purpose fixes that make caching and compression work on AWS Bedrock (contributed back upstream) over the stock headroom-ai package. Licensed Apache-2.0.