caprock 0.1.8

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?

caprock wrap claude picks the backend from your environment:

Your setup	What happens
CLAUDE_CODE_USE_BEDROCK=1 or an AWS profile	signs Bedrock with your creds
ANTHROPIC_API_KEY set	routes to the Anthropic API
Plain Claude subscription (Pro/Max, no env key)	add the flag: caprock wrap claude --anthropic — auto-detect reads env vars and can't see a subscription yet

Tip: alias claude='caprock wrap claude' (add --anthropic if you're on a subscription) — every session runs through caprock. Sessions started without wrap bypass caprock entirely.

Anything after caprock wrap claude 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 --anthropic --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

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	Opens the local savings dashboard

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.