caprock 0.1.4

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

caprock

Cut your AWS Bedrock LLM spend from Claude Code — context compression + prompt caching that actually work on Bedrock, on your machine, with your own credentials. Nothing leaves your machine.

pip install caprock          # or: uvx caprock
caprock wrap claude          # your Claude Code now runs through it
caprock stats                # see what you saved

Measured live against real Bedrock: ~48% fewer billed input token-equivalents on a tool-heavy Claude Code workload (your number will vary — run caprock measure to see yours).

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).
• Runs on localhost, signs with your Bedrock credentials. No caprock service in the request path.

Team?

A shared in-VPC gateway with per-user / per-role cost attribution, a team dashboard, and support is the managed tier → https://caprock.dev

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.