Metadata-Version: 2.4
Name: caprock
Version: 0.1.6
Summary: Cut AWS Bedrock LLM spend from Claude Code — compression + prompt caching, on your machine.
Author: Cybrix LLC
License: Apache-2.0
Project-URL: Homepage, https://caprock.dev
Keywords: aws,bedrock,claude,claude-code,llm,cost,compression,prompt-caching,headroom
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Utilities
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: headroom-ai[proxy]>=0.30.0
Requires-Dist: boto3
Requires-Dist: httpx
Requires-Dist: click>=8
Provides-Extra: dev
Requires-Dist: pytest>=8; extra == "dev"

# 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.

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

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. 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](https://github.com/headroomlabs-ai/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.
