Metadata-Version: 2.4
Name: cloakroom
Version: 0.1.0
Summary: Local privacy gate for AI coding agents: secrets and PII are masked before the model sees them, restored only for local tools.
Author: The Cloakroom authors
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/shanjeevrajendran/cloakroom
Project-URL: Issues, https://github.com/shanjeevrajendran/cloakroom/issues
Project-URL: Benchmark, https://github.com/shanjeevrajendran/cloakroom/blob/main/bench/RESULTS.md
Keywords: privacy,pii,secrets,redaction,claude-code,ai-agents,dlp
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Operating System :: MacOS
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Security
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
License-File: NOTICE
Requires-Dist: cryptography>=42
Requires-Dist: keyring>=24
Provides-Extra: model
Requires-Dist: onnxruntime>=1.20; extra == "model"
Requires-Dist: tokenizers>=0.20; extra == "model"
Requires-Dist: numpy; extra == "model"
Requires-Dist: huggingface_hub; extra == "model"
Provides-Extra: torch
Requires-Dist: torch>=2.5; extra == "torch"
Requires-Dist: transformers>=5.2; extra == "torch"
Requires-Dist: safetensors; extra == "torch"
Requires-Dist: huggingface_hub; extra == "torch"
Dynamic: license-file

<div align="center">

<img src="assets/hero.svg" alt="Cloakroom, a privacy layer for Claude Code. v0.1 benchmark on five fresh test sets: 0 of 1,005 personal data values leaked, 4 of 334 secrets and IDs leaked, 60 of 200 safe samples masked by mistake." width="880">

<p>
  <a href="#get-started">Get started</a> ·
  <a href="#results">Results</a> ·
  <a href="#how-it-works">How it works</a> ·
  <a href="#faq">FAQ</a> ·
  <a href="docs-LIMITS.md">Known limits</a>
</p>

</div>

Names, emails, addresses and API keys in the files Claude reads are swapped
for placeholders before the model sees them. When Claude writes a file, the real values go back in, on your machine.
Runs on macOS, Windows and Linux.

**Status:** v0.1. Tested on macOS and a real Windows machine (Linux in CI). It works; expect rough edges.

<div align="center">
  <img src="assets/demo.gif" alt="Claude Code reads a support ticket and .env through Cloakroom: the model sees PII_PERSON_1 and PII_SECRET_1, and reply.md on disk gets the real customer name back" width="820">
  <br><sub>Claude sees <code>PII_PERSON_1</code>. The reply it writes lands on your disk as "Hi Nadia Petrov".</sub>
</div>

## Why

Claude Code reads whatever your task touches: `.env` files, logs, customer exports, support tickets. All of it
goes to the model. Secret scanners catch keys with a known shape, but a customer's name in a ticket or an address
in a log looks like ordinary text to a regex.

## What's different

- **Catches personal data, not just keys.** A local detection model plus rules. Across five fresh test sets it
  leaked none of 1,005 planted names, emails, phone numbers, addresses and birth dates. The other tools we tested
  let 119 to 992 of them through.
- **Claude keeps working.** Placeholders stay the same for the whole session, and the real values are put back
  when Claude writes a file or runs a command locally.
- **Runs on your machine.** Detection, the encrypted vault and the restore are all local. The only network call is
  the one-time model download.
- **Cross-platform.** One install on all three, with the vault key in each system's own secure store:
  - **macOS:** Keychain. On Apple Silicon the model runs on the built-in GPU, about 20 ms per check.
  - **Windows:** Credential Manager, hooks that run in PowerShell, tested on a real Windows machine.
  - **Linux:** Secret Service, covered by CI on every change.
- **No GPU needed.** On an Apple M-series CPU a check takes about 60 ms.
- **Catches encoded dumps.** `base64`, `xxd` and `od` output is decoded and checked too.
- **Fails closed.** If Cloakroom can't run, prompts are blocked and tool calls denied instead of slipping through.

## How it works

```
  Claude Code reads a file or runs a tool
        │   "Nadia Petrov called about…"    sk_live_51Hx9Q…
        ▼
  ┌────────────────────────────────────────────┐
  │ Cloakroom  (on your machine)               │
  │   rules + local model  ->  find the values │
  │   encrypted vault      ->  remember them   │
  └────────────────────────────────────────────┘
        │   "PII_PERSON_1 called about…"    PII_SECRET_1
        ▼
  the model works with placeholders only
        │   Write reply.md: "Hi PII_PERSON_1,"
        ▼
  Cloakroom puts the real value back, locally
        │
        ▼
  reply.md on your disk: "Hi Nadia Petrov,"
```

Details: [docs-HOW-IT-WORKS.md](docs-HOW-IT-WORKS.md).

## Get started

```bash
# 1. Install
uv tool install "cloakroom[model]"        # or: pipx install "cloakroom[model]"

# 2. Check this machine: Python, the key store, the model and the service
cloakroom doctor
```

```
# 3. Add the plugin, inside Claude Code
/plugin marketplace add shanjeevrajendran/cloakroom
/plugin install cloakroom@cloakroom
```

Python 3.10+. GPU and CPU backends, Windows notes and a rules-only mode: [docs-SETUP.md](docs-SETUP.md).

## Results

Cloakroom and four other Claude Code redaction tools, default settings, the same synthetic agent traffic,
offline. Five fresh test sets, written by a different model and each run once before any tuning on it: 1,575
planted values to catch and 200 safe samples that should be left alone.

| Tool | Personal data (1,005) | Keys, passwords, cards, IDs (334) | False alarms (200 safe samples) |
|---|---|---|---|
| **Cloakroom** | **0** | **4** | 60 |
| sensitive-canary (blocks the call instead of masking) | 119 | 40 | 16 |
| maisecrets | 557 | 97 | 21 |
| claude-code-redact, PII on | 607 | 101 | 31 |
| redact-hook | 817-822 | 143-157 | 35-40 |
| claude-code-redact, secrets only | 992 | 179 | 2 |

Some of these tools only aim at secrets, so their personal-data column shows scope as much as quality.
False alarms are Cloakroom's weak spot: it masked 60 of 200 safe samples, such as historical names, landmark
addresses and documented test keys. A false alarm costs you a placeholder where Claude needed the real text; a
miss sends the value to the model. Method and every run:
[bench/RESULTS.md](bench/RESULTS.md). The maintainers of the compared tools were contacted before publishing.

## FAQ

**Does it send my data anywhere?** No. It downloads the detection model once from Hugging Face (a pinned
version). Everything else runs on 127.0.0.1.

**How much slower is Claude?** Each tool call is checked by a small local service: about 20 ms on an Apple GPU,
60 ms on an Apple M-series CPU, 400 ms on a 2-core cloud VM. `cloakroom doctor` prints yours.

**Will it mask things it shouldn't?** Sometimes, see above. Documented examples (Stripe test cards,
`example.com`, fictional 555 numbers) are left alone, and you can add your own exceptions to `allow` in
`~/.cloakroom/config.json`. `cloakroom check FILE` shows what would be masked.

**What doesn't it protect?** It stops accidental exposure; it isn't a sandbox. Out of scope: a prompt injection
set on smuggling data out piece by piece, text you paste into a prompt on purpose (that gets blocked, not
rewritten), and Claude Code's own local logs. Details: [docs-LIMITS.md](docs-LIMITS.md).

**How do I remove it?** See [Uninstall](docs-SETUP.md#uninstall).

## More

- [How it works](docs-HOW-IT-WORKS.md): the detectors, the known-safe filter, the vault and the restore
- [Setup details](docs-SETUP.md) · [Known limits](docs-LIMITS.md) · [Benchmark](bench/RESULTS.md)

## Credits

Detection model: [PII-Tracer](https://huggingface.co/perplexity-ai/PII-Tracer). The one-string hook command that
runs in both bash and PowerShell comes from [maisecrets](https://github.com/Mcpgate-de/maisecrets) (Apache-2.0).
Licensed Apache-2.0.
