-
Notifications
You must be signed in to change notification settings - Fork 4.5k
feat: add Ocultar PII Refinery extension #8867
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
Edu963
wants to merge
4
commits into
aaif-goose:main
Choose a base branch
from
Edu963:add-ocultar-pii-extension
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+208
−0
Open
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
8dbfdc5
feat: add Ocultar PII Refinery extension
Edu963 56b278f
docs: add ocultar-pii-mcp tutorial to fix 404 on extension docs link
Edu963 e355740
docs: normalize goose branding to lowercase per AGENTS.md style guide
Edu963 e867431
docs(ocultar-pii): add clone/cd context before docker compose step
Edu963 File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,184 @@ | ||
| --- | ||
| title: Ocultar PII Refinery Extension | ||
| description: Add zero-egress PII detection and redaction to your goose workflows | ||
| unlisted: true | ||
| --- | ||
|
|
||
| import Tabs from '@theme/Tabs'; | ||
| import TabItem from '@theme/TabItem'; | ||
| import GooseDesktopInstaller from '@site/src/components/GooseDesktopInstaller'; | ||
|
|
||
| This tutorial will get you started with the [Ocultar PII Refinery](https://github.com/Edu963/ocultar) as a goose extension. Ocultar detects and tokenizes personally identifiable information — names, emails, IBANs, phone numbers, addresses and more — in-place before any text reaches an upstream API. No raw PII ever leaves your infrastructure. | ||
|
|
||
| :::info Prerequisites | ||
| You need a running Ocultar instance before using this extension. The fastest way: | ||
| ```sh | ||
| docker compose -f docker-compose.community.yml up | ||
| ``` | ||
| See the [Ocultar repository](https://github.com/Edu963/ocultar) for full setup instructions. | ||
| ::: | ||
|
|
||
| :::tip Quick Install | ||
| <Tabs groupId="interface"> | ||
| <TabItem value="ui" label="goose Desktop" default> | ||
| [Launch the installer](goose://extension?cmd=uvx&arg=ocultar-goose-mcp&id=ocultar-pii&name=Ocultar%20PII%20Refinery&description=Zero-egress%20PII%20detection%20and%20redaction&env=OCULTAR_URL%3Dhttp%3A%2F%2Flocalhost%3A8080) | ||
| </TabItem> | ||
| <TabItem value="cli" label="goose CLI"> | ||
| **Command** | ||
| ```sh | ||
| uvx ocultar-goose-mcp | ||
| ``` | ||
| </TabItem> | ||
| </Tabs> | ||
| **Environment Variables** (both optional) | ||
| ``` | ||
| OCULTAR_URL: http://localhost:8080 # URL of your Ocultar instance | ||
| OCULTAR_API_KEY: <your-key> # Only required for authenticated deployments | ||
| ``` | ||
| ::: | ||
|
|
||
| ## Configuration | ||
|
|
||
| :::info | ||
| You need [uv](https://docs.astral.sh/uv/getting-started/installation/) installed on your system to run this command, as it uses `uvx`. | ||
| ::: | ||
|
|
||
| <Tabs groupId="interface"> | ||
| <TabItem value="ui" label="goose Desktop" default> | ||
| <GooseDesktopInstaller | ||
| extensionId="ocultar-pii" | ||
| extensionName="Ocultar PII Refinery" | ||
| description="Zero-egress PII detection and redaction" | ||
| command="uvx" | ||
| args={["ocultar-goose-mcp"]} | ||
| envVars={[ | ||
| { name: "OCULTAR_URL", label: "Ocultar instance URL (default: http://localhost:8080)" }, | ||
| { name: "OCULTAR_API_KEY", label: "API key (only for authenticated deployments)" } | ||
| ]} | ||
| /> | ||
| </TabItem> | ||
| <TabItem value="cli" label="goose CLI"> | ||
| 1. Run the `configure` command: | ||
| ```sh | ||
| goose configure | ||
| ``` | ||
|
|
||
| 2. Choose to add a `Command-line Extension` | ||
| ```sh | ||
| ┌ goose-configure | ||
| │ | ||
| ◇ What would you like to configure? | ||
| │ Add Extension (Connect to a new extension) | ||
| │ | ||
| ◆ What type of extension would you like to add? | ||
| │ ○ Built-in Extension | ||
| // highlight-start | ||
| │ ● Command-line Extension (Run a local command or script) | ||
| // highlight-end | ||
| │ ○ Remote Extension (Streamable HTTP) | ||
| └ | ||
| ``` | ||
|
|
||
| 3. Give your extension a name | ||
| ```sh | ||
| ┌ goose-configure | ||
| │ | ||
| // highlight-start | ||
| ◆ What would you like to call this extension? | ||
| │ ocultar-pii | ||
| // highlight-end | ||
| └ | ||
| ``` | ||
|
|
||
| 4. Enter the command | ||
| ```sh | ||
| ┌ goose-configure | ||
| │ | ||
| // highlight-start | ||
| ◆ What command should be run? | ||
| │ uvx ocultar-goose-mcp | ||
| // highlight-end | ||
| └ | ||
| ``` | ||
|
|
||
| 5. Set the timeout (default 300s is fine) | ||
| ```sh | ||
| ┌ goose-configure | ||
| │ | ||
| // highlight-start | ||
| ◆ Please set the timeout for this tool (in secs): | ||
| │ 300 | ||
| // highlight-end | ||
| └ | ||
| ``` | ||
|
|
||
| 6. Add environment variables if your Ocultar instance is not on `localhost:8080` | ||
| ```sh | ||
| ┌ goose-configure | ||
| │ | ||
| // highlight-start | ||
| ◆ Would you like to add environment variables? | ||
| │ Yes | ||
| │ | ||
| ◇ Environment variable name: | ||
| │ OCULTAR_URL | ||
| │ | ||
| ◇ Environment variable value: | ||
| │ http://localhost:8080 | ||
| │ | ||
| ◇ Add another environment variable? | ||
| │ No | ||
| // highlight-end | ||
| └ Added ocultar-pii extension | ||
| ``` | ||
| </TabItem> | ||
| </Tabs> | ||
|
|
||
| ## Example Usage | ||
|
|
||
| The Ocultar PII Refinery extension exposes a single `refine_text` tool. goose calls it automatically when you ask it to sanitize or redact content before sending it anywhere sensitive. | ||
|
|
||
| #### goose Prompt | ||
|
|
||
| ``` | ||
| ( O)> I need to send this support ticket to our AI summarizer, but it contains customer PII. | ||
| Redact it first: "Hi, I'm Jean-Pierre Dumont, my email is jp.dumont@societe-generale.fr | ||
| and my IBAN is FR76 3000 6000 0112 3456 7890 189. I have a billing issue." | ||
| ``` | ||
|
|
||
| #### goose Output | ||
|
|
||
| ``` | ||
| I'll redact the PII from that ticket before it goes anywhere. | ||
|
|
||
| refine_text | ||
| input: "Hi, I'm Jean-Pierre Dumont, my email is jp.dumont@societe-generale.fr | ||
| and my IBAN is FR76 3000 6000 0112 3456 7890 189. I have a billing issue." | ||
|
|
||
| Redacted result: | ||
|
|
||
| "Hi, I'm [PERSON_181bc039], my email is [EMAIL_b227fb2b] and my IBAN is | ||
| [IBAN_72eb0d24]. I have a billing issue." | ||
|
|
||
| 3 PII tokens detected and replaced: | ||
| - PERSON_181bc039 → name | ||
| - EMAIL_b227fb2b → email address | ||
| - IBAN_72eb0d24 → French IBAN | ||
|
|
||
| The sanitized text is safe to forward. Tokens are stored encrypted in your | ||
| local Ocultar vault and can be re-hydrated by authorized callers only. | ||
| ``` | ||
|
|
||
| ## What Gets Detected | ||
|
|
||
| Ocultar's community tier runs five detection layers with no external API calls: | ||
|
|
||
| | Layer | What it catches | | ||
| |---|---| | ||
| | Dictionary shield | Named entities from your protected list | | ||
| | Pattern + entropy | High-entropy strings, secrets, tokens | | ||
| | Regex rules | Email, SSN, phone, credit card, IBAN, passport | | ||
| | Phone validator | International numbers via libphonenumber | | ||
| | Address heuristics | Street addresses across formats | | ||
|
|
||
| Enterprise tier adds a Tier 2 AI scanner (local SLM) for contextual name and entity detection. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.