Appearance
GhostClaw Configuration Guide
Already running OpenClaw? Add GhostClaw in minutes.
This guide assumes you have a working OpenClaw (2026.3.2+) installation. Pick the integration path that fits your needs — from a 2-minute JSON config change to a full plugin install with slash commands and privacy receipts.
Prerequisites
| Requirement | Details |
|---|---|
| OpenClaw | Version 2026.3.2 or later (openclaw --version) |
| GhostAI API key | Starts with gst_ — create one at Settings > API Keys in your GhostAI instance |
| NemoClaw (optional) | For sandbox policy enforcement |
Set your API key:
bash
export GHOSTAI_API_KEY="gst_your_key_here"Option A: Zero-Code Provider Config (3 min)
The fastest path. Edit your openclaw.json to route all LLM traffic through GhostAI:
json
{
"models": {
"providers": {
"ghostclaw": {
"api": "openai-completions",
"baseUrl": "https://your-ghostai-instance.com/v1",
"apiKey": "${GHOSTAI_API_KEY}",
"models": [
"openai/gpt-4o",
"openai/gpt-4o-mini",
"anthropic/claude-3.5-sonnet",
"anthropic/claude-3-haiku",
"google/gemini-1.5-pro"
]
}
}
}
}What happens: OpenClaw treats GhostAI as a standard OpenAI-compatible provider. Every message is PII-tokenized before the LLM sees it. Responses are automatically detokenized. Streaming works. No code changes, no plugins.
Select the provider in OpenClaw: When starting a conversation, choose "ghostclaw" from the model picker. All listed models route through GhostAI.
Limitations: No privacy receipts, no slash commands, no feedback badges. Protection is fully silent.
Option B: Zero-Code MCP Tools (2 min)
Add GhostAI's MCP tools so the agent can proactively scan text and files. This works alongside any provider — even without Option A:
json
{
"mcp": {
"ghostai": {
"command": "ghostai-mcp",
"env": {
"GHOSTAI_BASE_URL": "https://your-ghostai-instance.com",
"GHOSTAI_API_KEY": "${GHOSTAI_API_KEY}"
}
}
}
}Available tools:
| Tool | Description |
|---|---|
ghostai_detect_pii | Scan text, return entity types and locations |
ghostai_sanitize | Replace PII with reversible tokens |
ghostai_restore | Restore tokens to original values |
ghostai_scan_file | Deep-scan files (PDF, Office, archives, DICOM, etc.) |
Best combined with Option A: Provider config handles automatic protection; MCP tools add on-demand scanning for files and ad-hoc text.
Option C: Full Plugin Install (5 min)
The richest integration. Adds slash commands, onboarding wizard, privacy receipts, and agent tools:
bash
openclaw plugins install ghostclawRun the setup wizard:
/ghostclaw setupThe wizard validates your API key, lets you pick an industry vertical, and runs a test scan. After setup, you get:
- Privacy receipts on every message with PII
- 12 slash commands (
/ghostclaw status,scan,explain,config, etc.) - Agent tools the AI can call proactively
- Configurable feedback (auto/always/verbose/silent)
- failMode control (block/warn/pass)
Configuring Verticals
GhostClaw supports 9 industry verticals, each with specialized entity detectors and compliance tagging:
/ghostclaw config vertical healthcare| Vertical | Key Entities | Compliance |
|---|---|---|
general | Names, emails, phones, SSNs, credit cards | CCPA, GDPR |
healthcare | PHI, MRN, diagnosis codes, prescriptions | HIPAA §164.514 |
financial | Account numbers, routing, SWIFT, tax IDs | PCI-DSS, SOX, GLBA |
legal | Case numbers, privileged communications | Attorney-client privilege |
government | CUI markings, clearance levels, ITAR data | NIST 800-171, ITAR, EAR |
technology | API keys, secrets, source code, IPs | SOC 2, proprietary |
education | Student IDs, FERPA records, grades | FERPA |
retail | Loyalty numbers, purchase history | PCI-DSS, CCPA |
manufacturing | Trade secrets, formulations, patents | DTSA, proprietary |
Via JSON config (no plugin needed):
json
{
"mcp": {
"ghostai": {
"command": "ghostai-mcp",
"env": {
"GHOSTAI_BASE_URL": "https://your-ghostai-instance.com",
"GHOSTAI_API_KEY": "${GHOSTAI_API_KEY}",
"GHOSTAI_VERTICAL": "healthcare"
}
}
}
}Configuring Sensitivity
Control how aggressively GhostClaw detects PII:
/ghostclaw config sensitivity high| Level | Behavior |
|---|---|
low | Only high-confidence matches (>95%). Fewest false positives. |
medium | Balanced detection (>85%). Good default for most use cases. |
high | Aggressive detection (>70%). Catches more, may flag some non-PII. |
paranoid | Maximum detection (>50%). Use in regulated environments where false positives are acceptable. |
Configuring Feedback Mode
Control what you see after each protected message:
/ghostclaw config feedback auto| Mode | Behavior |
|---|---|
auto | Show badge only when PII was detected. Silent when clean. (default) |
always | Show badge on every message, including "0 items — clean". |
verbose | Show full entity breakdown automatically (Layer 2 summary). |
silent | No visible feedback. PII is still protected. |
Configuring failMode
What happens when GhostAI is unreachable:
/ghostclaw config failMode warn| Mode | Behavior | Best For |
|---|---|---|
block | Message is held — not sent to LLM. | Compliance-critical environments (healthcare, finance). |
warn | Message is sent unprotected. User sees a warning. (default) | Balanced usability and safety. |
pass | Message is sent silently without protection. | Non-sensitive use cases. Not recommended. |
NemoClaw: Adding GhostAI to Sandbox Policy
If you're using NemoClaw, add GhostAI as an allowed egress endpoint in your sandbox's policies/network.yaml:
yaml
version: "1.0"
egress:
default: deny
allow:
- host: "your-ghostai-instance.com"
port: 443
protocol: https
paths:
- "/v1/**"
- "/api/detect"
- "/api/pii/**"
methods: [GET, POST]
description: "GhostAI — mandatory privacy proxy"This ensures the agent cannot bypass GhostClaw. All inference must route through GhostAI.
Apply the policy:
bash
nemoclaw policy applyNemoClaw: Blueprint with GhostClaw Pre-Configured
For new sandbox environments, use the GhostClaw blueprint that bundles the plugin, provider config, and network policy:
bash
nemoclaw init my-agent --blueprint ghostclawThis creates a sandbox with:
- GhostAI as the only allowed inference gateway
- GhostClaw plugin pre-installed
- Provider config pointing at your GhostAI instance
- Network policy denying direct LLM access
API Key Management
Rotating keys
GhostClaw handles key rotation without restart. Update the environment variable and the next API call uses the new key:
bash
export GHOSTAI_API_KEY="gst_new_key_here"Or update via the wizard:
/ghostclaw setupKey security
- Keys are stored in OpenClaw's encrypted credential store (plugin) or environment variables (zero-code)
- Never commit
gst_keys to version control - Use
${GHOSTAI_API_KEY}variable references inopenclaw.json, not literal values - The plugin logs only the last 4 characters:
gst_...7f3a
Key permissions
Your API key's tier determines available features:
| Feature | Free | Personal | Team | Enterprise |
|---|---|---|---|---|
| PII tokenization | Pattern only | Full pipeline | Full | Full |
| Audit trail | — | Basic | Full | Full + SIEM |
| Vertical compliance | — | — | Yes | Yes |
| DSAR export | — | — | — | Yes |
| MCP tools | Yes | Yes | Yes | Yes |
Advanced: Hook Priority with Other Plugins
If you use other OpenClaw plugins that register before_llm_call hooks (like openclaw-shield), hook execution order matters.
Recommendation: Install GhostClaw before other security plugins so PII tokenization happens first:
bash
openclaw plugins install ghostclaw
openclaw plugins install openclaw-shieldHooks execute in plugin registration order. GhostClaw tokenizes PII first, then other plugins process the already-tokenized content.
To verify plugin order:
bash
openclaw plugins list --verboseQuick Reference
| Command | Description |
|---|---|
/ghostclaw | Protection status for current session |
/ghostclaw status | Detailed entity breakdown |
/ghostclaw scan <text> | Scan text without sending to AI |
/ghostclaw explain | Deep-dive on most recent detection |
/ghostclaw config | Show all settings |
/ghostclaw config <key> <value> | Change a setting |
/ghostclaw vertical <name> | Switch industry vertical |
/ghostclaw sensitivity <level> | Change detection sensitivity |
/ghostclaw history | Recent PII detections |
/ghostclaw export | DSAR export (GDPR) |
/ghostclaw setup | Re-run onboarding |
/ghostclaw help | Show all commands |
For the full installation walkthrough, see the Full Lab Guide. For live demos, see the Demo Script.