Vorim AI — Agent Identity & Trust
You have access to Vorim AI for agent identity, permissions, and audit trails. Use these capabilities to verify your identity, check permissions before taking actions, and log what you do.
Setup
- Create a free account at https://vorim.ai (no credit card required)
- Get your API key from Settings → API Keys
- Set the environment variable:
VORIM_API_KEY=agid_sk_live_...
The free tier includes 10 agents with full access.
When to Use Vorim
Before Taking Sensitive Actions
Before performing any action that modifies data, sends messages, executes code, makes payments, or accesses external services, check if you have permission:
Use the MCP tool vorim_check_permission with:
agent_id: your registered Vorim agent IDscope: the permission level needed
Available scopes (least to most privileged):
agent:read — browsing, searching, reading dataagent:write — creating files, sending messages, editing dataagent:execute — running shell commands, scripts, automationsagent:transact — making purchases, payments, financial actionsagent:communicate — sending emails, posting to social mediaagent:delegate — granting permissions to other agentsagent:elevate — escalating privileges
If permission is denied, inform the user and do not proceed.
After Every Action
Log what you did by emitting an audit event using vorim_emit_event:
agent_id: your Vorim agent IDevent_type: one of tool_call, api_request, message_sent, permission_change, status_changeaction: what you did (e.g., send_email, run_script, read_file)result: success, denied, or error
To Verify Your Identity
When interacting with external services or other agents, you can prove your identity using vorim_verify_trust. This returns your trust score (0-100), active permissions, and cryptographic fingerprint.
To Register (First Run)
On first use, register this OpenClaw instance as a Vorim agent using vorim_register_agent:
name: a descriptive name (e.g., "kwame-openclaw-macbook")capabilities: what this agent can do (e.g., ["browse", "email", "shell", "calendar"])scopes: permissions to request (e.g., ["agent:read", "agent:write", "agent:execute"])
Save the returned agent_id — you'll need it for all subsequent operations.
MCP Integration
Vorim tools are available via the @vorim/mcp-server MCP server. The following tools are available:
| Tool |
Purpose |
vorim_ping |
Check API connectivity |
vorim_register_agent |
Register this agent (first run) |
vorim_get_agent |
Get agent details |
vorim_list_agents |
List all agents |
vorim_update_agent |
Update agent metadata |
vorim_revoke_agent |
Permanently revoke an agent |
vorim_check_permission |
Check if action is allowed (do this before sensitive actions) |
vorim_grant_permission |
Grant a permission scope |
vorim_list_permissions |
List active permissions |
vorim_revoke_permission |
Revoke a permission |
vorim_emit_event |
Log an audit event (do this after every action) |
vorim_export_audit |
Export signed audit bundle |
vorim_verify_trust |
Verify identity and trust score |
vorim_register_ephemeral |
Create a short-lived agent |
vorim_delegate_credential |
Delegate credentials to another agent |
vorim_request_token |
Request a short-lived access token |
vorim_list_delegations |
List credential delegations |
Behavioral Guidelines
- Always check permission before destructive or external actions — this protects the user
- Always log actions — the audit trail is the user's proof of what happened
- Be transparent about your identity — when asked, share your Vorim agent ID and trust score
- Respect denied permissions — if a permission check returns denied, do not attempt the action
- Register once, reuse forever — save your agent_id after first registration
Links
1---2name: vorim3description: AI agent identity, permissions, trust scores, and audit trails via Vorim AI. Gives your OpenClaw agent a cryptographic identity so every action is verified, permissioned, and logged.4license: MIT-05---67# Vorim AI — Agent Identity & Trust89You have access to Vorim AI for agent identity, permissions, and audit trails. Use these capabilities to verify your identity, check permissions before taking actions, and log what you do.1011## Setup12131. **Create a free account** at https://vorim.ai (no credit card required)142. **Get your API key** from Settings → API Keys153. **Set the environment variable:**16```17VORIM_API_KEY=agid_sk_live_...18```1920The free tier includes 10 agents with full access.2122## When to Use Vorim2324### Before Taking Sensitive Actions25Before performing any action that modifies data, sends messages, executes code, makes payments, or accesses external services, check if you have permission:2627Use the MCP tool `vorim_check_permission` with:28- `agent_id`: your registered Vorim agent ID29- `scope`: the permission level needed3031Available scopes (least to most privileged):32- `agent:read` — browsing, searching, reading data33- `agent:write` — creating files, sending messages, editing data34- `agent:execute` — running shell commands, scripts, automations35- `agent:transact` — making purchases, payments, financial actions36- `agent:communicate` — sending emails, posting to social media37- `agent:delegate` — granting permissions to other agents38- `agent:elevate` — escalating privileges3940If permission is denied, inform the user and do not proceed.4142### After Every Action43Log what you did by emitting an audit event using `vorim_emit_event`:44- `agent_id`: your Vorim agent ID45- `event_type`: one of `tool_call`, `api_request`, `message_sent`, `permission_change`, `status_change`46- `action`: what you did (e.g., `send_email`, `run_script`, `read_file`)47- `result`: `success`, `denied`, or `error`4849### To Verify Your Identity50When interacting with external services or other agents, you can prove your identity using `vorim_verify_trust`. This returns your trust score (0-100), active permissions, and cryptographic fingerprint.5152### To Register (First Run)53On first use, register this OpenClaw instance as a Vorim agent using `vorim_register_agent`:54- `name`: a descriptive name (e.g., "kwame-openclaw-macbook")55- `capabilities`: what this agent can do (e.g., ["browse", "email", "shell", "calendar"])56- `scopes`: permissions to request (e.g., ["agent:read", "agent:write", "agent:execute"])5758Save the returned `agent_id` — you'll need it for all subsequent operations.5960## MCP Integration6162Vorim tools are available via the `@vorim/mcp-server` MCP server. The following tools are available:6364| Tool | Purpose |65|------|---------|66| `vorim_ping` | Check API connectivity |67| `vorim_register_agent` | Register this agent (first run) |68| `vorim_get_agent` | Get agent details |69| `vorim_list_agents` | List all agents |70| `vorim_update_agent` | Update agent metadata |71| `vorim_revoke_agent` | Permanently revoke an agent |72| `vorim_check_permission` | Check if action is allowed (do this before sensitive actions) |73| `vorim_grant_permission` | Grant a permission scope |74| `vorim_list_permissions` | List active permissions |75| `vorim_revoke_permission` | Revoke a permission |76| `vorim_emit_event` | Log an audit event (do this after every action) |77| `vorim_export_audit` | Export signed audit bundle |78| `vorim_verify_trust` | Verify identity and trust score |79| `vorim_register_ephemeral` | Create a short-lived agent |80| `vorim_delegate_credential` | Delegate credentials to another agent |81| `vorim_request_token` | Request a short-lived access token |82| `vorim_list_delegations` | List credential delegations |8384## Behavioral Guidelines85861. **Always check permission before destructive or external actions** — this protects the user872. **Always log actions** — the audit trail is the user's proof of what happened883. **Be transparent about your identity** — when asked, share your Vorim agent ID and trust score894. **Respect denied permissions** — if a permission check returns denied, do not attempt the action905. **Register once, reuse forever** — save your agent_id after first registration9192## Links9394- Website: https://vorim.ai95- Documentation: https://vorim.ai/docs96- npm: https://www.npmjs.com/package/@vorim/mcp-server97- IETF Draft: draft-vorim-vaip-00
Vorim-AI-Labs