Agent registryRegister a new agent

Register a new agent

Register a new agent — status starts as draft.

curl -X POST "https://api.autopil.ai/v1/agents" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{
  "agent_role": "transaction_analyst",
  "display_name": "Fraud Transaction Analyst v2",
  "description": "Analyzes transaction patterns for fraud signals",
  "owner": "fraud-eng-team",
  "framework": "langgraph"
}'
{
  "agent_id": "agt_abc123",
  "status": "draft"
}
POST
/v1/agents
POST
Base URLstring

Target server for requests. Edit to use your own host.

API Key (header: X-API-Key)
X-API-Keystring
Required

API key with admin, read, or evaluate scope. Missing key → 401; invalid or revoked key → 403.

API key with admin, read, or evaluate scope. Missing key → 401; invalid or revoked key → 403.
Content-Typestring
Required

The media type of the request body

Options: application/json
agent_rolestring
Required

The role this agent will claim in evaluate calls. Must match a policy.

display_namestring

Human-readable name shown in the dashboard.

descriptionstring

Purpose and data access rationale. Used during approval review.

ownerstring

Team or individual responsible for this agent.

frameworkstring

Runtime framework: langgraph, openai_agents, bedrock, etc.

permitted_rolesarray

Roles this agent is allowed to claim. Defaults to [agent_role].

credential_typestring

Authentication method. Defaults to api_key.

Options: api_key, jwt_oidc, mtls, conjur
bound_key_idstring

If set, only the key with this ID may present this agent's identity.

statusstring
Options: draft, pending_approval, approved, deprecated
Request Preview
Response

Response will appear here after sending the request

Authentication

header
X-API-Keystring
Required

API Key for authentication. API key with admin, read, or evaluate scope. Missing key → 401; invalid or revoked key → 403.

Body

application/json
agent_rolestring
Required

The role this agent will claim in evaluate calls. Must match a policy.

display_namestring

Human-readable name shown in the dashboard.

descriptionstring

Purpose and data access rationale. Used during approval review.

ownerstring

Team or individual responsible for this agent.

frameworkstring

Runtime framework: langgraph, openai_agents, bedrock, etc.

permitted_rolesarray

Roles this agent is allowed to claim. Defaults to [agent_role].

credential_typestring

Authentication method. Defaults to api_key.

Allowed values:api_keyjwt_oidcmtlsconjur
bound_key_idstring

If set, only the key with this ID may present this agent's identity.

statusstring
Allowed values:draftpending_approvalapproveddeprecated

Responses