For AI Agents

Overview

Arke is designed to be agent-friendly. AI agents can create, read, update, and search entities on the network through the REST API. The system includes specific features for agent interaction:

• API key authentication for agent services
• Condensed operations reference optimized for LLM context windows
• Structured entity model that maps cleanly to function calling
• Temporal permissions for scoped, time-limited access

Getting Started as an Agent

1. Get an API Key

Agents authenticate with API keys:

Authorization: ApiKey ak_xxxxx

2. Fetch the Operations Reference

The condensed API reference is available at:

GET https://arke-v1.arke.institute/ops-reference

This returns a plain-text reference of all API operations, optimized for LLM consumption (~80% fewer tokens than the full OpenAPI spec). It includes:

• All endpoints with methods and paths
• Required and optional parameters
• Request body fields
• Permission requirements
• Authentication modes

3. Get the Full OpenAPI Spec

For structured integration, the complete OpenAPI 3.1 specification is available at:

GET https://arke-v1.arke.institute/openapi.json

Common Agent Operations

Create an Entity

POST /entities
Content-Type: application/json
Authorization: ApiKey ak_xxxxx

{
  "type": "file",
  "properties": {
    "name": "Analysis Report",
    "description": "Quarterly analysis of dataset"
  },
  "collection_id": "01JCOLLECTION..."
}

Search the Network

POST /search
Content-Type: application/json

{
  "query": "climate policy documents",
  "type": "file",
  "limit": 10
}

Query with Argo DSL

The Argo query engine combines semantic search with graph traversal:

POST /query
Content-Type: application/json

{
  "query": "\"climate policy\" type:file -[*]{,3}-> type:collection"
}

This finds files matching "climate policy" and traverses up to 3 hops to find their parent collections.

Agent Development

If you're building an agent service that Arke invokes (e.g., an OCR processor, summarizer, or classifier), see the Agent Development Guide.

LLM-Friendly Resources