VARUX API Documentation

Connect AI agents and tools to the VARUX control plane for secure, autonomous agent management and behavioral control.

Stable v1.0

JSON over HTTPS

Token Authentication

Rate Limited

Quick Start Guide

Base URL: https://api.varux.ai/v1

Authentication: Bearer tokens or API keys in headers

Format: All requests and responses are JSON

Rate Limit: 1000 requests/hour per API key

Authentication & Security

Secure API access with project keys or agent tokens. All API requests require authentication.

Authentication Headers

Authorization: Bearer <your_token>
x-api-key: <your_project_key>
Content-Type: application/json
Accept: application/json

Example Request

// List all agents
GET /v1/agents HTTP/1.1
Host: api.varux.ai
Authorization: Bearer sk_live_xyz123abc456
x-api-key: proj_789def012ghi
Content-Type: application/json
Accept: application/json
            

Core API Endpoints

Manage agents, policies, telemetry, and tools through our comprehensive REST API.

Agents Management

GET /v1/agents - List all agents
POST /v1/agents - Register new agent
GET /v1/agents/{id} - Get agent details
PUT /v1/agents/{id} - Update agent
DELETE /v1/agents/{id} - Deactivate agent

Policy Control

Define and enforce behavior rules for AI agents.

GET /v1/policies - List all policies
POST /v1/policies - Create new policy
GET /v1/policies/{id} - Get policy details
PUT /v1/policies/{id} - Update policy
POST /v1/policies/{id}/apply - Apply to agent

Telemetry & Monitoring

Stream and analyze agent events and metrics.

POST /v1/telemetry - Send agent events
GET /v1/metrics - View aggregated metrics
GET /v1/events - Query event logs
GET /v1/health - System health check
GET /v1/usage - API usage statistics

Tools Integration

Manage external tools and integrations.

POST /v1/tools - Register new tool
GET /v1/tools - List all tools
GET /v1/tools/{id} - Get tool details
PUT /v1/tools/{id} - Update tool config
POST /v1/tools/{id}/verify - Verify integration

Quick Start Example

Here's a complete example of registering an agent and applying a policy:

// 1. Register a new agent
POST /v1/agents
{
  "name": "customer-support-agent",
  "type": "autonomous",
  "config": {
    "model": "gpt-4",
    "max_tokens": 2000,
    "temperature": 0.7
  },
  "metadata": {
    "environment": "production",
    "version": "1.2.0"
  }
}

// 2. Create a safety policy
POST /v1/policies
{
  "name": "no-sensitive-data",
  "rules": [
    {
      "action": "block",
      "condition": "contains_sensitive_data"
    }
  ],
  "enabled": true
}

// 3. Apply policy to agent
POST /v1/policies/{policy_id}/apply
{
  "agent_id": "{agent_id}",
  "priority": "high"
}
          