KnowledgeMemoryBlogPricingDocs Log in

API Documentation

Ragionex provides two products through a single REST API: Knowledge for semantic search over documentation, and Memory for persistent semantic memory for AI agents. Both products share the same base URL and use JSON for requests and responses.

Base URL

All API requests are made to:

https://api.ragionex.com

Authentication

All API endpoints require authentication via the X-API-Key header. The two products use different API key types:

Knowledge API

Uses a shared API key provided during Developer Preview. The key prefix is rgx_knowledge_demo_. Grab the key from the Knowledge page.

Memory API

Uses per-user API keys generated at first sign-in. The key prefix is rgx_memory_. Sign in at app.ragionex.com/login to receive your key.

HTTP Header
X-API-Key: rgx_memory_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Note

Keep your API key secure. Do not expose it in client-side code or public repositories.

API Products

Pick the product you're integrating to see its full endpoint reference:

Error Handling

All API errors return a consistent JSON format with success: false and an error message describing the issue.

Error Response Format
{
  "success": false,
  "error": "Description of what went wrong"
}

HTTP Status Codes

CodeDescription
200Success
400Bad Request - Invalid parameters or malformed request
401Unauthorized - Invalid or missing API key
404Not Found - Resource does not exist or is not owned by you
422Validation Error - Parameter constraints not met
429Rate Limit Exceeded - Too many requests
500Internal Server Error - Something went wrong on our end
503Service Unavailable - API is temporarily unavailable

Common Errors

401 - Invalid API Key (Knowledge)
{
  "success": false,
  "error": "Invalid or missing API key"
}
401 - Invalid API Key (Memory)
{
  "success": false,
  "error": "Invalid or missing API key. Get your key by signing in at https://app.ragionex.com/login"
}
422 - Parameter Too Long
{
  "success": false,
  "error": "question parameter is too long (max 128 characters)"
}
429 - Rate Limited
{
  "success": false,
  "error": "Rate limit exceeded"
}

Rate Limits

Rate limits are applied per IP address. When you exceed the limit, the API returns a 429 status code.

Knowledge API Limits

EndpointLimit
/v1/knowledge/search30 requests per minute
/health60 requests per minute

Memory API Limits

EndpointLimit
/v1/memory/write30 requests per minute
/v1/memory/search60 requests per minute
/v1/memory/list30 requests per minute
/v1/memory/view30 requests per minute
/v1/memory/update10 requests per minute
/v1/memory/delete10 requests per minute
/v1/memory/status/{id}60 requests per minute
/v1/memory/projects60 requests per minute
/v1/memory/projects/{name} (PATCH)5 requests per minute
/v1/memory/projects/{name} (DELETE)5 requests per minute
Developer Preview

Rate limits may be adjusted during the Developer Preview period. Contact us if you need higher limits for testing.