Welcome to Reminix API
The Reminix API gives you programmatic access to your deployed agents and tools. Agents are exposed as REST endpoints. Tools are served via the Model Context Protocol (MCP) — the open standard that Claude, Cursor, and other AI clients use to discover and call tools.Key Features
- Agent Invocation: One-shot tasks with structured input/output
- Conversational Chat: Multi-turn conversations with OpenAI-compatible message format
- Workflow Runs: Multi-step processes with pause, resume, and human-in-the-loop
- Streaming: Real-time Server-Sent Events (SSE) for progressive responses
- Tools via MCP: Connect any MCP client to discover and call your deployed tools
- OAuth Connections: Managed OAuth tokens for 20+ services
Authentication
All API requests require authentication using a Project API Key passed in theAuthorization header.
Getting Your API Key
- Sign in to the Reminix Dashboard
- Navigate to your project settings
- Copy your Project API Key from the API Keys section
Base URL
All API requests should be made to:SDKs
Python
Official Python SDK
TypeScript
Official TypeScript SDK
Next steps
Authentication
The three token types and when to use each.
Errors
Status codes and error response shapes.
Streaming
Server-Sent Events format and event types.
CLI Reference
Hit the same endpoints from the command line.