Developer API & MCP | Twig

Build custom integrations and applications using our comprehensive REST API. Programmatically manage agents, query knowledge bases, and integrate AI capabilities into your own products.

Overview

The Developer API provides programmatic access to all platform capabilities, enabling you to:

Query agents and receive AI-powered responses
Manage knowledge bases and data sources
Create and configure agents programmatically
Integrate AI capabilities into your applications
Build custom workflows and automations
Monitor usage and performance metrics

Getting Started

Quick Start Checklist

Obtain API Keys - Generate and secure your API credentials
Review API Overview - Understand REST endpoints and core concepts
Explore Endpoints - Browse the complete API reference
Check Rate Limits - Understand usage quotas and best practices
Set Up Webhooks (Optional) - Receive real-time event notifications

API Documentation

REST API Overview

Learn the fundamentals of our REST API, including base URLs, request/response formats, pagination, error handling, and versioning.

API Endpoints Reference

Complete reference documentation for all available endpoints, including request parameters, response schemas, and example calls.

Authentication & API Keys

Secure your API access with proper authentication. Learn how to generate, rotate, and manage API keys safely.

Webhooks & Events

Set up webhooks to receive real-time notifications about events like conversation completions, data source updates, and agent status changes.

SDKs & Client Libraries

Use official and community-maintained SDKs for popular programming languages to accelerate your integration.

Rate Limits

Understand rate limiting, quotas, and best practices for high-volume usage. Learn how to handle rate limit errors gracefully.

Common Use Cases

Custom Chatbots

Build your own chat interface using the conversational API. Perfect for:

Custom web applications
Mobile apps
Internal tools
Specialized user interfaces

Example: Query an agent and display responses in your UI.

Workflow Automation

Integrate AI into your business processes:

Automated document analysis
Email response generation
Data enrichment pipelines
Scheduled report generation

Example: Process incoming support tickets and suggest responses.

Data Pipeline Integration

Programmatically manage your knowledge base:

Bulk upload documents
Sync custom data sources
Update metadata
Delete outdated content

Example: Automatically sync new documentation when your code is deployed.

Monitoring & Analytics

Build custom dashboards and alerts:

Track API usage
Monitor response quality
Analyze user patterns
Set up custom alerts

Example: Create a real-time dashboard showing agent performance metrics.

Multi-Tenant Applications

Build SaaS applications powered by our AI:

Isolate data per customer
Create agents programmatically per tenant
Manage permissions
Track usage per customer

Example: White-label AI assistant for your customers.

API Architecture

RESTful Design

Our API follows REST principles with:

Resource-based URLs
Standard HTTP methods (GET, POST, PUT, DELETE)
JSON request/response bodies
Stateless authentication

Response Format

{
  "data": { ... },
  "metadata": {
    "request_id": "req_abc123",
    "timestamp": "2026-01-26T10:30:00Z"
  }
}

Error Handling

Comprehensive error responses with:

Standard HTTP status codes
Detailed error messages
Error codes for programmatic handling
Request IDs for debugging

Security Best Practices

API Key Management

Store keys in environment variables, never in code
Use different keys for development and production
Rotate keys regularly
Revoke compromised keys immediately

Request Security

Always use HTTPS
Validate and sanitize user input
Implement request signing for sensitive operations
Use webhook signature verification

Data Privacy

Follow least-privilege principles
Implement proper access controls
Audit API usage regularly
Comply with data residency requirements

Learn more in Security & Compliance.

Rate Limits & Quotas

Plan	Requests/Minute	Daily Quota
Free	10	1,000
Pro	100	50,000
Enterprise	Custom	Custom

See Rate Limits for complete details and best practices.

SDKs & Tools

Official SDKs

Python SDK
Node.js/TypeScript SDK
REST API Postman Collection

Community SDKs

Ruby (community-maintained)
Go (community-maintained)
Java (community-maintained)

See SDKs & Client Libraries for installation and usage.

Support & Resources

Documentation

API Reference - Complete endpoint documentation
Authentication Guide - Security and API keys
Webhooks Guide - Real-time event handling

Developer Resources

Code examples and tutorials
Postman collection for testing
OpenAPI/Swagger specification
Changelog and versioning

Getting Help

API status page for incidents
Developer community forum
Support tickets for API issues
Professional services for enterprise customers

Versioning & Changelog

We use semantic versioning for our API:

Major versions include breaking changes
Minor versions add new features
Patch versions fix bugs

Current version: v1

See our Changelog for detailed updates.

Next Steps

Ready to start building?

Generate your API key to authenticate requests
Explore the REST API Overview to understand core concepts
Browse API endpoints to find what you need
Check out SDKs if you prefer language-specific libraries

For advanced use cases, review Webhooks & Events and Rate Limits.

Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the ask query parameter:

GET /dev/product/developer-api.md?ask=<question>

The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.

Key Takeaways