Integration Philosophy
Freeplay follows a layered approach:- HTTP API - The foundation. All Freeplay functionality is accessible via REST endpoints.
- Native SDKs - Language-specific bindings for common operations (Python, TypeScript, Java/Kotlin).
- Framework Integrations - Packages optimized for specific AI frameworks (LangGraph, Vercel AI SDK, Google ADK).
- OpenTelemetry - For observability with OTel-compatible frameworks where Freeplay lacks a direct integration.
Freeplay SDKs
Native SDKs for direct integration with full control over prompt management, observability, and testing / evaluation.Python
Full-featured SDK for Python applications
TypeScript
Native support for Node.js and TypeScript projects
Java/Kotlin
JVM SDK for Java and Kotlin applications
- Fetch and format prompt templates with variable interpolation
- Record completions, traces, and sessions for observability
- Execute batch tests using saved datasets
- Add customer feedback to observability logs
AI Framework Integrations
For teams using popular AI frameworks, dedicated integration packages provide simplified, automatic observability and streamlined prompt management.| Integration | Language | Observability | Prompt Management | Best For |
|---|---|---|---|---|
| LangGraph | Python only | Automatic tracing | Full support | LangGraph agents |
| Vercel AI SDK | TypeScript | Automatic tracing | Full support | TypeScript/JS AI applications |
| Google ADK | Python | Automatic tracing | Full support | Google ADK agents |
| OpenTelemetry | Any | ”AI centric” OTel | Not included (use SDKs) | Vendor agnostic / custom frameworks |
OpenTelemetry integration provides observability only. For prompt management with OTel-traced applications, use the Freeplay SDK alongside your OTel instrumentation.
HTTP API
The REST API provides programmatic access to all Freeplay capabilities. Use the API when you need:- Operations not covered by the SDK (e.g. bulk uploads, search, statistics)
- Integration with languages without a native SDK
- Additional automation and scripting
API Reference
Complete HTTP API documentation with authentication, endpoints, and interactive playground
Code Recipes
Complete, runnable examples for common integration patterns. Use these as starting points.Code Recipes
Browse examples for prompts, chat, tool calling, providers, and testing
Choosing Your Integration
| Your Situation | Recommended Path |
|---|---|
| New, custom application in Python/TypeScript/Java | Start with the Freeplay SDK |
| New, custom application in other languages (Go, Ruby, etc.) | Use the HTTP API directly |
| Building with LangGraph in Python | Use the LangGraph integration |
| Using Vercel AI SDK | Use the Vercel AI SDK integration |
| Using Google ADK | Use the ADK integration |
| Using another OTel-compatible framework (LlamaIndex, etc.) or prefer OTel | OpenTelemetry for observability + SDK for prompts |
| Need additional bulk operations or automation | HTTP API directly |
| Want working examples | Browse Code Recipes |
MCP integration & Freeplay Skills
For teams using Claude Code, Cursor, Claude Desktop, or similar, Freeplay provides experimental integrations that enable AI agents to interact directly with your Freeplay workspace through natural language.Freeplay MCP Server
Model Context Protocol server with tools and skills
Freeplay Skills
Specialized skills for Claude Code and Cursor
Freeplay Plugin
Native Claude Code plugin (bundles MCP server)
- Analyze production logs and diagnose quality issues through conversation
- Iterate on prompts and agent configurations using real production data
- Run experiments and manage datasets directly from your editor
- Debug AI systems by exploring traces and sessions interactively