Integrations

The Doubleword Inference API is OpenAI-compatible, so it works with any framework that supports custom OpenAI endpoints.

The integrations below are grouped by what you are building, and each guide shows how to route that framework's requests through the API. Frameworks that accept an AsyncOpenAI client also support Autobatcher for batch pricing, cutting inference costs by up to 90% for background workloads.

Code and run agentic workflows

Coding agents and sandboxes that run on Doubleword.

Daytona OpenClaw Opencode Pi

Build agents and agentic workflows

Frameworks for building and orchestrating AI agents.

Agno atomic-agents CrewAI Google ADK Microsoft Agent Framework OpenAI Agents SDK PydanticAI smolagents

Ship AI features in your product

Build LLM-powered features and data pipelines into your product.

LangChain / LangGraph LlamaIndex Mastra Vercel AI SDK

Add memory to your app

Give your app and agents long-term memory.

mem0 Supermemory BetterDB

Evaluate, trace, and observe

Trace, evaluate, and monitor your LLM calls.

Arize AX Arize Phoenix Langsmith