Integrations Overview

Cycles integrates with LLM providers, agent frameworks, and web servers. Each integration wraps model calls with the reserve → commit → release lifecycle so that every call is budget-checked before execution.

Supported integrations

Integration	Language	Streaming	Pattern
OpenAI	Python	Yes	Decorator
Anthropic	Python	Yes	Decorator
LangChain	Python	Yes	Callback handler
LangChain.js	TypeScript	Yes	Callback handler
Vercel AI SDK	TypeScript	Yes	reserveForStream
AWS Bedrock	TypeScript	Yes	withCycles / reserveForStream
Google Gemini	TypeScript	Yes	withCycles / reserveForStream
Express	TypeScript	Yes	Middleware / withCycles
FastAPI	Python	—	Middleware / Decorator
OpenClaw	TypeScript	Yes	Plugin (lifecycle hooks)

Integration patterns

Cycles offers several integration approaches depending on your stack:

Decorator / Higher-order function

The simplest approach. Wrap your LLM-calling function and Cycles handles reservation, commit, and release automatically.

• Python: @cycles decorator
• TypeScript: withCycles higher-order function

Best for: individual model calls, simple request-response flows.

Callback handler

For agent frameworks like LangChain that fire events on every LLM call. A custom callback handler creates reservations on llm_start and commits on llm_end.

Best for: multi-turn agents, tool-calling chains, LangChain/LangGraph pipelines.

reserveForStream

For streaming responses where the actual cost is only known after the stream completes. Reserves budget upfront, auto-extends the reservation TTL during streaming, and commits actual usage when the stream finishes.

Best for: streaming chat UIs, Vercel AI SDK, any provider with streaming support.

Programmatic client

Direct access to the Cycles client for full control over the reservation lifecycle. Use when the higher-level patterns don't fit your architecture.

Best for: custom frameworks, complex orchestration, batch processing.

See Choosing the Right Integration Pattern for detailed guidance.

Adding a new integration

All integrations follow the same protocol:

1. Reserve budget before the LLM call with an estimated cost
2. Execute the model call (respecting any caps returned)
3. Commit actual cost from token usage after execution
4. Release on error to free held budget

See Using the Cycles Client Programmatically for the full client API reference.

Next steps

• Adding Cycles to an Existing Application — step-by-step guide for your first integration
• Cost Estimation Cheat Sheet — pricing reference for estimation
• Error Handling Patterns — handling budget errors across languages