Choose an Adapter

Pick the Kitaru integration path for your existing agent harness

Kitaru does not require one agent framework. Pick the boundary that matches the code you already have.

Decision table

You have...	Use this	Replay boundary	First page
Plain Python functions	@flow + @checkpoint	Your function boundaries	Quickstart
PydanticAI agent	KitaruAgent	model/tool/MCP calls by default, or one turn checkpoint	PydanticAI Adapter
OpenAI Agents SDK agent	KitaruRunner	per-call checkpoints or one runner-call checkpoint	OpenAI Agents Adapter
Claude Agent SDK invocation	KitaruClaudeRunner	one completed Claude invocation	Claude Agent SDK Adapter
LangGraph graph	KitaruGraphRunner	one graph call, or middleware-wrapped model/tool calls	LangGraph Adapter

Pick by goal

I want the simplest durable boundary

Wrap phases of work in @checkpoint and keep your existing Python control flow

I want granular agent observability

Use PydanticAI or OpenAI calls mode so model and tool calls become visible replay units

I want a clean return value from flow.wait()

Use a coarse runner-call or turn checkpoint around the whole agent turn

I need human approval

Keep wait/approval bridges at flow scope so the execution can suspend safely

Strategy notes

Strategy	Best for	Trade-off
Coarse checkpoint	Fast migration, easy .wait() return value, low adapter complexity	Replay reruns the whole agent turn if it fails inside the turn
Granular checkpoints	Expensive LLM/tool chains where partial replay matters	More checkpoint rows and stricter rules around waits/nesting
Explicit raw checkpoints	Maximum control and framework independence	You decide every durable boundary yourself

Human-in-the-loop rule

kitaru.wait() belongs at flow scope, not inside a normal checkpoint body. If your harness adapter creates granular tool checkpoints, configure wait-bearing tools so the adapter keeps that wait outside the synthetic checkpoint wrapper.

Start with:

• Wait, Input, and Resume

• PydanticAI human-in-the-loop tools

• OpenAI approval interruptions

• LangGraph interrupt and resume

Next

Run a small adapter example from Examples before porting a production agent. The fastest useful proof is one completed execution where you can see the expected checkpoint shape.