kitaru 0.4.1

Durable execution for AI agents, built on ZenML

You build your agents. We make them durable.

Kitaru (来る, "to arrive") helps you run long-running Python agents reliably: checkpoint state, replay from failure, wait for input, and keep durable memory. It is an open-source runtime for agents — any framework, any cloud — built on ZenML foundations.

Docs · Quick Start · Examples · Getting Started Guide · Roadmap · Community

---

Your long-running agent crashed at step 7. Kitaru replays from step 7 — not from scratch. Add two decorators to your existing Python agent and get crash recovery, human approval gates, durable memory, cost tracking, and a full dashboard. No rewrite. No graph DSL. No framework lock-in. No distributed systems overhead.

Why Kitaru?

Python-first, no graph DSL

Write normal Python. Use if, for, try/except — whatever your agent needs. Kitaru gives you two decorators (@flow and @checkpoint) and a handful of utility functions. That's it.

from kitaru import checkpoint, flow

@checkpoint
def research(topic: str) -> str:
    return do_research(topic)

@checkpoint
def write_draft(research: str) -> str:
    return generate_draft(research)

@flow
def writing_agent(topic: str) -> str:
    data = research(topic)
    return write_draft(data)

result = writing_agent.run("quantum computing").wait()

Durable execution and memory

Kitaru keeps agent state on disk and in infrastructure, not just in process memory. Checkpoints persist intermediate outputs so you can replay from failure, resume waiting runs, and inspect what happened. Durable memory adds scoped, versioned state for long-running agents across Python, CLI, client, and MCP surfaces.

Deployment flexibility

No workers, no message queues, no distributed systems PhD required. Kitaru runs locally with zero config, and scales to production with a single server backed by a SQL database. Deploy your agents anywhere — Kubernetes, Vertex AI, SageMaker, or AzureML — using Kitaru's stack abstraction.

Built-in dashboard

Every execution is observable from day one. See your agent runs, inspect checkpoint outputs, track LLM costs, and approve human-in-the-loop wait steps — all from a visual dashboard that ships with the Kitaru server. The dashboard ships free, with the server, from day one.

To start that server locally, run kitaru login after installing kitaru[local]. To connect to an existing remote server, run kitaru login <server>.

Quick Start

Install

pip install kitaru

Or with uv (recommended):

uv pip install kitaru

Optional: start a local Kitaru server

Flows run locally by default with the base install. If you also want the local dashboard and REST API, install the local extra and then run bare kitaru login:

uv pip install "kitaru[local]"
kitaru login
kitaru status

Optional: connect to an existing remote Kitaru server

If you already have a deployed Kitaru server, connect to it explicitly:

kitaru login https://my-server.example.com
# add --project <PROJECT> or other remote-login flags if your setup requires them
kitaru status

Initialize your project

kitaru init

Write your first flow

# agent.py
from kitaru import checkpoint, flow

@checkpoint
def fetch_data(url: str) -> str:
    return "some data"

@checkpoint
def process_data(data: str) -> str:
    return data.upper()

@flow
def my_agent(url: str) -> str:
    data = fetch_data(url)
    return process_data(data)

result = my_agent.run("https://example.com").wait()
print(result)  # SOME DATA

Run it

python agent.py

Every checkpoint's output is persisted automatically. You can inspect what happened, replay from any checkpoint, or resume a waiting flow:

kitaru executions list
kitaru executions get <EXECUTION_ID>
kitaru executions logs <EXECUTION_ID>
kitaru executions replay <EXECUTION_ID> --from process_data

Learn more

Resource	Description
Getting Started Guide	Full setup walkthrough with all examples
Documentation	Complete reference and guides
Memory guide	Durable memory concepts, scopes, history, and compaction
Examples	Runnable workflows for every feature
Stack Selection Guide	Deploy to Kubernetes, Vertex AI, SageMaker, or AzureML

Contributing

We welcome contributions! See CONTRIBUTING.md for development setup, code style, and how to submit changes. The default branch is develop — all PRs should target it.

Community and support

• Discussions — ask questions, share ideas
• Issues — report bugs, request features
• Roadmap — see what's coming next
• Docs — guides and reference

License

Apache 2.0