Kitaru7 mins
Choosing a sandbox runtime for long-lived coding agents
How we evaluated sandbox providers for coding agents, what we chose for now, and the trade-offs behind that decision.
Blog
Insights on MLOps, LLMOps, and production machine learning from the ZenML team.
Popular:
Kitaru10 mins
Introducing the new Kitaru: from production traces to repeatable evals
The new Kitaru turns production traces you already collect into replayable test scenarios, expert-reviewed cohorts, and evaluators you can run on every change.
MLOps8 mins
Your GPUs Are Everywhere. Your Robot-Learning Loop Shouldn't Be.
Robotics compute is spreading across clouds and clusters. Learn how one portable pipeline layer can keep the robot-learning loop reproducible.
Kitaru8 mins
Don't make Claude do the same work twice
Claude Agent SDK runs the agent loop. Kitaru adds the durable runtime around a completed invocation — checkpointed results, artifacts, replay boundaries, and waits.
Kitaru9 mins
Your LangGraph agent works. Now make the workflow durable.
LangGraph keeps graph state, threads, and interrupts. Kitaru adds the durable workflow around the graph call — replay boundaries, durable waits, and inspectable runs.
Kitaru10 mins
OpenAI Agents are great. Production still needs a runtime.
The OpenAI Agents SDK stays the harness; Kitaru adds the runtime around it — durable workflow waits, replay boundaries, and inspectable execution history.
Checkpoint Replay, Worker Shape, and Where Durable Execution Is Going
Armin Ronacher's Absurd and Kitaru arrived at the same answers on replay semantics, ephemeral compute, and an agent-legible runtime. Here's why that matters.
The runtime layer underneath your agent stack
What people call the agent stack is really four layers: model, harness, runtime, platform. Conflating them costs durability. The runtime layer, and one split inside it, gets the least attention.
Kitaru8 mins
Introducing Kitaru: Open Source Infrastructure For Asynchronous Agents (Built by the ZenML Team)
Meet Kitaru — open source durable execution for Python agents, built by the ZenML team. Crash recovery, human-in-the-loop, and replay from any checkpoint.
Kitaru is open source and ready to use
Kitaru is live: open-source infrastructure platform for running Python agents in production.
The Anatomy of a Production Coding Agent
A production coding agent isn't a prompt and a while loop. It's eight stages, each with different failure modes, costs, and human touchpoints. Here's the full pattern.
From Pipelines to Agents: How Orchestration is Being Rewritten
ML pipelines were DAGs. Agents are loops. The orchestration layer that worked for training jobs doesn't work for autonomous systems, and the industry is scrambling to catch up.
AI orchestration,
on the infra you choose
Get new posts by email
New posts and product updates, sent when we publish. No spam.
By subscribing, you agree to our privacy policy.