.png)
Anthropic has two ways to build and launch agents with Claude now
As of this morning, I'm using both. I'm going to be explaining this alongside the Momentic AI Studio, because A) it's a good way to visualize this stuff, and B) more people should know the things we're doing here in Milwaukee.
The difference between Anthropic's Agent SDK and Managed Agents is mostly about who runs the compute and who optimizes the running of it.
- Agent SDK has been around for a bit. It's the engine under Claude Code, packaged as a library. You build the whole thing yourself. You write a program that says "connect to this database, pull these exact fields, if anything looks weird flag it, then post a summary to Slack." Every step, every fallback, every detail. That's on you. You run it on your own computer or server. It's reliable because you decided exactly what happens. It's a pain because you decided exactly what happens.
- Managed Agents went into public beta yesterday. You describe the same task. Pull from a database, flag something, post to Slack. But Anthropic figures out the steps and runs it on their infrastructure. You don't write the logic. You don't host anything. You tell it what the job is, and their system handles the how. It's quicker to set up, but the tradeoff is that Anthropic's system is deciding the steps, so the output is less predictable. There is a per hour of runtime plus token costs.
Cooking at home vs. ordering delivery*. You get a similar meal either way. When you cook, you control every ingredient. When you order out, it shows up at your door, but hope they remembered to swap the beef out for an Impossible patty.
* where sometimes you don't even get your food, but you still pay for it because Door Dash and Uber Eats have evil apps and policies.
How do you use Managed Agents or Agent SDK?
Neither of these is a thing you click around in. Both require an API key and a terminal.
Agent SDK: you install a separate library (Python or TypeScript are the two options), then write a program from scratch. Your code defines every tool the agent can use, including permission and fallbacks. You run it on your own machine or server. If it breaks at 3am, that's your problem. It also works through Amazon Bedrock, Google Vertex, or Microsoft Azure. Still Claude, just different billing and infrastructure.
Managed Agents: you use the standard anthropic SDK (same package you'd use for any Claude API call, just different endpoints) or a CLI tool called ant. You set up three things. An agent, an environment, and a session. Anthropic handles the rest. It's their servers, their error recovery, their execution. It uses a completely separate API from the normal Claude messages endpoint. It supports seven languages, not just two.
The difference in practice: SDK you're building and running "the machine". Managed Agents you're handing Anthropic a job description and they run the machine.
Agentic options in Claude desktop app
If you're not technical and you just want Claude doing stuff for you automatically, use scheduled tasks in Cowork on the Claude desktop app. You type what you want done, set how often, it runs. Pair it with the mobile app to kick things off from your phone. It's not as powerful but that's where most people should start.
What is better? Agent SDK vs Managed Agents
- Doing the thing the same way every time: Agent SDK. You wrote the steps, so it follows them.
- Controlling costs: It depends. SDK has no runtime fee but you pay for servers and your own time building it. Managed Agents is $0.08/hr plus tokens, but there's no hosting to pay for.
- Maintenance and overhead: Managed Agents. Anthropic handles infrastructure, error recovery, the execution environment. SDK means if it breaks at 3am that's a you problem.
- Getting started fast: Managed Agents. Less code to write, no infrastructure to set up.
- Working with sensitive data: Agent SDK. It runs on your infrastructure, so nothing leaves your environment unless you send it.
- Language options: Managed Agents supports seven languages. SDK is Python or TypeScript only.
- Running through your own cloud provider: Agent SDK. It works through Bedrock, Vertex, and Azure. Managed Agents runs on Anthropic's infrastructure only.
Are Managed Agents similar to OpenClaw?
Yes, Anthropic Managed Agents is similar to OpenClaw, in a way. But so is Agents SDK, in a different way. And it makes sense for Anthropic to release the public beta given recent events.
Anthropic updated their consumer terms in February to prohibit subscription tokens in third-party tools. In April, Boris Cherny (Head of Claude Code) announced that subscriptions would no longer cover tools like OpenClaw, effective immediately. The same week, Anthropic released Managed Agents, a paid path to autonomous Claude agents (like what OpenClaw originally offered). (Note: there's no official Anthropic blog post about the OpenClaw block specifically. This timeline is based on press reporting from TechCrunch, VentureBeat, and The Register.)
For context: OpenClaw is a self-hosted open-source personal AI assistant. It's model-agnostic, bridges like 20 messaging channels to 37 LLM providers, does sub-agent dispatch, persistent memory, cron (repeat) jobs. The operating system/infrastructure is free if you bring your own API key or use a self-hosted LLM. People were running it with their Claude subscription tokens and a single instance could burn $1,000-$5,000/day in equivalent API costs on a $200/month subscription. That's why Anthropic shut that down.
Now there's Managed Agents. It solves a similar problem but from the opposite direction. OpenClaw is self-hosted. You run the compute, you optimize the execution, you pick the model. That's closer to how SDK is configured. Managed Agents is the other end. Anthropic runs the compute, Anthropic optimizes the execution, and it's Claude only. It's actually priced for the use case.
If you were using OpenClaw to run autonomous Claude agents, Managed Agents is probably the official path to the same outcome. You just give up the self-hosting and the model choice in exchange for Anthropic handling the infrastructure.
If you liked OpenClaw because it's open source and model-agnostic and you own everything, Managed Agents is a different thing entirely.
There's a cynical way to read into this: Anthropic closed the cheap door and opened a paid one. And a less cynical way to read into this: Managed Agents was probably already in development, the subscription block was genuinely about economics, and these are different products.
Keep your eyes peeled for these things
Multi-agent orchestration, memory tooling, and self-evaluation loops are still in limited preview, and not in the public beta. These are the features that would close the gap between Managed Agents and the SDK for a lot of complex situations. I have not seen a timeline on when they'll be available.
It's early!
PS - reach out to me on LinkedIn for questions about this topic. But if you're interesting in working with Momentic, please reach out to us at info@momenticmarketing.com. Have a good day.
.png)
.png)
