Ask HN: Who is using OpenClaw?

What it adds is making this kind of thing easy for normies, even if it's neither the best way to do things nor very difficult for hobbyists to do using existing tech.

Maybe it's the wrong approach, maybe what people really want is more deterministic software that they use agents to help write. But this kind of thing can maybe serve as a prototyping phase for that. Perhaps in the future, people's assistants will offer to "solidify" frequently used workflows into software that minimizes or eliminates the LLM's role. For existing Claude Code users, its like "please just skip to that step! its cheaper and more secure and more reliable". But to many people who are interested in automation, perhaps that seems out of reach as a first step.

There are only a few primitives:

1. session history

1a. context map + rendered context map (think of a drive partitioning scheme, but for context -- you can specify what goes into each block of context and this gets built before being sent out for inference).

2. agent definition / runtime

3. workflow definition / runtime

4. workflow history

5. runtime history (for all the stuff session and workflow history fail to capture because they are at a lower level in the stack)

That's it. Everything else builds on top of these primitives, including

- memory (a new context block that you add to a context map)

- tool usage (which is a set of hooks on inference return and can optionally send the output straight back for inference -- this is a special case inside the inference loop and so just lives there)

- anything to do with agent operating environment (this is an extension of workflows)

- anything to do with governance/provenance/security (this is an extension of either workflows and/or agent operating environment... I haven't nailed this down yet).

I suppose I should say something about how agents and workflows work together. I've broken up 'what to do' and 'how to think' into the two primitives of 'workflow' and 'agent' respectively. An agent's context map will have a section for system prompt and cognitive prompt, and an agent can 'bind' to a workflow. When bound, the agent has an additional field in their context map that spells out the workflow state the agent is in, the available tools, and state exit criteria. Ideally an agent can bind/unbind from a workflow at will, which means long-running workflows are durable beyond just agent activity. There's some nuance here in how session history from a workflow is stored, and I haven't figured that out yet.

Generally, the idea of a workflow allows you to do things like scheduled tasks, user UI, connectors to a variety of comms interfaces, tasks requiring specific outputs, etc. The primitive lays the foundation for a huge chunk of functionality that openclaw and others expose.

It's been fun reasoning through this, and I'll admit that I've had an awful lot of FOMO in the mean time, as I watch so many other harnesses come online. The majority of them look polished, and are well marketed (as far as AI hype marketing goes). But I've managed to stay the course so far.

I hope you find your ideal fit. These tools have the potential to be very powerful if we can manage to build them well enough.

I cringe at my old boss’s handiwork in Claude and power automate sometimes and go “you know I could just do that in a script and a cron job and it would be completely bullet proof, right?”

Then he just shoots back with, “yeah but now I don’t have to ask you.”

This is my kludge, there are many others like it but this one is mine.