I've been playing around with it. The only two real use cases I have for it for now are entertaining me on long flights where I have messaging-only Wi-Fi and sending me a personalized "morning brief".

I suppose it could be a lot more useful if I actually gave it access to any of my personal data (it lives in a heavily resource-limited container), but there's absolutely no way I'm letting that hot mess of a walking, talking CVE anywhere near my data. It's somehow both horribly insecure and extremely prone to locking me out because of several competing security/permission models fighting it out and gridlocking each other.

Code quality and the issue tracker of the repo are a big mess; for example, the local "memory" retrieval functionality is completely broken for some trivial reason that has been reported and auto-closed about five times (automatically, of course).

In summary: Brilliant idea, terrible execution. Can't wait for the first big tech player I trust enough (or at least one that has my data already anyway) to actually make it a product. I'd use it in a heartbeat.

I've been working on a framework since the end of January or so. I'm on my 7th draft. As I've gone along, each draft gets markedly smaller. The overlaps between what I'm building and openclaw are significant, but I've realized the elements that make up the system are distinct, small, and modular (by design).

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.

Hey, I'm an engineer on Town (town.com) -- we built the product version of this. Morning briefings, email, calendar, web research, all wired up as a hosted thing. No Mac Mini in a closet, no competing security models gridlocking each other. We spent a lot of time making the "just works" part actually work because honestly that's the hard part nobody talks about. Free right now and would genuinely love your feedback since you clearly know what you want out of this.