About three weeks ago I was seduced by people singing praise to OpenClaw, and also by the fact that OpenClaw team burns millions of dollars of tokens per month on developing it — surely it must be good.

It turned out to be probably the crappiest, glitchiest piece of software I’ve used in the past few years. Its basic onboarding workflow was completely broken, GUI was a hallucinated mess.

Also it turned out that not a single person I know who dedicated time to configuring it, ever achieved anything remotely interesting as a result.

I really want to like these "agentic assistant" tools, because I feel like the problem they claim to solve is real: give me an interface across desktop and mobile to a persistent backend where I can set up agents (using natural language) to do... whatever I want. Deep market research? Building + hosting a browser game? Checking my email? etc.

But after trying both Hermes and OpenClaw, it feels like they both... miss the point? Last time I tried OpenClaw it wanted to download something like 11 GB of local models to do... something (embeddings for memory indexing or chat labeling/classification maybe?) which my sorry old 16gb M1 is certainly not capable of running.

Hermes seems to suffer from the same problem: why do I need to download (and then immediately disable to avoid confusing my poor "agents"... a concept which I also feel like way too many tools fundamentally misunderstand) skills for managing Spotify playlists or pokemon or minecraft in order to run the thing? (I acknowledge that they cleaned some of this up in a recent release, so maybe this isn't as bad as it was when I last tried it)

WRT "agents"... can someone explain to me why there's so much effort put into naming agents and giving them personalities? An "agent" is simply a separate context window with different prompting (itself written by the spawning/parent "agent") that's specific to a partial slice of the task you're trying to solve. If you have to write their prompt ahead of time that defeats the whole purpose of a programmable, autonomous subagent, doesn't it?

Everything you mentioned OpenClaw does is also something that Hermes supports. Hermes also supports project-scoped kanban boards and can orchestrate across multiple specialized Hermes profiles.

What are some examples of features that they have added since December that you use? I originally had setup openclaw back in Jan(?) and had it generating some news summaries for me and stuff. But ran out of ideas... would like to try it out again.

I tried to make mine as human-like as possible, with self-reflection, episodic memory / hippocampus, emotional tagging etc. If you prefer talking to a person, not a tool, you can take a look at https://lethe.gg/ (open source, written in Rust, hosted version available).

I've done similar, even to the point of a discord gateway integration that is very similar to the one Hermes ships with.

I still use Hermes because it's not a problem I care about solving right now and am spending my time and tokens on more important problems. I don't plan to always use it, and if anything it gives me ideas for what the ideal shape of what I want would be.

Also to add, having a unified space to chat with an agent that has a local system it can work with is quite liberating because I use it to drive my agent orchestration system. So I'm no longer bound to my computer or any one providers harness and whatever mobile solution they provide if any. It's been quite freeing and I don't use Hermes that differently than I would chatgpt, except it know exactly how I like to do my work and that means I have to remind it less.

I did the same thing. I use the Pi coding agent and they support extensions. I asked GPT 5.5 to create a Pi extension that has the magic of Hermes and for me that was the long term memory and the cron/scheduling. And that way, I can use Pi as is and turn on these using a slash command.

openclaw = claude code + memory + cron job

persistent memory plus cron job lets you do stuff that you can't do with just codex/claude code/opencode

I set up a Hermes agent for our company and connected it to BigQuery, Stripe, Amplitude, etc so that our nontechnical teammates can ask and answer their own data questions via Slack. It works great!

I similarly haven’t found it useful to run a bunch of these agents in developing the product, but it’s a nice interface for people who don’t live in their terminal all day.

I don't understand people running OpenClaw. I just full shot a prompt to create a better clone. Its extremely custom to my work and flow. I use it as a personal agent, emails, slacks + as a hardcore coding agent. If it sees a problem in email it will create a ticket, assign it to an agent monitor progress, get a PR ready for me - then it harasses me until I review the PR. If I ignore the PR it will call my wife. It can also reason on what emails need critical attention etc.

I understand that hermes needs to do be able to do "everything" but I can't stand how much crap comes along with it.

It feels like when you do a fresh Windows install and you have to debloat it from all the spyware and candy crush type games.

Pi is the perfect clean slate, I absolutely love it.

My struggle is despite giving it a good honest go I couldn’t find the use case for OpenClaw. Maybe I and my life is just too simple, and I’ve admittedly not invested a huge effort into spending countless hours watching breathless YouTubers vying for my attention to figure it out. I have built a few bits and bobs, I feel like I’m ideal in that I’m pretty deep into agentic workflows for work, my house is totally home assistant, I’ve got current tool following models pinned to local 4090’s, I’ve been fine tuning my smaller models, i even have a custom chatterbox based tts/sst pipeline with voice nodes everywhere.

I’d love some OpenClaw master to opine on meaningful use cases beyond clawbook, checking the weather, and telling you about crypto news, as it genuinely feels like something I should find utility for but am just too old or something.

You could ask the same question about any tool ever created. Users who figure out ways to use their agents that are profitable to them make money. Everyone else spends money.

> Did you invest in teknium's company, JumpCrisscross?

Nope!

That's great, but did you invest in Eastern Poland?

You should be looking for a pyproject.toml: https://github.com/NousResearch/hermes-agent/blob/main/pypro...

And a uv.lock is also there...

I might be a little more paranoid than most because of my profession, but none of these projects inspire enough trust to justify being installed - let alone directly on the machine I use every day.

OpenClaw, at least initially, and Hermes both appear to have been heavily astroturfed using all kinds of blackhat tactics, which is a huge red flag to me.

And then there is the code.

My bad... saw the setup.py and quickly posted.

I'm sorry but if this is not a debacle, then we're operating under very different premises:

- teknium1 retitled the original issue to "." and edited the issue text to "."

- Nous Research deleted comments from 4 users, including the issue submitter, and blocked all of them.

- No formal response has been given by teknium or the Nous Research project. It appears they are trying their darndest to brush it under the rug.

Ref: https://news.ycombinator.com/item?id=48318706

Wow, the response from their team was really awful.

Basically: it is a free service, free is good, why are you being difficult?

People running Hermes on local models thought their data was theirs, but what if the model is not the only leakage vector??

And already removed: https://github.com/NousResearch/hermes-agent/pull/46350

tl;dr for people who just read the inaccurate quote: It was the default search provider (for free), if you configured anything else, it was not used. They removed the default.

Did you read it? Given it's all AI slop I wouldn't be surprised if not, but the claim is basically "I had this idea first, I think they stole it from me."

Not that they stole code or even copy, just the idea from a completely open source project (at the time).

Given how many people have posted and released similar systems over the time skills came out and even before, that's a huge claim with no substance to back it.

As Musk and Dorsey have said, IP law is highly incompatible with AI.

Wasn't there some news a while ago that Anthropic and other frontier model companies used a bunch of pirated books to train their models? Are we not all benefiting from the fact that they also crawled a bunch of open code repos?

If something is open source, it's pretty easy to tell if code is pulled directly from another repo and included in a project. It's much harder to know if whatever model was building something pulled from it (through training or simply searching online).