I still use it and find it helpful.

My OpenClaw instance uses an Obsidian project as its memory. Mainly, it's just my main day-to-day LLM that I access via WhatsApp, but instead of the memory being locked away with a specific vendor, it's stored in version control that I can read and edit. That reason alone makes it compelling to me. When a better LLM comes along, I can just switch, and my memory and system prompts come with it.

However, I also use it for calorie/weight/workout tracking, to-do lists (bill, birthday, event reminders), and to support my various life admin tasks. I don't give it access to much at all, except a few skills that give it read-only access to some data.

Hasn't given me a 10x productivity boost or anything. It's just handy.

I wrote an article on it, if anyone is interested: https://notesbylex.com/openclaw-the-missing-piece-for-obsidi...

I’ve also found it useful for personal stuff. For example I have my OpenClaw bot in a family group on Telegram and everyday it asks my family members stories from their lives that it meticulously documents and uses as a basis for further questions in the future and has so far managed to build a rich family history spanning 50 odd family members (a project I had always been planning to do for never found the time to).

This is a great idea! I’d be curious to learn more about your setup, particularly how it asks your family and follows up with further questions? Does it do it based on a graph of your family it builds real time? Or is it smart enough that you just prompt it to “follow up with more questions”? I’m having a hard time imagining it asking my family engaging questions they won’t just say, “I don’t remember”.

I can't relate to this need to fully explore and then document everyone's history - I can have a conversation for an evening and forget everything the next day, and I'm happy with that, the truly important things (to me) will distill themselves naturally.

A case of different strokes for different folks I suppose.

In my case, I was curious about my ancestry and Nepal doesn't currently have an equivalent of an ancestry.com therefore the best source of the information is my family themselves while they're still alive.

I am weirded out but this, I find it horrific, like some kind of mind zombie, leeching humanity from your family members.

Someone somewhere is thinking they're connecting with you and sharing their humanity but they're just shoveling their soul into a machine that is "meticulously documenting" them.

Sorry, but ick.

To give a different perspective: archival is important. If nobody does this job, generational knowledge is lost at some point.

I talked plenty with my grandpa, but I'm sure he didn't even tell me 20% of his life.

And my other grandpa died when I was still a kid, so I didn't even get to have adult conversations with him.

Imagine making this available to your grandgrandgrandson.

Yeah, but you're kaoD. You're a bonafide person. You should talk with other people; it's good. (We're chatting right now.)

That's quite different from chatting with a bot that pretends to be human. (Do you want to chat with my bot?)

Yes. And I will die along with the memories from my grandpa. Most of them died already with him, and I don't remember all our conversations.

I have no kids but, even if I did, let's say I'd pass 20% of the 20% he passed on to me, and they pass 20% of the 20% of the 20%... You get the idea.

Heck, I already forgot 50% of my life since I don't have a journal!

This is not an "either" situation. Archival is important.

People write memories for a reason. This is automating the process, not superseding human communication.

I am the sort of person that never took photos (live in the moment yadda yadda). 15 years later, I'm starting to regret it.

Why does it have to be black and white? Why can't a bot do the exploration and notetaking along with people in the channel?

That's not how I interpreted it as being in this instance, but it could certainly be that way.

I guess that'd be like keeping all correspondence in a shoe box (to be reviewed later -- or maybe never), or maybe the automated recording of my phone calls with others (which is completely legal where I am; I don't even have to tell them).

And I suppose whether I felt that would be creepy or not depends a lot upon intent, and consent.

If the intent were pure and good, and the consent both informed and granted, then I'd have no problem with any of this at all -- whether a shoebox, a tape recorder, or a bot is involved in taking the notes.

I called my parents, told them about the idea, they never even had Telegram before we started this project but they especially joined when they learnt that I was trying to build a family history. They are native Nepalese speakers therefore the system promptensured that the bot always responds to their questions and answers in Nepalese.

Btw my family know they are talking to the bot and they know that the bot is taking notes for our benefit. And I am in the channel and I enjoy reading those stories myself and would have never thought to ask those questions myself. Sometimes I ask the follow up questions myself too...

Well that makes it a lot less bad, it sounded from your post like it messages on your behalf and as you.

If it identifies as a bot then I find it a lot less objectionable.

I still wouldn't do it myself, but I can put the pitchfork down.

I actually think this is cool. How is this different than sitting people down with a camera every day and asking for a new random story? we won't be around forever and documenting it is one way to keep memories alive in people's minds

I was surprised myself how engaged my family have been with the bot. And equipped with the knowledge of our family history, it is able to ask deeply informed follow up questions! I would recommend trying it!

You are making a lot of assumptions.

I hope OP is using some self-hosted local model to document their family archives

This is actually a really interesting use case for a local model.

The writing might be a bit mediocre but it would capture all the information.

Parent post really stumbled on a great idea here.

Wow. This is a really cool idea. I am using Obsidian for family history, but I never thought to let people chat with it and update it via OpenClaw.

This is to the people who are highly against this - when you read a book you are doing this - talking to others across time and space. This isn't that much different.

I used it very similarly to you, but found it to be about $3.50 per day, or $100 a month. It wasn't worth that.

My minimax has liberal usage at $10 per month, if you’re not looking for some amazing model.

Minimax 2.7 gets confused too often and misses a lot of things. GLM 5.1 is better, closer to a Sonnet style model, but also significantly more pricey.

minimax 2.7 is great at smaller tasks. I use it for simple subagents and it is capable and I don’t come close to using the quota.

Couldn't you use it with a Codex subscription? Plus is $20 per month

That's Anthropic. Codex is OpenAI.

For what it's worth, codex doesn't yet seem to be aggressively terminating accounts or invalidating auth tokens if they detect usage in a non-first party tool. Whether that will continue to be the case or not a gamble though.

Claude is not Codex.

Try opencode go using kimi - its more than enough for most usecases unless you try something really stupid that you shouldn't be getting openclaw to do directly, like coding.

Z.ai explicitly allows you to use it with OpenClaw on their plans.

I find it funny you call it an Obsidian project.

It is just folders and MD files. You are not even locked-in with Obsidian.

Or maybe OpenClaw is reading the graph view?

Yeah, not locked in with Obsidian.

I just use it as a Markdown viewer/editor, and it handles updating links across notes when a file is renamed. There are some handy conventions that Obsidian encourages, like Daily Notes, templates and linking across notes, enough to call it an Obsidian project, but yeah - it's just markdown. I don't even use the [[Wiki-links]] style that it uses by default.

This is roughly how I use it as well, except I made it a little bit more proactive and actively chases me whether it should track certain things in OmniFocus and chases me about completing overdue tasks or other things I would otherwise forget.

I keep data collection out of the LLMs. I have separate scripts that push and pull data from external sources. So I don’t need to provide the LLM with auth keys, and the things it can do is very limited.

Interested in the calorie tracking (have done amateur bodybuilding). Are you mostly cooking your own meals? Wonder if scanning items and tracking more loosely (a more forgiving myfitnesspal) would be helpful for you? Its on the roadmap of things I'm looking to build for myself (just made this last weekend for buying tovala meals: http://brovala.site)

Why oh why is openclaw an improvement for workouts and calorie tracking?

MyFitnessPal takes a lot of clicks to log one meal, I can just use natural language with openclaw.

What is the accuracy of this method vs manual entry?

When I message my claw "Mark that I had 825 calories for lunch today", it has marked down 825 correctly 100% of the time so far.

It shows me way fewer ads than all the popular fitness apps and loads way quicker since it doesn't have to load like 10MB of ads for me to enter one number, so it seems like a good improvement.

I do not think it's an improvement over an excel sheet, but as the average openclaw user, I would rather pay anthropic $10/day in API credits than create a google sheets document.

I do something similar with Claude Code. I say, "I ate a single serving of that Toasted Beef Ravioli that Aldi sells." Claude web searches, finds it, gets its nutrition info, then uses gspread to add it to the daily food log tab of my spreadsheet.

So much less hassle, lower activation energy needed than with MyFitnessPal.

This is basically the same setup as mine, except I built a grocery price crawler, that spits out a weekly menu along with a check-box shopping list straight into my google drive. Wife loves being able to just type "we need toothpaste" or whatever into Telegram and whenever we go to do our weekly shop we get an up to date shopping list optimised for prices and our dietary preferences.

Before getting side-tracked by other projects I was also going to build a kind of family archiving function like someone in the comments also mentioned. Just to quickly be able to record small/funny family moments.

Thank you for this detailed writeup. If it's not a secret - what is your monthly ballpark figure. I'm planning to deploy an instance during the weekend, for light - medium usage. Can't gauge costs.

Hi,

You mentioned switching out LLM backends. Would you think that lesser models e.g. one of the recent Qwen variants would work for your use case?

Do you build out your own information hierarchies and tell the model to use as-is, or do you let it organize everything itself?

I already had the hierarchy from years of maintaining the notes, but for new things I do collaborate with the model on how best to structure stuff and get it to refactor when needed.

Great article, thanks for sharing. How much does it run you a month roughly?

I recently switched to Codex using my ChatGPT Plus subscription, so only $20 a month or so. Before that, using Opus 4.5/6 it was like $100-150.

Opus was by far the best at the job, but Codex with GPT 5.4 is decent.

That's exactly what I want to use it for, thanks for writing an article about it !

> I can't traverse as much land on foot as my ancestors did, but I can travel further by car/plane/etc

Which is partially how we found ourselves in the midst of an obesity epidemic.

Only either indirectly or extremely partially. Everybody was driving by the 40s in the US but the obesity epidemic didn't start until the late 70s. Really, obesity is an example of exactly what the GP was talking about- our evolved relationship with food is not inherently good, and it's better for us to change our behaviors than to abandon our advancements and return to the food-scarce world we're adapted to.

>our evolved relationship with food is not inherently good, and it's better for us to change our behaviors than to abandon our advancements and return to the food-scarce world we're adapted to.

So are you arguing we should change our relationship with human intelligence? What does that even mean?

My intent was to argue that the obesity epidemic is not a supporting analogy for their point. I didn't mean to imply that the problems with it analogize back to AI.

I've found that most non-tech people are indifferent or, at worst, utterly bored by any mention of AI.

The tech people are the ones that have the strongest opinions one way or the other.

That is my experience, as well.

I had always assumed that all of them shared the pseudonym of Satoshi, along with Nick Szabo.

Back wrote the white paper with input from Hal and Nick Szabo. Sassaman did the coding work on the client. Sassaman had the keys to the Satoshi wallet, hence it never moving since his passing.

Since Satoshi is a collective, it means that each of them individually can claim, without lying, that they're not Satoshi.

That's my uninformed guess.

This very interesting hypothesis and solves multiple issues at once, has anyone attempted debunking it?

Ah yes, I guess wait for full release

It has hit the mainstream imo. Most people are content with the amount of music already available.

I'm a real user. I've found all sorts of uses for it, from calorie/fitness tracking to birthdays and gifts. I love how well it integrates with an existing Obsidian vault. I wrote a blog post about it, if anyone is interested: https://notesbylex.com/openclaw-the-missing-piece-for-obsidi...

It's this but with a lot of handy features.

The mass-poverty and climate changed ravaged world parts, I could definitely see.