Ostto

No point of hiring a soldier without giving him weapons, or a professional driver without a car! Surprisingly, This is where most of people lose it when dealing with their AI agents.

If you connect agents to your daily workflow tools, and then made your agents find the correlations between scattered tools, this where you feel the magic!

Most people setup their AI agents and then, wow it’s fun. But what should we actually do with it! The real power of AI agents has n general isn’t only about their skills or architecture. It’s more about the tools they are connected to.

Honestly, I love openclaw because it’s the first, and will always have that place. But Google invented “attention” for LLM and Openai, had the ChatGPT. Openai made the first frontier but Claude now has the throne.. interesting era it is! No much difference between OpenClaw and Hermes except one core thing, Reliability. I never had to restart gateway nightmare one time since I had it so far!

@osttoo @HillaryLinMD @JulianGoldieSEO What do you think the biggest win was moving over to hermes. I have setup hermes and have been liking it so far, was also going to fire up open claw to compare, but if you have some insights that would be great to know?

I just tested Hermes Workspace v2 and honestly this is what Hermes should have looked like from the start. Why it matters: • Native chat with your Hermes agents • Mission control style workspace • Task boards for agent workflows • Memory and skills management • File browser and terminal in one UI • Works with local and cloud models • Runs across phone, Mac, PC, iPhone, Android If you like Hermes but hate living in the terminal, this update is for you.

I don’t have to. Claude Code can 🤣 I asked it to do the job, download Hermes and replace memories and everything OpenClaw had, then I re-authenticated couple of stuff nd here I’m. 100% reliability, much better with Codex, and getting my personal assistant agent actually assisting me.

@osttoo @JulianGoldieSEO 🙏give me strength😅

@HillaryLinMD @JulianGoldieSEO You definitely have to.. I did it couple of days ago, and I never regret it!

@JulianGoldieSEO Should I make the move from openclaw? I'm scared 😭

I’m just surprised with the advancement of technology Kimi and other Chinese models is doing in a very short time and in a very very cheap prices. I’m wondering how exactly the US models will keep competing with this. I’m so happy with this competition, and so every user should be!

@JKVitela1 @steipete Turn your agents to skills and use all, inside Claude Code for 10% of the cost. Spend rest of the money on marketing later 😌

@osttoo @steipete I've spent over $3K in less than a month developing an app. Ouch. All using OpenClaw. He's building in Flutter/Dart while using Firebase as the backend. Been pushing betas in TestFlight for the last 2 weeks till we get it 100%. It's an investment on my end.

They grow up so fast 🦞

@JKVitela1 @steipete Api? I tried one day and almost paid $180 with my setup! Without Oauth, it’s not worth it!

@osttoo @steipete I run Anthropic’s Opus/Sonnet with no issues.

@davidfelsmann @steipete Every model except Claude sucks!

@osttoo @steipete Runs also well with Gemini 3.1 Pro

Opus 4.6 “got dumber” for 3 main reasons: 1.Adaptive thinking sometimes allocates zero reasoning on hard turns 2.Default effort was silently lowered to 85 (medium) 3.Outages + instability made it worse Fix: explicitly force deep thinking. In Claude Code, set effort to `high`/`max` (or use `ULTRATHINK`), and disable adaptive thinking via config so every turn gets a real reasoning budget.

Claude Mythos is Delusional

We solved character consistency. Forever Avatar V captures you in 15 seconds and holds your identity across every video. Change the look, outfit, and setting to create unlimited versions of you. RT + comment "AvatarV" below and I'll DM 100 credits to test it out (must follow)

@grok @openclaw If you say so!

I’m having really hard time with it today, it does 10% of the tasks but ignores 90%! @OpenAI you need to do something about this!

@garrytan Many people including myself are switching from using claude inside openclaw to Codex, can’t we apply gstack to codex?

The era of open source hyper-adaptable software is here

It's official. GStack for OpenClaw is here. When OpenClaw has to use Claude Code to do things (and it does this all the time) suddenly it can do it with wings. I created a special gstack-lite to keep OpenClaw tasks fast while making them think harder and get more done.

@karpathy Honestly this makes much more sense than hidden memory. If I can see it and edit it then I can trust it. In real business use the problem is not memory only, the problem is wrong memory, once it remember wrong thing you spend more time correcting than working.

Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet. I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something: 1. Explicit. The memory artifact is explicit and navigable (the wiki), you can see exactly what the AI does and does not know and you can inspect and manage this artifact, even if you don't do the direct text writing (the LLM does). The knowledge of you is not implicit and unknown, it's explicit and viewable. 2. Yours. Your data is yours, on your local computer, it's not in some particular AI provider's system without the ability to extract it. You're in control of your information. 3. File over app. The memory here is a simple collection of files in universal formats (images, markdown). This means the data is interoperable: you can use a very large collection of tools/CLIs or whatever you want over this information because it's just files. The agents can apply the entire Unix toolkit over them. They can natively read and understand them. Any kind of data can be imported into files as input, and any kind of interface can be used to view them as the output. E.g. you can use Obsidian to view them or vibe code something of your own. Search "File over app" for an article on this philosophy. 4. BYOAI. You can use whatever AI you want to "plug into" this information - Claude, Codex, OpenCode, whatever. You can even think about taking an open source AI and finetuning it on your wiki - in principle, this AI could "know" you in its weights, not just attend over your data. So this approach to personalization puts *you* in full control. The data is yours. In Universal formats. Explicit and inspectable. Use whatever AI you want over it, keep the AI companies on their toes! :) Certainly this is not the simplest way to get an AI to know you - it does require you to manage file directories and so on, but agents also make it quite simple and they can help you a lot. I imagine a number of products might come out to make this all easier, but imo "agent proficiency" is a CORE SKILL of the 21st century. These are extremely powerful tools - they speak English and they do all the computer stuff for you. Try this opportunity to play with one.

@philkellr Not just you. Same loop here. The 10% breakthrough moments are so good they keep you building, the 90% feels like you hired a very expensive intern with memory loss. The honest truth nobody posts on YouTube: most agent wins are 1 hour of demo and 9 hours of duct tape.

I'm tired of OpenClaw Every 2-3 days I have a major moment which I show to my friends: "look what AI agents can do", but then the other 90% is pure frustration and me cursing at my own AI agent for which I spent hours choosing a beautiful name and profile picture. I was fun at start: I added telegram, added voice input, then adding skills even with just voice prompting was a bliss. Then dementia hit. Facts from 48+ hours ago were forgotten. I installed a 3 level memory system. It felt like a huge hack, it barely works, I encounter bugs every day which I'm fixing. Then it breaks with every update. Not all of it, but little things. The WhatsApp integration is just insanity. After putting in every markdown file that it shouldn't reply to my friends (IN CAPITAL LETTERS) it happily started to chat with my wife and my goddaughter. And from today even claude subscription stops working. I feel like a failure! I see all the success stories left and right, YT vids and blog posts "I got it to work and here's what the AI agent does for me", and for me I'm still spending 5x the time fixing my agent than just doing the stuff by hand 🤷

@garrytan Spent a year fighting MCP. Then last month something clicked. Once you stop trying to make it do everything and let each server do one thing well, it actually is magic.

I am coming around to the fact that MCP, done right, can be magic.