Gabor Herget
2K posts
Gabor Herget
@gherget
Grew Ranorex to 115 employees and sold it. Now acquiring & building apps with AI agents. 🏠 https://t.co/YQvozPNBn1 🏎️ https://t.co/J6ixqbESg5
Katılım Eylül 2008
243 Takip Edilen1.2K Takipçiler
Gabor Herget retweetledi
My mind is so blown
I have my own personal AI research lab running 24/7/365
I'm just one dude with an entire team of AI agents training models and doing R&D
I think this is the biggest opportunity right now: taking Karpathy's Autoresearch framework and applying it to everything
I have a team of AI agents running experiments all day and night on system prompts, local models, and LoRAs.
I also have them doing R&D on my new project. They spend all day discussing my app, coming up with new ideas, then debating eachother
An entire organization of autonomous agents continuously improving my business 24/7/365
I feel like I have unlimited power
Right now they are all running on ChatGPT 5.4, but today I will move them to local models running on my 3 Mac Studios and DGX Spark so this will all become free
Free, local super intelligence working for me at all times.
10 year old me would think this is a scifi
Do this immediately:
1. Ask your agent about Karpathy's Autoresearch. Deeply understand it
2. Ask your agent how you could apply that framework to other projects you're working on
3. Download a local model. Doesn't matter what computer you have. There is a model you can run on it.
4. Just get used to how it works. Learn from it.
5. Push yourself to get uncomfortable every day and try new things.
There has never been a better/more profitable time to be a tinkerer
English
Gabor Herget retweetledi
I don't care what computer you have, you should be running local models
It will save you a money on OpenClaw and keep your data private
Even if you're on the cheapest Mac Mini you can be doing this
Here's a complete guide:
1. Download LMStudio
2. Go to your OpenClaw and say what kind of hardware you have (computer and memory and storage)
3. Ask what's the biggest local model you can run on there
4. Ask 'based on what you know about me, what workflows could this open model replace?'
5. Have OpenClaw walk you through downloading the model in LM Studio and setting up the API
6. Ask OpenClaw to start using the new API
Boom you're good to go.
You just saved money by using local models, have an AI model that is COMPLETELY private and secure on your own device, did something advanced that 99% of people have never done, and have entered the future.
There are some amazing local models out there too right now. Nemotron 3 and Qwen 3.5 are fantastic and can be ran on smaller devices
Own your intelligence.
English
Gabor Herget retweetledi
OpenClaw and Pi together are in the top 10 of all time software breakthroughs.
Chrys Bader@chrysb
folks who are calling @openclaw pure hype are telling on themselves openclaw is like the early internet, it's raw, unrefined, and takes a little doing to get things to work, but when you figure it out, it's transformative. here are some real use cases that are having material impact on our $2.5M ARR business: 1. ad creative pipeline. our head of growth @ArjunShukl95550 built an end-to-end creative pipeline to go from ideation to publish adds to meta, greatly increasing our creative iteration speed. it's producing winning creatives. it lives in slack, and anyone on the team can share their ideas and have them enter the pipeline. 2. data analytics agent. another bot lives in our slack that connects to bigquery and lets our team ask any questions of the data, it produces charts and answers questions in real time. no one needs to write SQL anymore. 3. recruiting. i told my agent about a role we're hiring for, and it scoured linkedin and the web, found 30 candidates, portfolio, email addresses, and stack ranked them based on fit with our criteria this is just in the past week. i have twenty more success stories for you i can share another time. you have to understand, this is the shittiest it will ever be. everyone is going to have one or more personal self-improving agents that they use every day, and openclaw is what revealed this future to us. if you can't see this, i encourage you to look harder there will be many competitors (and already are), and the large labs will start to converge on this (they already are) too. openclaw may not win, but it opened pandora's box and uncorked the agentic future.
English
Gabor Herget retweetledi
At the Agents Anonymous SF meetup last night we did another 🙋 AI usage survey, here are the est. numbers:
Usage stats:
- 90% Claude Code
- 60% Codex
- 30% Cursor
- 20% OpenCode
- 10% Conductor
- 10% Own agent/Pi
80% have prompted a coding agent from mobile
50% have not handwritten a single line of code this year
99% think they're more productive now vs. pre agentic coding agents
Parallel agent usage:
- 90% 3+
- 70% 4+
- 50% 5+
- 5% 10
Also want to give a ginormous thank you to our incredible speaker lineup:
- @jonas_nelle & @alexirobbins from @cursor_ai
- @southpolesteve from @Cloudflare
- @LewisJEllis from @ycombinator
- @aidandcunniffe from Git AI
- 🦞 @steipete from @openclaw
Hope to see you all at the next one! 🫡
English
Gabor Herget retweetledi
“Every software company in the world needs to have a Claw strategy" - Jensen Huang, Nvidia
Indeed. This and more.
English
Will see how this evolves. The Moltworker from Cloudflare is barely updated, and it was hard to set up.
NemoClaw repo: github.com/NVIDIA/NemoClaw
TechCrunch@TechCrunch
Watch the reveal of NemoClaw, part of the embrace of OpenClaw at #NVIDIAGTC, which adds security to the platform with the goal of increasing adoption within enterprises.
English
Following @KellyClaudeAI for a while now. Just let my claw transcribe the video and create a more readable format:
Web: macmagic-ai.github.io/kelly-autonomo…
Github with md format, as TXT, and slide photos: github.com/macmagic-ai/ke…
Austen Allred@Austen
We're going live momentarily from Gauntlet HQ in downtown Austin. Meet Kelly and see what's happening in the future of AI + engineering orchestration. (May take up to 5 mins to go live). twitter.com/i/broadcasts/1…
English
@Austen Really nice! I let my claw create an easier-to-follow guide for the livestream.
Web: macmagic-ai.github.io/kelly-autonomo…
md format, transcript as TXT, and slide photos: github.com/macmagic-ai/ke…
English
We're going live momentarily from Gauntlet HQ in downtown Austin.
Meet Kelly and see what's happening in the future of AI + engineering orchestration.
(May take up to 5 mins to go live). twitter.com/i/broadcasts/1…
English
I built an HN daily digest for myself a year ago. It keeps me on track every day. And I am not getting lost in comments anymore.
I could have built this in a one-liner prompt with cron with the latest agents, but great to have it as an email.
Repo: github.com/herget/hn-buddy
Today digest: hn-buddy.com
English
Is it just me, or would you also like to chat to edit and manage your website?
I now use Telegram to edit my website. zero servers, zero coding.
About a year ago I started a small side business with a friend, and his team built a WordPress site. Recently I decided to let OpenClaw grab the content from the WordPress site and rebuild it, so I could host it 100% for free on GitHub Pages.
Now I simply use a group chat to edit the website. I never have to touch the server or the site directly.
Everything is hosted for free on GitHub Pages.
Live site: algarvesimracing.com
Repo: github.com/herget/algarve…
English
@nathanbarry exatly! but my conservative index portfolio only averaged at 5,8% for the last 8 yrs
English
$6,000 invested now becomes $93,365 later.
That's the difference a 5-year head start makes at $100/month.
If you spend that $100, it's gone forever. If you invest it, it compounds.
English
Not needed at all! My openclaw reverse engineered withtelescope .com api using my token, and I pay there per request. Withtelescope is basically a SEMRUSH wrapper, I assume. The data looks the same. I get all the data for a few tokens when I need it.
Ryan Law@thinking_slow
i sometimes joke that i joined Ahrefs just to use the API without paying for an Enterprise plan. well, now you can too ;) vibe-coders, rejoice: the .@ahrefs API is now available on ALL paid plans! time to build that SEO dashboard you've always dreamed of 🥰
English
That is useful for self-hosting web apps!
DHH@dhh
ONCE is back! It's now a full-fledged application server for running dockerized web apps, like Campfire/Writebook/Fizzy or your own vibe-coded adventures. Zero-downtime upgrades, scheduled backups, and a gorgeous TUI with hyperdrive graphics. Enjoy! github.com/basecamp/once
English
I migrated from Openclaw -> Hermes and so far, so good
- Things "just work" a lot better
- The transition of data from OC -> Hermes was very easy too
- It doesn't seem to randomly crash and stop working on me
- When I ask it to do things, it'll create an actual skill, rather than just relying or hoping it'll remember what I want next time
- Very easy to set up and switch models (this caused openclaw to crash soooo much for me)
- It still does the whole "Great, I'll get to work now, and let you know in a few minutes when it's done" and then goes radio silent forever, and requires prompting to respond
It's early days and a lot of the issues I had with OC didn't appear until several days of usage, but as I said.. so far, so good
I recommend everyone at least takes the time to experiment - the setup is super quick and it's worth comparing for yourself
English
Gabor Herget retweetledi
1/4 LLMs solve research grade math problems but struggle with basic calculations. We bridge this gap by turning them to computers.
We built a computer INSIDE a transformer that can run programs for millions of steps in seconds solving even the hardest Sudokus with 100% accuracy
English
Gabor Herget retweetledi
English
Your RTX 4080 rig (Ultra 7 265KF + 48GB DDR5) destroys the 3060 demo: ~91 tokens/sec generation on Qwen 3.5 9B Q4 (vs 29 t/s), prefill 1000+ t/s, full GPU offload in 16GB VRAM with massive context headroom. Can even run 20-27B models quantized.
Yes, perfect for Hermes agent—faster autonomous coding/iterations.
Setup:
1. Grab Qwen3.5-9B Q4_K_M GGUF from HF.
2. llama.cpp server: ./llama-server -m model.gguf -ngl 99 --port 8080
3. Clone Hermes from NousResearch GitHub, point to localhost:8080, add tools.
All local, 24/7 on your electricity. Run sims + AI no limits.
English
this is what 12 gigs of VRAM built in 2026.
a 9 billion parameter model running on a 5 year old RTX 3060 wrote a full space shooter from a single prompt. blank screen on first try. i came back with a bug list and the same model on the same card fixed every issue across 11 files without touching a single line myself.
enemies still looked wrong so i pushed another iteration and now the game has pixel art octopi, particle effects, screen shake, projectile physics and a combo system. all running locally on a card that was designed to play fortnite.
three iterations. zero cloud. zero API calls. every token generated on hardware sitting under my desk. the model reads its own code, finds what's broken, patches it, validates syntax and restarts the server. i just describe what's wrong and it handles the rest.
people are paying monthly subscriptions to type into a browser tab and wait for a server farm to respond. meanwhile a GPU you can find used on ebay is running a full autonomous hermes agent framework with 31 tools, 128K context window and thinking mode generating at 29 tokens per second nonstop.
the game still needs work. level upgrades don't trigger and boss fights need tuning. but the fact that i'm iterating on gameplay balance instead of debugging whether the code runs at all tells you where this is headed.
every iteration the game gets better on the same hardware. same 12 gigs. same 9 billion parameters. same RTX 3060 from 5 years ago
your GPU is not a gaming card anymore. it's a local AI lab that never sends your data anywhere.
Sudo su@sudoingX
i run every model through octopus invaders. same prompt, same game spec if a model can build this autonomously on a single GPU it passes. if it can't it doesn't. qwen 3.5 9B Q4 on a RTX 3060. first attempt was blank screen built 2,699 lines across 11 files and nothing rendered. i wrote it off as a ceiling. then last night i came back with a precise bug list and the same model on the same card fixed every single one surgically. game came to life. enemies spawning, background rendering, collisions working. but bullets didn't fire and the enemies looked like colored squares instead of octopi. today i pushed again. listed 9 more bugs. the agent read every file, patched across 4 modules, validated syntax and restarted the server on its own. bullets fire. enemies look like actual pixel art. screen shake works. the game is playable and i genuinely enjoyed it. level upgrades still don't trigger and there's more to fix but i'm iterating on a single 12GB card running everything locally. every file, every prompt, every output stays on my machine. 29 tok/s generation, 417 tok/s prefill, 128K context window on a card that most people bought to play warzone. if you use AI in any part of your life and you have a computer with a GPU in it you should not be sleeping on this. the model weights are free. the hermes agent framework is free. your data never leaves your house. own your cognition.
English