Deep in Agents, LLMs and automation · Open source at ♥ · Sharing AI gems daily to help you work smarter · Ex-data scientist @Snowflake | @Streamlit ·
📩 DM for Collabs
Joined January 2009
- Tweets35.7K
- Following49.4K
- Followers183K
- Likes11K
pretty mind-blowing.
An AI that learns your preferences directly from your brain activity.
I need to dig into this 👀
Charly Wargnier ♨️ retweeted
Testing ElevenLabs SFX v3 with a heartbeat for a thriller trailer pitch.
Asked for it to sound slightly distant and muffled.
Exactly what I got.
No weird digital artifacts.
Just a natural heartbeat 👀
🤝 Paid partnership
Big scenes rarely come down to one sound, so we built SFX v3 to handle more than ever.
Our latest model lets you create richer, more precise sound effects from a single text prompt, with improved music and vocals.
Now available inside @ElevenCreative and ElevenAPI.
Testing ElevenLabs SFX v3 with a heartbeat for a thriller trailer pitch.
Asked for it to sound slightly distant and muffled.
Exactly what I got.
No weird digital artifacts.
Just a natural heartbeat 👀
🤝 Paid partnership
Big scenes rarely come down to one sound, so we built SFX v3 to handle more than ever.
Our latest model lets you create richer, more precise sound effects from a single text prompt, with improved music and vocals.
Now available inside @ElevenCreative and ElevenAPI.
WHAT SERRO ACTUALLY DOES IS JUST WILD
> joins your daily sync calls
> picks up decisions in real time
> updates your coding agents automatically
> tracks risks across programs
Your agents stay in sync without the manual work.
you can book a demo now at serro.ai
🤝 Paid partnership
Your coding agents are fast now.
The problem? They can move just as fast in the wrong direction.
Miss one update, and they can spend days building the wrong thing - costing you tokens and engineering time. That's why devs are still glued to their monitors.
Meet Serro: the Agentic TPM.
It keeps your people and coding agents working from the same evolving program. 👇 @serroai
ROBYN MIGHT HAVE KILLED INSTINCT
and it's invite-only access
> one sentence launches a fleet of agents... that already know your context 🔥
> zero setup
> works via text or web
Get finished decks, market maps, and briefings.
Only 1,000 invite codes. Comment "Robyn" on Jenny's post.
I'd jump on this 👇
Meet Robyn, the personal agentic platform built around your life and work.
- Tell her what you need in one sentence. No setup, ever.
- Spin up a fleet of agents preloaded with your context that work while you sleep.
- Access it on the web or just text it.
- 20hrs/week saved per user.
I’m Jenny, and I spent 3 years working with Nobel Laureate Eric Kandel, who mapped out memory in the human brain.
We built all of that into Robyn, making it the first AI capable of taking intelligent action.
Invite only access opens today. We’re giving out 1000 invite codes. Link in first comment. Comment "Robyn" for 100 free credits.
NO API?
THAT'S THE POINT.
AgentWeb is built to help agents work across government portals, insurance directories and signed-in sites.
@Andrey__HQ reports 47/47 live tasks completed, a 1.9s median and $3 total.
Definitely one to watch 👀
🤝 Paid partnership
Introducing AgentWeb: reliable web infrastructure for generalized agents.
47/47 real world tasks on live sites. 1.9s median. $3 total.
Request access: agentweb.us
✅ Claude Code
✅ Claude Cowork
✅ Claude Design
✅ Claude Finance
✅ Claude Science
✅ Claude Teacher
✅ Claude Business Analyst
✅ Claude Legal
⬜ Claude HR
⬜ Claude Marketing
⬜ Claude Sales
⬜ Claude Logistics
⬜ Claude R&D
⬜ Claude Procurement
⬜ Claude Accounting
⬜ Claude Engineering
AI AGENTS ARE COMING FOR THE DRAWING BOARD
@snaptrude goes from a brief to a detailed building model, plumbing, electrical and drawings.
It shows you the plan first.
You approve, steer or take over 🔥
very impressive.
🤝 Paid partnership
Today we're launching @snaptrude Agent, the most advanced agent for building design.
It does real design work with you, from a site to a construction-ready LOD 400 model with structure, MEP and drawings. Then can go back to your existing software with your families intact.
About a year ago we bet the company on AI. Honestly the insight came from software engineering. It wasn't long ago that autocomplete felt like a big deal, and now engineers direct agents that write a lot of the code. I think the same shift is coming to how we design buildings, and it's already started.
Most designers I meet aren't short on skill, they're short on time. Take the call every design team dreads, the client cuts the budget by 30%. Today that's a bad month for everyone. With the agent you're the director. You decide where the cost comes out, and it updates the layout, coordinates the structure and MEP, and redoes the drawings. So when design exploration gets this cheap, we go from 3 options to 300, and more options means better buildings.
Since August our users have gone through more than 140 billion tokens, and firms like Jacobs, Studio+, Kajima, VMDO, Dekker and hundreds of others use Snaptrude today. In our early access, more than 2,000 designers have run over 25,000 tasks through the agent since September.
We also built a benchmark for this, AECBench, because in AEC an almost correct answer is still wrong. It gives AI the same brief an architect would get, has its design in a real BIM model, and scores the result against the brief and against how architects review design. We're publishing the first results today, link below.
Thank you @prashanthp at @Accel and Shub and the team at @foundamental for backing us when this was still a bet, and the Snaptrude team, who built every bit of this. Really proud of you all.
Thanks to our investors, @scottbelsky, @andreasklinger, @thilokonzok, @immad, @CindyXBi, @DanilaVladi, @jmwass, rahulchaudhary, @adamecourt, Zach Ginsburg, Alex duff, Paul grossinger, really appreciate all the help along the way.
your agent still has to read the PDF...
the tables.
the formulas.
the columns that turn into nonsense the second you flatten them into plain text.
OXR is a 1.3B document parsing model that turns PDFs and document images into structured Markdown or JSON, with coordinates and reading order.
it handles 13 document element types, chemical structures included 🔥
if you're building RAG or document workflows, you can't afford to skip this 🧵↓
🤝 Paid partnership
try the demo, or grab the code and weights below:
github.com/SoMarkAI/OXR
I hope you liked it!
If you found this useful, a like or RT goes a long way.
Follow me → @datachaz for insights on LLMs, AI agents, and data science.
your agent still has to read the PDF...
the tables.
the formulas.
the columns that turn into nonsense the second you flatten them into plain text.
OXR is a 1.3B document parsing model that turns PDFs and document images into structured Markdown or JSON, with coordinates and reading order.
it handles 13 document element types, chemical structures included 🔥
if you're building RAG or document workflows, you can't afford to skip this 🧵↓
Most OCR models come as-is.
If they can't handle your old scans, tough luck.
@OpenBMB ships MiniCPM-OCR with open weights *AND* fine-tuning code.
Now even small archives and university libraries can adapt the model to their own documents.
Smart move.
🤝 Paid partnership
🎬 MiniCPM-OCR in action — running locally on iPhone Duo and iPad.
Parse fast and accurately. Guard the results. All in your hands. 🙌
Handwritten notes, complex formulas, newspapers, poor-quality scans—real documents put OCR to the test.
📄 MiniCPM-OCR 1.0 — SOTA OCR performance and speed at 1B scale.
It achieves 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, combining accurate document parsing with efficient inference.
🛡️ MiniCPM-OCR Jev — A 2B decision model that checks OCR accuracy.
It approaches Qwen3.5-397B-A17B on JevOCRBench and works with outputs from different OCR parsers.
Watch it compare parsed text, formulas, and tables with the original image and assign 0–1 correctness scores—helping you pick better results and identify what needs human review.
🔓 Open weights. Deploy your way.
Run with llama.cpp, vLLM, SGLang, or Ollama. Customize with open-source fine-tuning code.
Watch it in action. 👇
🔗 GitHub: github.com/OpenBMB/MiniCPM-O…
🤗 Hugging Face: huggingface.co/spaces/openbm…
👉 Try the Demo：platform.modelbest.ai/consol…
Use the API：platform.modelbest.ai/consol…