Today we release Mirage: A 22 MB visual-language model that runs scene descriptions + object detection + OCR + segmentation + spatial relations analysis + extractions + decisions, in a single pass.
It can do all that in 74 ms on Samsung Galaxy S26 NPU or 107 ms on its CPU.
Mirage has a 7.8M encoder + a 40.8M decoder at 2bits, and describes images in English, German, French, Spanish, Italian, Dutch and Polish.
We trade general language capacity, to compete top small VLMs today (SmolVLM2-500M, LFM2.5-450M and Florence2-230m) on these tasks.
On 256 VQAv2 questions, feeding Mirage's structured output and full trace to text-only Qwen3-0.6B raised its score from 9.3 to 31.3 out of 100, without fine-tuning either model.
Read more and benchmark it yourself here:
https://t.co/QNlavPrHt2
The Hermes Agent Plugin Hackathon starts now!
It runs for 7 days, with $20,000 in cash prizes and more.
Plugins are the most powerful way to extend Hermes Agent, and we want this hackathon to show what they can do. A plugin can change anything from the model Hermes runs on, where it stores its memory, where it runs commands, which messaging apps it works in and what Hermes Desktop shows. Plugins in the marketplace already let Hermes do things like control a phone or turn a photo into a printable 3D model.
Every kind of plugin is eligible, so build whatever functionality you want Hermes to have. We'll list accepted entries in the new Hermes Marketplace, where every Hermes user can install them.
Prizes
1st: $10,000 + neon sign + merch + $1,000 creds
2nd: $5,000 + neon sign + merch + $1,000 creds
3rd: $2,500 + neon sign + merch + $1,000 creds
4th: $1,500 + merch + $500 creds
5th: $1,000 + merch + $500 creds
Runners up (x5): merch + $250 creds
Submissions are due 5PM EST on Nov 11th. To enter:
1. Open a pull request that adds your plugin to the Hermes plugin catalog: https://t.co/mXvYukJ0mZ
2. Post a demo video on X and tag @NousResearch
3. Submit both links through the form: https://t.co/jlduHHW3dr
Your entry is the plugin itself. Judges score it on usefulness, reliability, polish and creativity, and they favor plugins that do more than a prompt or a skill could. Keep the demo under 90 seconds and show the plugin working.
The developer guide shows how to build and test a plugin: https://t.co/FVGjSgjNoV
When submissions close, we'll open a thread for every entry in the Nous Research Discord, so you can browse all the plugins and talk to the people who built them.
You can submit the form as soon as your pull request is open. The catalog checks run once a maintainer starts them, and we review entries every few days.
If you have any questions stop by the Nous Research Discord: https://t.co/qxek9haYeb
GLHF!
@IndianTechGuide For @IndianTechGuide , These Are Already Implemented Over All IITs Like A 5-6 Years Ago And Our Professor From IIT Madras Holds Patent For This, Poor Works From You Bruhhhh! Do Some Proper Researchhh!
Either way, I’m not complaining. If you’ve been waiting to try proper agentic coding models without burning credits, this is the moment.
Go grab them before they vanish.
Who else is lowkey shook by this?
https://t.co/S9D6O1e4tW
Bro… how the hell is @OpenCode just giving this away for free right now?
GLM-5.3-Flash
DeepSeek V4.1 Flash
Big Pickle
Space Bunny
MiMo-V2.6
Nemotron 3 Ultra + 3.5 series
LongCat 2.5
Muse Spark 1.3
and a whole stack of others
All free.
Limited time.
Some with zero-retention.
@opencode No training on your data.
You open OpenCode, type /models, and suddenly you’re running models that normally cost real money… for $0.
This doesn’t feel real.
Like… are they just collecting feedback? Testing the market? Or did someone forget to turn the paid switch on?
@poteto Hi There! I Was Wondering Still There Is No Single Official Arch Linux Build or AppImage Version Of Grok Bots To Use, Do We Get That? Is That In Plan? Thanks Btw