I built a real-time voice agent that runs entirely on a 4GB VRAM laptop.
No cloud APIs. No managed services. Just Go, Python, and gRPC.
Sub-1.1s from speech to first audio byte.
Here is how it actually works ๐งต
@anurag__kochar naah manu paaji has less viewer himself, it wont benefit your reach, hitesh x piyush would be great as mostly people watch theirs only.
3 days after Jev was introduced we got its open source alternative.
and now just a day after @OpenAI released their Dots we already have its open source alternative.
God Bless software engineering and ofc OSS.
We are launching Open Dots, run the same capabilities in 1/10th of the cost
OpenAI shipped Dot yesterday for Pro users.
Ours is open source, runs on your Mac and cheaper
Here's how it works:
- each dot has its own browser that stays logged in securely
- it can use and setup triggers on your Gmail, Calendar and 1,500 other apps
- you can call it and give it things to do while you talk
- dots can coordinate and schedule reminders
built with @composio@OpenRouter
free and open source: https://t.co/f7KctlpMBj
@SridharSaatvik@mutton2pyaza ig country context is also needed, if you consider genZ of the world then the facts are true, but if you are country specific then it can be a different story.
after knowing about:
- muse
- grok bot
- mo
- fo
- dots
- and all sort of agents, idk what comes next...
I want a simple single use-case from, an agent/ai which is capable of merging with my work (email, chats, etc, how i reply) they understand my ways by looking and asking.
ML challenge round 1 ended and we have submitted the code as well.
when ppl were buying others code/output, our team felt a whole new experience we were attacked. soon will be writing a blog on the incident.