Atanas Lambev

Product designer, ex teacher and father of two night furies.

[Peter Nikolow @PeterNikolow]

"Against that backdrop, a general-purpose Azure Linux is the logical next step. Microsoft went from consuming Linux, to shipping Linux internally, to shipping a Linux distribution anyone can run."

https://t.co/Ueo31JDUr5

[LM Studio @lmstudio]

Meet LM Studio's mobile app.

Your local models, now in your pocket.

[Peter Nikolow @PeterNikolow]

Learn SQL Once, Use It for 30 Years by @FagnerBrack https://t.co/2tbNPJwdTl

[Peter Nikolow @PeterNikolow]

Introducing Gemma 4 12B: a unified, encoder-free multimodal model @google https://t.co/MPeV1hZPgf

[Nous Research @NousResearch]

The next evolution of Hermes Agent is here!

Introducing Hermes Desktop: everything you love about Hermes, now native on your machine.

First demoed in Jensen's GTC keynote, it's now in public preview.

[Atanas Lambev @ALambev]

@Saboo_Shubham_ everythink is perfect but in this enviropment don't have access to file system and I start using again terminal ....

[YanXbt @IBuzovskyi]

https://t.co/KnxXYg1sSp

[Shann³ @shannholmberg]

how to create marketing specialist agents in Hermes Agent

send this visual to your agent to get started

[Kanika @KanikaBK]

I found this last night and I have not stopped thinking about it.

HERMES JUST LAUNCHED HERMES DESKTOP. 100% FREE.

It is a free desktop app that gives Hermes Agent a proper interface. One place for everything.

What is inside:
�� Auto install and setup, no terminal needed
↳ Streaming chat with token tracking
↳ Multiple agent profiles
↳ Memory you can actually see and edit
↳ 14 tool categories including web, browser, image gen, and voice
↳ Scheduler for automated tasks
↳ 16 messaging gateways including Telegram, WhatsApp, Discord, Slack, and Signal
↳ Full conversation history with search
↳ Backups and logs in one settings screen

Works with Anthropic, OpenAI, Gemini, Grok, Groq, Ollama, and more.
Hermes Agent is the brain. Hermes Desktop is the cockpit.

Free. Open source. Mac, Windows, and Linux.

[WorldofAI @intheworldofai]

🚨BREAKING: OpenAI's Codex is now completely FREE to run locally with Ollama.

No API costs. No rate limits. 100% private on your machine.

You can now use both the Codex App and Codex CLI with powerful open-source models like DeepSeek V4, Gemma 4, and Qwen 3.6.

Here's how to set it up in minutes:

[Nous Research @NousResearch]

Hermes Agent now has access to hundreds of browser skills through @browserbase’s new https://t.co/SZ93w9Z0mk hub, so agents can more reliably perform any task on the internet. You can try a skill from their catalog or contribute your own.

[Atanas Lambev @ALambev]

AI agents are evolving beyond simple chat interfaces. 🚀

Hermes Agent is a great example of the new generation of local-first AI tools combining:
⚡ CLI workflows
🌐 Web dashboards
🔗 Gateway services
🧠 Local AI models
🔄 Automation pipelines

I created a visual CLI cheat sheet

[Atanas Lambev @ALambev]

@PeterNikolow ��ъде е твоя приятел да ти каже че и те са хванати от гората?

[Barry Schwartz @rustybrick]

Google to no longer support FAQ rich results https://t.co/4FwDBmKRsX

[Peter Nikolow @PeterNikolow]

Accelerating Gemma 4: faster inference with multi-token prediction drafters @google https://t.co/gsYT6NlbeL

[Arena.ai @arena]

MiMo-V2.5 by @XiaomiMiMo is the #11 model (#3 among open) in Code Arena for frontend design. A new MIT-licensed open source model with 1M context, it also ranks strongly as an open model in Text and Vision Arena.

Code Arena: frontend webdev design
- MiMo-V2.5-Pro: #3 open (#11 overall)
- MiMo-V2.5: #5 open (#18 overall)

Text Arena: text prompts
- MiMo-V2.5-Pro: #2 open (#22 overall)

Vision Arena: visual input reasoning
MiMo-V2.5: #7 open (#37 overall)

Congrats to the @XiaomiMiMo team on this achievement!

[Atanas Lambev @ALambev]

@googlegemma https://t.co/XJeLw9Gw5i

[LM Studio @lmstudio]

Nemotron 3 Nano Omni is now in LM Studio!

A new 30B multi-modal MoE from @nvidia

Supports Image input, reasoning, and tool use

Requires ~25GB to run locally 🔥🚀

https://t.co/0pdO0WU7Gc

[Atanas Lambev @ALambev]

1. Introduction: Why M1 Max is Ideal for Local Models

Apple Silicon computers, specifically the M1 Max with 64GB RAM, offer a unique advantage for running Large Language Models (LLMs) due to their Unified Memory architecture.
https://t.co/XJeLw9Gw5i