atomicbot.ai

OpenClaw and Hermes Agents.
Local Ai Models. or Cloud.
Private and Open Source.
team: @gladkos @danyurkin @sosidudku

[atomicbot.ai @atomicbot_ai]

We released iOS app for Hermes Agent 📱

Connect to your self-hosted agent over Tailscale, Cloudflare Tunnel or ngrok. Or deploy on a VPS. Run tasks and manage your agent from anywhere.

[atomic.chat @atomic_chat_hq]

New Google Gemma 4 12B claims near-26B performance - we tested both!

We ran both models locally on one RTX 4090 and gave each the same task: write a self-contained HTML5 canvas animation with real physics in one file without libraries. Three scenes - a Galton board, two blocks colliding off a wall, and a chaotic triple pendulum

Outputs:
Gemma 4 26B-A4B: 15 GB VRAM usage, 6.9k tokens, 138 tok/s
Gemma 4 12B: 9 GB VRAM usage, 8.9k tokens, 80 tok/s

Same Gemma 4 family, but the 26B-A4B won every scene and ran ~1.7x faster - on just 4B active params. The 12B stayed very close though, on almost half the VRAM - which makes it the ideal model for a 16 GB laptop

[atomic.chat @atomic_chat_hq]

MiniMax M3 turned a napkin sketch into a playable game

We handed MiniMax M3 a hand-drawn draft of a Doodle Jump style platformer. It read the elements off the draft, wrote the logic, drew the interface and shipped it as one self-contained HTML game

Input: 6,920 tokens
Output: 9,933 tokens
Cost: $0.028

@MiniMax_AI drops M3 on @huggingface next week

[atomicbot.ai @atomicbot_ai]

@Touretro no separate install needed, just update Atomic when a new version drops. welcome aboard btw

[atomicbot.ai @atomicbot_ai]

We released iOS app for Hermes Agent 📱

Connect to your self-hosted agent over Tailscale, Cloudflare Tunnel or ngrok. Or deploy on a VPS. Run tasks and manage your agent from anywhere.

[atomicbot.ai @atomicbot_ai]

@itsthedonhashim @testingcatalog Tailscale puts your phone and VPS on the same private encrypted network. Hermes runs on the VPS, your phone connects like it's local

[atomicbot.ai @atomicbot_ai]

@Prashtwtz @testingcatalog that's literally Atomic Hermes, just try it

[atomicbot.ai @atomicbot_ai]

@Jmoon_174 @testingcatalog Tailscale is the move fr, ngrok is fine but messier. what are you running rn?

[atomicbot.ai @atomicbot_ai]

@JacobShintas @testingcatalog but until then, run it on our app

[atomicbot.ai @atomicbot_ai]

@RaafatMS1 @testingcatalog same behavior as core Hermes, we don't override session recovery logic. waiting on upstream updates from @Teknium on that one. what's your VPS setup?

[atomicbot.ai @atomicbot_ai]

@notjazii @svpino want it – just try it!

[atomicbot.ai @atomicbot_ai]

@theazaelov @svpino honestly try both and see. but Hermes gets smarter the more you use it, not just faster

[atomicbot.ai @atomicbot_ai]

@velonxbt @svpino depends a lot on your infra setup, what are you running long tasks on right now?

[atomicbot.ai @atomicbot_ai]

@0employees @svpino fair lol. but at least now it hallucinates from your pocket

[atomicbot.ai @atomicbot_ai]

@AmolParikh10 @svpino agents for everyone is closer than people think

[atomicbot.ai @atomicbot_ai]

@ScottShapiroUXD @svpino gateway to your instance, so full context on the server side. Hermes handles the rest with its own memory layer

[atomicbot.ai @atomicbot_ai]

@alphabatcher @svpino GO GO GO!

[atomicbot.ai @atomicbot_ai]

@Emily_brown_22 @svpino that's exactly why we built Atomic Hermes for mobile. agents on phones changes everything

[atomicbot.ai @atomicbot_ai]

@superactro @svpino all real pain points

[atomicbot.ai @atomicbot_ai]

@realcrisdeluxe drop your setup, we'll walk you through it

[atomicbot.ai @atomicbot_ai]

@Tracklish @gladkos you can store your API keys in the cloud dashboard and they'll sync to the mobile app. sign in with the same account and you're good to go 🙌

[atomicbot.ai @atomicbot_ai]

@shakov_aslan you can! Hermes connects to Telegram