Sigma Browser

Super Private AI browser with the local AI

Founder: @skinbagwbones

[Sigma Browser @Sigma_Browser]

Hermes agent running in private browser on free local models

Private by design. Local. Open-source

[Atomic Mail @atomic_mail]

Meet Atomic VPN for $2/month

– 6,500+ servers in 88+ countries
– zero logs
– 5 devices on one account

Download Atomic VPN - link in comments

[atomic.chat @atomic_chat_hq]

Le Chonk enters the Frontier race 🐈

We put @MistralAI Large 4, MiMo V2.6 Pro, Opus 5.5 and GPT-6.1 Sol side by side with voxel, ASCII, Blender and SVG remakes of the launch clip

Run AI models locally and via API -> https://t.co/RbcCOIgVkj

[atomic.chat @atomic_chat_hq]

Run decision models with our llama.cpp engine ⚙️

We're bringing support for over 10 System One models into Atomic Chat, now your device makes choices 10.43x faster than Jev's API utilising only the CPU

Run decision models locally -> https://t.co/RbcCOIht9R

[Atomic Agent @atomicagent_io]

Atomic Fusion cut GPT-6.1 Sol’s API bill by 77% 💥

We tested cloud-only, local-only and orchestrated builds. Cloud GPT-6.1 made a plan and orchestrated local Qwen 3.8 27B, making it cheaper with minimal quality loss

Try Atomic Fusion -> https://t.co/295O9ILOgw

[atomic.chat @atomic_chat_hq]

GPT 6.1 Sol 30x cheaper than Sonnet 5.5 at 3D ⚙️

openAI just dropped GPT 6.1 Sol, we put it up against Sonnet 5.5 and made them create a 3D keyboard assembly video in @threejs

Run both models via sub -> https://t.co/RbcCOIht9R

[atomic.chat @atomic_chat_hq]

Space Bunny Alpha mogged by DeepSeek V4.1 Flash 🐳

We asked both to build Minecraft in one HTML file and DeepSeek V4.1 Flash made a forest biome you can walk and dig in while Space Bunny Alpha's ground has holes showing the sky

Run AI models locally -> https://t.co/RbcCOIgVkj

[atomic.chat @atomic_chat_hq]

Opus 5.5 destroyed GPT 6 Sol at Blender 3D Pelican 🦩

Both frontier models dropped today so we gave them the same brief to animate a looping 3D pelican on a bicycle in Blender and Opus 5.5 came back with the more charming ride

Run both models via API -> https://t.co/RbcCOIgVkj

[atomic.chat @atomic_chat_hq]

Local Laya moggs Jev at @grok 4.7-built Tetris 🧩

An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air!

Run AI models locally -> https://t.co/RbcCOIgVkj

[atomic.chat @atomic_chat_hq]

DeepSeek V4.1 Flash made DOOM in Atomic Chat 🐳

@deepseek_ai dropped a new architecture for the flash model so we tested it by making Doom in an html file and it built a real raycasting shooter with gun mechanics and enemy waves

Run AI models locally -> https://t.co/RbcCOIgVkj

[atomic.chat @atomic_chat_hq]

New Fable 5.1 absolutely crushed Fable 5 at making a racing game👾🔥

@claudeai just dropped Fable 5.1, so we gave both models the same prompt to build a playable racing game from scratch in Godot with BlenderMCP

Tasks:
- Make car and environment models using BlenderMCP
- A big map for long driving sessions
- Realistic car handling
- Simple HUD for speed and controls

Outputs:
Fable 5.1: 1.2M tokens, 123.98$, 59.8 minutes
Fable 5: 897K tokens, 95.87, 57.3 minutes

Fable 5.1's models are far more detailed and the game runs smooth, the world feels alive while you drive. Fable 5 finished all three tasks and its HUD and controls work, but its models are plain and the game feels stiff

[atomic.chat @atomic_chat_hq]

Run OpenClaw 2.0 through Atomic Chat local LLM server on a 16GB MacBook 💻🦞

We gave OpenClaw a task to edit a video using Gemma 4 E4B, it successfully created a welcome video in two minutes by writing custom React code

Load the model in https://t.co/lW9A0SLtWj, start the LLM server and OpenClaw 2.0 picks it right up

[atomic.chat @atomic_chat_hq]

Open-weight Qwen 3.8 2.4T built a Call of Duty clone in one prompt 🪖

@Alibaba_Qwen released the 2.4T Max weights, so we rented a B200 cluster and asked the model to make a Call of Duty clone

Output: ~1.1M tokens · 5 hours · one prompt

Almost no one can run 2.4T at home, luckily there is a 27B version that runs on a 16GB MacBook Air with our Atomic Dynamic quants

[atomic.chat @atomic_chat_hq]

New Muse Glimmer 30B destroyed Gemma 4 31B at making retro arcade games!

We gave three models the same task and compared one-shot outputs. Muse Glimmer 30B, Gemma 4 31B and Qwen3.6 27B each ran locally on its own RTX 5090 with 32GB VRAM

Tasks:
- Space Invaders
- Tetris
- Arkanoid with multiball

Outputs:
Muse Glimmer 30B: 83.4K tokens, 17.7 min
Qwen3.6 27B: 23.7K tokens, 5.4 min
Gemma 4 31B: 17.8K tokens, 4.5 min

Glimmer's games play like the originals. The alien fleet speeds up with every kill, the blocks lock and lines clear, the bricks break. Nothing froze or crashed. Gemma broke on Tetris, its bot piles every piece against the left wall until the stack hits the ceiling with half the well empty. Qwen finished all three but some of its Arkanoid balls phase straight through the paddle.

Run Muse Glimmer yourself in Atomic Chat from day 0!

[Sigma Browser @Sigma_Browser]

@ValerianWaters @DataChaz Honestly haven't benchmarked with 3-4 concurrent agents yet. Real talk though: local agent performance is mostly a RAM story

[Sigma Browser @Sigma_Browser]

@HarryTandy @DataChaz Yep!

[Sigma Browser @Sigma_Browser]

@hanzi_li @DataChaz Especially if you've got a good device

[Sigma Browser @Sigma_Browser]

@Timur_Yessenov @testingcatalog Interesting take. Maybe we should be thinking about a "categorizer" layer for agents on our side too

[Sigma Browser @Sigma_Browser]

@zihua_ma @testingcatalog Exactly! Hermes with its on-the-fly learning makes the in-browser agent genuinely smart

[Sigma Browser @Sigma_Browser]

@sir4K_zen @DanKornas Nothing but privacy!

[Sigma Browser @Sigma_Browser]

@onchaindudes This issue was real in the early versions, but the Nous Research team is actively working on improving the agent - and we ship the latest version of the agent in our browser ;)

[Sigma Browser @Sigma_Browser]

Hermes agent running in private browser on free local models

Private by design. Local. Open-source