someone you know

@skinbagwbones

Founder at: @atomicbot_ai @atomic_chat_hq @atomic_mail

atomic.chat

Joined October 2023

Replies Reposts Media

Pinned
someone you know
@skinbagwbones
Jul 22
New Atomic release!!! Finally a privacy centric Agent is live. Your own inference, your own data, your own AI!
Atomic Agent
@atomicagent_io
Jul 22
First local agent to beat Hermes on benchmarks! ✦ runs Qwen, Gemma, Llama via llama.cpp ✦ stable-prefix caching keeps sessions cheap ✦ TurboQuant cuts the KV-cache 6.4× smaller ✦ 37 tasks solved vs Hermes' 31 on GAIA Level 1 Open source on macOS, Windows & Linux 👇
00:00
6
someone you know
@skinbagwbones
Aug 29
Sometimes you must use all inference to get all the inference
Atomic Agent
@atomicagent_io
Aug 28
Atomic Agent made GLM 5.3 better and it costs only 77 cents more! We ran three prompts: ✦ Teddy bear falling apart mid-run ✦ Frog popping ✦ Snowman melting in a sauna Outputs: ✦ GLM 5.3, API only: 543,290 tokens, $2.39 ✦ GLM 5.3 + Atomic Agent: 1,091,380 tokens, $3.16 An
00:00
1
someone you know
@skinbagwbones
Aug 11
Fastest hand on the Wild West
AI/ML API
@aimlapi
Aug 11
NVIDIA's new 3B model just turned coffee stains into planets Nemotron 3.5 Lightning dropped today: a 30B mixture-of-experts model with only 3B active parameters, a 1M-token context window, and open weights. NVIDIA claims up to 4x faster output than competing models in its class
00:00
someone you know
@skinbagwbones
Jul 28
This is enabling @n8n_io with so many commercial use cases! 🤩
Atomic Mail
@atomic_mail
Jul 28
Atomic Mail for AI Agents integrated in n8n Drop @atomic_mail into any @n8n_io workflow. Create an email for your AI agent with MCP or Agent Skill, connect it to the node via API and choose any of the 7 actions. Node is up, try it!
00:00
1
someone you know
@skinbagwbones
Jul 23
I still call this work🤣
Atomic Mail
@atomic_mail
Jul 23
Atomic Mail put OpenClaw and Hermes head-to-head We gave OpenClaw and Hermes one inbox each and the same prompt: prove you’re better. Who won? Get your agent an inbox in 30 seconds: – Plug in with one prompt via MCP or Agent Skill – No CAPTCHA, no signup – Run any workflow over
00:00
2