Smartloop Studio
Your AI Mission control - extract information, generate new content, create skills, and connect to external systems
Features
Everything you need to run AI privately
Small Language Model
Run quantized open models directly on your hardware — no cloud required, no data leaves your machine.
Connect to External Systems
Extend capabilities by connecting to Model Context Protocol servers for tools, search, and external services.
Create Custom Skills
Define reusable prompt-based skills to automate repetitive tasks and shape how your AI responds.
Open Model, Local Agents
Spin up autonomous agents powered by open models that plan and execute tasks entirely on your device.
Personalized Projects
Create personalized projects tailored to your needs, with your own documents, skills, and connected tools.
OpenAI Compatible API
Drop-in replacement for the OpenAI API — point any existing integration at your local instance.
Documentation
Guides to get you up and running
FAQ
01What is Smartloop?
Smartloop is a local AI agent that runs entirely on your own machine. Instead of depending on a single large cloud model, it uses agent orchestration across small language models (SLMs) to extract information from your documents, connect external tools, and generate content — without sending your data anywhere.
02How does Smartloop work?
Smartloop breaks each request into smaller tasks and routes them to the best on-device model. It runs open small language models — including Google’s Gemma family (such as Gemma 3) and Qwen2-VL for vision — and its orchestration model (slp-orchestra-mini) selects the right one by capability and workload, delivering comparable results locally without cloud infrastructure or per-token costs.
03Is Smartloop free?
Yes, Smartloop is free to use. An optional $10/month subscription unlocks select capability-specific models and supports continued development of our base models, which are regularly updated to handle most everyday tasks efficiently.
04Is my data private and offline?
Yes. Because Smartloop runs on-device, your documents and conversations stay on your machine and are never uploaded. With models running locally, it keeps working offline for most everyday tasks. For best performance, use an Apple Silicon Mac (M1 or newer) or an NVIDIA GPU with at least 4 GB of VRAM and CUDA 12.4.
Accelerated by
