studio v1.0.59 · runs on your device
Frontier quality. Local first.
A fast System 1 model plans every request and routes each step to the open model built for it — documents, tools, web search and an API, all on the hardware you already own. Your data never leaves the device.
free · on-device · no account
Smartloop Studio for macOS · Linux · Windows
The orchestrator
You shouldn’t have to pick a model.
Running AI locally usually means choosing between hundreds of models, guessing at quantization and hoping it fits in your RAM. Smartloop makes those calls for you: on first launch it checks the memory and GPU you have, then fits the models to them — integrated graphics included.
What you do with it
Real work, not just chat.
Documents and projects
Drop PDFs, Office files and scans into a project. They are indexed on your machine and never uploaded; every answer shows the file it came from.
read the guideOn-device privacy
An associate that never leaves the office.
Some documents can’t go to a cloud model. Smartloop reads and reasons over them on your own machine, so privileged material never leaves the device — and every answer cites the clause it came from.
The template is a fictional firm’s client file: five agreements and two review skills, ready to import into Studio.
- Five agreements. A services agreement with its amendment and 2026 renewal draft, a mutual NDA, and a one-sided supply agreement.
- Issues list. A first-pass review against a checklist — term, termination, liability, assignment — quoting each clause by section.
- Version compare. What changed between the signed agreement and the draft, clause by clause.
In your terminalv1.0.43
Same agent. No window.
Install docent to chat with your documents, search the web and connect MCP servers — in your scripts or over SSH, with the same models and projects as Studio.
- One command. Sets itself up on first run.
- Your files. Drop a PDF on the terminal and ask.
- Scriptable. Pipe answers with
--plain.
$curl -fsSL https://smartloop.ai/install | shinstalls as docent and smartloop · full reference
How it works
Four steps, none of them a setting.
- 01
Install
One installer from your platform’s store. On first launch it checks your memory and GPU and fits the models to them.
- 02
Bring your documents
Make a project and drop in your files. They are indexed on your machine. Nothing uploads.
- 03
Ask
The orchestrator splits the request and routes each step to the open model built for it. You never pick one.
- 04
Take it to the terminal
docent runs the same agent, models and projects from your shell, your scripts or over SSH.
Documentation
Guides to get you running.
Introduction
Overview of Smartloop and what it can do for you.
Getting Started
Install Smartloop and run your first local AI session.
Model Orchestration
See how Smartloop routes each task to the right on-device model.
Skills
Extend your project with agent skills.
Connections
Connect external tools and services to your AI.
Local AI
Create AI tools and integrations.
FAQ
Questions, answered.
What is Smartloop?
Smartloop is a local AI assistant that runs entirely on your own machine. You install it and start asking; there are no models to choose, nothing to configure, and no account to create. It reads your documents, connects to your tools, and generates content without sending your data anywhere.
How does Smartloop work?
Smartloop breaks each request into smaller tasks and routes them to the best on-device model. We curate the models it ships with — open small language models including Google’s Gemma family (such as Gemma 3) and Qwen2-VL for vision — and its orchestration model (sl-mini) picks the right one by capability and workload. You never see that choice; you just get the answer.
Do I need to pick a model or configure anything?
No. That is the point. There are hundreds of open models, each with its own file formats, quantizations, and memory requirements, and most people have no reason to learn the difference. Smartloop is opinionated: we curate the models, size them to your machine on first launch, and swap in better ones as they land. There is nothing to choose or configure.
Is Smartloop free?
Yes, Smartloop is free to use, with models that are regularly updated to handle most everyday tasks efficiently. No account or credit card is needed, and it stays free for organizations running it at scale. The one metered part is AI search, which runs through us: every account gets a monthly allowance of searches, and you can buy more from your dashboard. If you want a hand getting it running, you can contact us to set it up and get it working on your data — on-premise deployment, tuning for your use case, rollout across your team, and a dedicated point of contact. Reach us at support@smartloop.ai.
Is my data private and offline?
Yes. Smartloop runs models on-device, so your documents and conversations stay on your machine, and it works offline for most everyday tasks. AI search is the exception: it sends only a search query to find current web information, never your documents or conversation, and you can turn it off per project. Smartloop sizes the models it runs to the memory your machine has. The minimum is an Apple Silicon Mac (M3 or newer) with 16 GB of unified memory, or a Windows 11 / Linux machine with 16 GB of RAM and a Vulkan-capable GPU — integrated Intel, AMD, or NVIDIA graphics all qualify, and the Vulkan runtime ships with the app. More memory is better.
free to start
Start asking. Locally.
Install Studio, drop in a document and ask. Nothing to pick, nothing to configure.
Accelerated by
