Chat with your documents.
Private. Local. Free.

Informity AI indexes your files and gives source-cited answers using local models, entirely on your machine. No cloud uploads, no accounts, no subscriptions.

Download for Mac View on GitHub

Optimized for Apple Silicon · Free · Open Source · v0.9.8

Features

Private AI for your files

From indexing to chat to history, your data never leaves your machine. Local models do the heavy lifting.

Fully Local by Design

Indexing, embeddings, vector search, and chat history stay on your machine. Your data is never uploaded to the cloud.

Ask Across Real Documents

Search PDFs, Word documents, spreadsheets, slides, markdown, JSON, YAML, and more. All in one place.

Answer with Source Citations

Every response includes source references so you can open the exact file and verify the original passage.

Two AI Chat Modes

Researcher mode answers from your indexed documents with source citations. Assistant mode handles open-ended questions with optional web search.

Flexible Model Choice

Pick Small, Balanced, or Quality tiers based on your hardware. Swap models anytime without reinstalling or losing your index.

Simple. Straightforward.

A guided setup walks you through model selection. Point to your folders and Informity AI starts indexing automatically.

How it works

From folders to answers in minutes

No configuration complexity. Point, index, ask, verify.

Choose folders

Select one or more folders on your machine and let Informity AI handle the rest.

Index your files

Your files are processed and indexed locally. No cloud, no external services.

Ask anything

Type in plain language. Answers arrive as streaming text, grounded in your documents.

Verify sources

Every answer cites its sources. Open the original file with one click to review.

See it in action

Simple interface, serious capability

Powerful local AI, wrapped in a clean and fast interface.

Chat with source citations. Click any reference to open the original file.

Dashboard showing index status and stats

Dashboard shows indexing progress, document counts, and scan controls.

Browse every indexed file, see which documents are searchable, and manage your library.

Choose from local model profiles based on your hardware, from lightweight to full-size.

Get started in minutes. Select one or more folders on your machine and let Informity AI handle the rest.

Privacy

Privacy isn't a feature. It's the whole point.

Built local-first from the ground up. Your documents, your models, your machine.

No Accounts Required

Download and use immediately. No sign-up, no email address, no credit card, no ads.

No Cloud Storage

Your documents never leave your machine. All actions are local, fast, and under your full control.

No Telemetry

Zero telemetry of any kind. No data is ever collected, stored remotely, or transmitted anywhere.

Open Source

Every line of code is auditable on GitHub. Free to use, inspect, and modify forever under the MIT License.

FAQ

Questions worth asking

Does it send my files to the cloud?

No. Indexing, embeddings, vector search, and chat all run locally on your machine. Nothing is ever uploaded to any server.

Does it work offline?

Yes, once your local model is installed. After setup, Informity AI runs entirely without an internet connection.

Does web search share my documents?

No. Web search is opt-in, Assistant mode only, and requires a Tavily or Linkup API key in Settings. Only your query text leaves your machine and your documents are never involved. Disabled by default in Full Privacy Mode, but can be enabled per chat.

What file types are supported?

PDF, DOCX, XLSX, CSV, PPTX, HTML, TXT, MD, RST, and LOG. JSON, YAML, and TOML are available via Settings. OCR is enabled by default for scanned PDFs.

Can I choose which AI model to use?

Yes. The default is Qwen3.6 35B A3B, optimized for Apple Silicon. Smaller profiles are available for lower-memory machines. Model selection is configurable in Settings.

What are the system requirements?

macOS with Apple Silicon is required for the default Qwen3.6 35B A3B model, with at least 24 GB unified memory recommended. Smaller model profiles are available for 16 GB machines.

How do I get started?

Download the app, run the installer, and point Informity AI to your folders. The first index build takes a few minutes depending on how many files you have. After that, just ask.

Is it free?

Yes, completely. Informity AI is free and open source under the MIT License. No accounts, no subscriptions, no usage fees, no paywalled features, no ads. Ever.

Free Download

Own your AI. No asterisks.

Source-backed answers from your own files, running entirely on your machine. Free forever. Fully open source. Full stop.