SecureThink

Local AI document analysis. No cloud. Total privacy.

12 followers

Local AI document analysis. No cloud. Total privacy.

12 followers

SecureThink is a privacy-first AI document assistant that runs entirely on your Mac. No cloud uploads, no data harvesting — your files never leave your device. Built on local LLMs via Ollama, it uses RAG to let you query contracts, legal docs, and sensitive files in plain English. Get accurate, contextual answers without the privacy trade-off. Perfect for lawyers, accountants, healthcare pros, or anyone who needs AI without handing confidential documents to big tech.

This is the 2nd launch from SecureThink. View more

SecureThink

Launched this week

Local AI RAG on ANY Apple Silicon, even MacBook Neo

SecureThink v2.0 is a native, standalone macOS rewrite Zero deps. MLX runtime and models bundled in the DMG. Drag, drop, done. Apple Silicon optimised. MLX Core + Metal tap Unified Memory. Fast on 8GB Macs. Audio transcription. Local Whisper transcribes and indexes recordings offline. File creation. Ask for a doc, deck, or spreadsheet — get native .docx, .pptx, .xlsx. Local OCR. Import and query scanned docs and images, fully offline. Interactive charts. Bar, Line, and Pie charts in chat.

Free Options

Launch tags:Privacy•Artificial Intelligence•Apple

Launch Team / Built With

Fin Startups get Fin free for a year + 93% off Intercom

Promoted

Maker

📌

SecureThink v2.0 is a ground-up rewrite — a native, standalone macOS app built for privacy-first AI, no compromises. What's new since v1.0: Zero dependencies. v1.0 required Ollama and terminal setup. v2.0 is fully self-contained — the MLX runtime and model weights are bundled inside the DMG. Drag to Applications, open, done. Optimised for Apple Silicon. Native MLX Core and Metal Performance Shaders tap directly into Unified Memory. Programmatic memory capping and aggressive cache clearing keep things fast even on baseline 8GB MacBook Air/Pro models. On-device audio transcription. Drop in a recording and a local Whisper engine transcribes, indexes, and lets you query or summarise meetings — entirely offline. Agentic file creation. Ask SecureThink to draft a contract, build a slide deck, or compile a spreadsheet. It writes native .docx, .pptx, and .xlsx files directly to your Mac. Interactive in-chat charts. Structured data outputs are automatically parsed and rendered as interactive Bar, Line, and Pie charts inside the chat window. Local OCR. An embedded OCR engine lets you import and query scanned documents, images, and screenshots — no cloud, no uploads.

Report

15d ago

Previous SecureThink Launches

SecureThinkLocal AI RAG on ANY Silicon Mac including the MacBook Neo

Launched on January 13th, 2026

Forum Threads

p/securethink

•

15d ago

New in SecureThink v2.0

SecureThink v2.0 is a complete, ground-up rewrite of our local AI engine. We ve moved away from standard wrappers to build a native, standalone macOS powerhouse. Here are the major changes since v1.0:

Zero Dependencies (Goodbye Ollama & Terminal Setup):
- v1.0 required installing external CLI tools like Ollama and downloading models via the terminal.
- v2.0 is a 100% standalone desktop app. The MLX runtime and optimized model weights are built directly into our DMG installer. Drag it to your Applications folder and it works instantly.
Apple UMA & 8GB Mac Optimization:
- We integrated Apple s native MLX Core and Metal Performance Shaders (MPS) to tap directly into Apple Silicon s Unified Memory.
- With programmatic memory capping and aggressive post-inference cache clearing, SecureThink v2.0 runs lightning-fast on baseline 8GB MacBook Air/Pro models without lagging the OS.
On-Device Audio Transcription (Speech-to-Text):
- You can now drag and drop audio recordings. A local Whisper engine transcribes them offline, indexes the text, and lets you query or summarize meetings on-device.
Agentic Office File Creator (Word, PPTX, Excel):
- We added a local creation agent. Ask SecureThink to draft a contract, build a slide deck, or compile a spreadsheet, and it writes and saves native .docx, .pptx, and .xlsx files directly to your Mac.
Interactive In-Chat Charting:
- SecureThink now automatically parses structured LLM data outputs to render fully interactive, responsive Bar, Line, and Pie charts right inside the chat area.
Local OCR (Scanned PDF Reader):
- We embedded a local OCR engine so you can import and query scanned paper documents, images, and screenshots completely offline.

View all

Zero Dependencies (Goodbye Ollama & Terminal Setup):
- v1.0 required installing external CLI tools like Ollama and downloading models via the terminal.
- v2.0 is a 100% standalone desktop app. The MLX runtime and optimized model weights are built directly into our DMG installer. Drag it to your Applications folder and it works instantly.
Apple UMA & 8GB Mac Optimization:
- We integrated Apple s native MLX Core and Metal Performance Shaders (MPS) to tap directly into Apple Silicon s Unified Memory.
- With programmatic memory capping and aggressive post-inference cache clearing, SecureThink v2.0 runs lightning-fast on baseline 8GB MacBook Air/Pro models without lagging the OS.
On-Device Audio Transcription (Speech-to-Text):
- You can now drag and drop audio recordings. A local Whisper engine transcribes them offline, indexes the text, and lets you query or summarize meetings on-device.
Agentic Office File Creator (Word, PPTX, Excel):
- We added a local creation agent. Ask SecureThink to draft a contract, build a slide deck, or compile a spreadsheet, and it writes and saves native .docx, .pptx, and .xlsx files directly to your Mac.
Interactive In-Chat Charting:
- SecureThink now automatically parses structured LLM data outputs to render fully interactive, responsive Bar, Line, and Pie charts right inside the chat area.
Local OCR (Scanned PDF Reader):
- We embedded a local OCR engine so you can import and query scanned paper documents, images, and screenshots completely offline.