This is a big update to how you organize and work with Tresor.

Previously, uploaded files were ephemeral — available only during a single request. Now, 

 across your conversation. Upload a contract at the start of a chat, and reference it ten messages later.

Your files remain encrypted and private. Only you can access them.

Projects now go beyond grouping conversations. You can:

Think of a project as a private, focused workspace — shaped around a client, a case, a deal, or a research topic.

Ever hit the point where a conversation gets too long and the AI starts losing context? The new 

 feature solves this. Tresor intelligently compresses earlier parts of the conversation so you can keep going — without losing the thread.

This is especially useful for deep research sessions, ongoing advisory work, or any conversation that naturally runs long.

Both models run inside secure, sealed environments — same privacy guarantees as every other model on Tresor.

This release makes Tresor a more powerful workspace for ongoing, complex work. Set up a project, attach your files, and let the AI work within your context.

Projects, persistent files, and longer conversations

A round of polish to make your day-to-day experience smoother:

Small improvements, steady progress. We're shipping these alongside larger features to keep the everyday experience feeling fast and reliable.

Smoother conversations, better sources

Tresor now understands images. Upload a photo, screenshot, chart, or diagram — and ask the AI to describe it, extract text, analyze data, or answer questions about what it sees.

Like everything on Tresor, your images are processed privately inside the sealed environment. They're never stored or visible to anyone.

See it for yourself — drop an image into your next conversation.

Upload and analyze images

You can now upload documents directly into your conversations. Drop a PDF, Word document, spreadsheet, or any supported file — and ask the AI to summarize, analyze, extract, or transform it.

Your files are encrypted and processed inside the sealed environment. Tresor never sees or stores the contents.

PDF, DOCX, XLS, XLSX, PPTX, CSV, JSON, RTF, ODT, TXT, and HTML.

Upload something and see what the AI makes of it.

Upload documents, get answers

Tresor can now go beyond what the AI model knows. Ask a question that needs current information, and Tresor will search the web, read relevant pages, and synthesize an answer — with sources.

All of this happens inside the sealed environment. The websites you search never know who's asking, and Tresor never sees what you searched for.

 — a multi-step reasoning loop that can plan, search, read, and reflect before giving you an answer. For straightforward questions, it answers directly. For research tasks, it takes multiple steps automatically.

 by including a search flag in your prompt, or just ask naturally — Tresor will decide when the web can help.

This is a big one. Give it a try — ask Tresor something that needs today's information.

Search the web, privately

You can now use Thinking Mode in Tresor. This mode lets you choose models that reason through your question before answering. You can see how long the model spends thinking and, if you want, inspect its reasoning process.

For complex or ambiguous requests, Thinking Mode can noticeably improve answer quality and reliability.

 from the model selector in the top left, or choose any model with “thinking” in its name.

Thinking Mode uses a budget-based approach — the model decides how much reasoning a question needs and allocates time accordingly. Simple questions still get fast answers. Complex ones get the deep thought they deserve.

Thinking Mode is here

Every menu, button, and setting adapts to your chosen language — so you can navigate Tresor in the language that feels most natural to you. Your AI conversations already worked in any language; now the app around them does too.