v1.3.0
What's New
All new, from the inside out.
We rebuilt R.E.V.I.S. almost from scratch, from the inference engine to the interface. Seven in-house cores work together, taking it from an AI you just talk to into an AI you can delegate work to. Every v1.x update is included at no extra cost.
At a Glance
Four big changes.
- 01 ENGINEInference without PythonBuilt from scratch for the Mac, Q.E.L.V.A.R.I. runs models directly inside the app.
- 02 AGENTS PROFrom talking to delegatingCode and documents, from creation to revision. An agent does the hands-on work.
- 03 TASKSWork runs in the backgroundM.μ.X.I.S. takes on delegated work as tasks, so your conversation never stops.
- 04 TERMINAL PROFrom the tools you already userevis in the terminal, MCP, and an OpenAI-compatible API. Call it from outside the app, too.
Engine — Q.E.L.V.A.R.I.
Rebuilt from the engine up.
Written from scratch in Swift, C++, and Metal, the Q.E.L.V.A.R.I. inference engine runs models directly inside R.E.V.I.S. without a Python server in between.
Light and faithful
Our own quantization recipes (Q4T, Q3T) make models smaller and lighter while keeping accuracy close to the original model's output.※1
More about quantizationDraft ahead. Check in one pass.
With MTP, a small draft model writes ahead and the main model verifies it. Answers move forward in fewer steps.
Continue without rereading
Context the model has finished reading is encrypted and kept on your Mac, so follow-up conversations pick up right where you left off.
Agents PRO
From an AI you talk to, to an AI you can delegate to.
Whether it's code or documents, the agent handles the work from first draft to final edits. You choose how much to delegate in steps, from read-only all the way to full autonomy.
Code
Runtimes for Python, Node.js, Java, Rust, Go, C#, and more are set up automatically as soon as they're needed. It writes, runs, and checks the code.
Documents
Word documents are displayed just as they look and edited with tracked changes intact. It handles PDF editing, too.
Hand over files
Add files with the + button in the input bar or by drag and drop. Files are copied into a folder for each conversation, leaving your originals untouched.
Conversation
Change the subject. Come right back.
Every time you send a message, it tells whether you're continuing the current conversation or returning to an earlier one, switches to the right thread, and then starts thinking. You never have to switch threads yourself.
No need to repeat yourself
Go back to that Python question from earlier and it picks up right where you left off, building on what it already researched.
Topics don't bleed together
Jump between work and casual chat and each conversation stays separate. Even over long use, answers stay sharp.
Readable while it's still writing
The L.A.T.R.I.O. rendering engine displays math, tables, and code cleanly without breaking layout while they're still being generated.
And More
More that's new.
Remembers your preferences
K.E.C.H.I. learns your preferences from your conversations. Review what it has learned in Personalization settings, search through entries, and delete them one by one.
From the terminalPRO
The revis command, MCP, and the OpenAI-compatible API can each be turned on or off individually.
Across multiple MacsPRO
F.A.L.Q. shares inference work across Macs on the same network. No central server required.
Before You Update
Before you update.
| Release | Available now |
|---|---|
| Pricing | Every v1.x update is included at no extra cost. |
| Requirements | Mac with Apple silicon, macOS 27 or later, 24GB or more of memory (48GB or more recommended).View system requirements |
| Model | Models for v1.3.0 (Q4T, Q3T) will need to be downloaded fresh. |
| Edition | File attachments, agents, sharing work across multiple Macs, and CLI, MCP, and API access are available in the Pro edition. |
Same name.
Built different inside.
SEVEN CORES / ONE CONSCIOUSNESS