Skip to content

News

News from Milly Lab

Releases and publications from Milly Lab: what is new in the workspace and in the company, newest first.

All posts

Release

Workflows are on for every account

Draw a repeatable process once (a trigger, the steps and the approvals it needs) and let Milly Lab run it on a schedule, from a form or from a chat. Fifteen ready-made templates help you start.

Release

A new sign-in, with codes by e-mail

Signing in and creating an account now happen on one redesigned screen, and two-factor sign-in can use a 6-digit code sent to your e-mail.

Publication

Milly Lab has a new home at m-lab.app

Our company site now lives at m-lab.app in English, Russian and Tajik, and the workspace itself has its own address, app.m-lab.app.

Release notes

Every user-visible change by the date it was completed, newest first, since June 2026.

What changed in October 2026?8

October 2026 brought agents to Spaces, 15 built-in skills, schedules, remote MCP servers, plugins, notebooks and the Console, and a chat that shows each step and tool call while the model works.

  1. Built-in skills, including Tajik and Russian business letters

    Fifteen built-in skills are on for every account, among them official letters in Tajik and Russian, e-mail drafting in Russian and Tajik, translation with a glossary, contract review for CIS contracts and research briefs. You can also write or upload skills of your own.

  2. Schedules

    A prompt or an agent can run on a schedule. Each run opens a new chat or adds to a conversation you choose, and its result lands in the Tasks inbox.

  3. MCP servers and plugins

    Add any remote MCP server by its https address, with OAuth sign-in, a bearer token or custom headers, and use its tools in chats and agents. Plugins built for Claude, Codex and Gemini can be installed, switched on and off, and exported.

  4. The Console

    Agents, skills, MCP servers, connected accounts, schedules, API keys, usage and the audit log are managed in one place: inside the app, or in the full Console in its own tab.

  5. Notebooks

    A memory collection can become a notebook that answers questions with citations to its sources and can record a short audio overview.

  6. Stop, Regenerate and retry

    Stop now ends a reply on the server as well, Regenerate replaces the previous answer, and a reply that failed can be retried.

  7. Agents in Spaces

    Save an assistant with its own instructions, model and tools, call it with @ in any chat, or let Milly Lab draft one from your chats. Nothing becomes an agent until you review the draft.

  8. Chat shows its work

    While a model works, the reply shows its plan, each tool call, the files it creates and a status line.

What changed in September 2026?3

September 2026 added an OpenAI-compatible API with API keys for the Max, Advanced and Enterprise plans, two-factor authentication, sealed Spaces and memory collections shared with a team.

  1. OpenAI-compatible API

    On the Max, Advanced and Enterprise plans you can create API keys and call Milly Lab models through an OpenAI-compatible endpoint at https://api.m-lab.app/v1. API usage is charged to the same account as the app.

  2. Two-factor authentication

    Turn on two-factor authentication in Settings → Security with an authenticator app. Signing in with a password or with Google then asks for a code, and recovery codes are shown once.

  3. Sealed Spaces, shared collections and memory import

    A Space can seal its memory, so its chats use only their own memory and nothing learned there appears in other chats. Memory collections can be shared with your team and imported from files.

What changed in August 2026?7

August 2026 added Tajik as the third interface language, memory across chats, file previews, models that read attached Office files, textured 3D models, public documentation and web search that runs only when a question needs it.

  1. Memory across chats

    With memory switched on, Milly Lab keeps short facts about you and summaries of past chats, marks the answers that used them, and lets you read, edit or forget each fact. Memory is part of the paid plans.

  2. File previews

    Click a generated file's name to preview it, with presentations shown as slides, or use the download icon to save it.

  3. Models read your attachments

    Attach Word, Excel, PowerPoint or text files to a chat and the model reads their content. Each chat keeps its files together in one place, and files can be dragged into the chat.

  4. Tajik interface

    Tajik became the third interface language after English and Russian, across the website and the app.

  5. Textured 3D models and image-to-3D

    3D Studio builds textured models from a text description or from an uploaded image. 3D Studio is part of the Advanced plan.

  6. Public documentation

    Guides to plans, features, security and the API are published at /docs.

What changed in July 2026?5

July 2026 introduced the Free plan, a document engine for Word, PowerPoint, Excel and PDF files, GitHub repositories and Google Drive folders connected to Swarm Mind with staged changes, and password reset by e-mail.

  1. New GitHub repositories on Apply

    A Project or Council session can put its changes into a new private GitHub repository, which is created only when you press Apply.

  2. Connected GitHub repositories and Google Drive folders

    Project and Council sessions can read a connected GitHub repository or Google Drive folder. Every change they propose is staged, and nothing is written until you press Apply and choose the default branch or a new branch.

  3. Password reset by e-mail

    If you forget your password, request a one-time link by e-mail and set a new password.

  4. Free plan

    New accounts start on the Free plan without a card: 10 messages per model every 4 hours with Luna · GPT-6 and DeepSeek Flash.

  5. Document engine with Excel files

    A new document engine builds designed Word, PowerPoint, Excel and PDF files from a chat, with themes and charts. Document files are part of the Pro plan and higher.

What changed in June 2026?5

June 2026 introduced Council Mode and Project Mode, sign-in with Google, voice messages and the first downloadable documents from a chat.

  1. Council Mode

    Several models answer the same brief on separate cards. You can compare the cards, start a debate between them and merge the result into a final answer.

  2. Project Mode

    An orchestrator model splits a larger task into subtasks, several models work on them, and the results are combined into one deliverable.

  3. Sign in with Google

    Create an account or sign in with a Google account.

  4. Voice messages

    Record a request instead of typing it: when you stop recording, the speech is transcribed and sent.

  5. Documents from a chat

    Ask for a Word, PDF, PowerPoint or Markdown file and download it from the conversation. Document files are part of the Pro plan and higher.

Last updated:

See what is new for yourself

Every account starts on the Free plan, without a card.