Sign In
The AI workspace

Truly private AI.

ChatVLM is a complete AI workspace: chat, documents, research and agents, with a private pool of models behind it. It runs where your data already lives, so nothing sensitive has to leave the building to get answered.
Talk to us

Runs on a rack in your building, in a private cloud, or in ours.

The workspace

Everything your people need, in one place

A chat that can do the work, not just talk about it. Answers come with the documents, files and sources they produced, and the same workspace is shared by the whole team.
  • Council Mode
    For decisions that matter, several models research, draft and cross-review, and a judge writes the final answer.
  • Real deliverables
    Word documents, slide decks, spreadsheets, PDFs and images, made in the conversation and versioned in a side panel.
  • Projects and teams
    Group chats and files into projects, share them with the people who need them, and build on the same context.
  • Personas
    Assistants built for a job, such as a legal analyst or a research assistant, or your own with exactly the tools it needs.
  • Memory and files
    Long documents, spreadsheets and past conversations stay searchable, and the assistant remembers what you told it.
  • Answers with receipts
    Every reply shows which model answered, what was searched and what was cited, so anyone can check the work.
Everything included
One workspace, the whole toolbox. Nothing to install or hunt down.
Share links
File Q&A
Word docs
Personas
Deep research
Share links
File Q&A
Word docs
Personas
Deep research
Image editing
Spreadsheets
Web search
Council Mode
Memory
Image editing
Spreadsheets
Web search
Council Mode
Memory
Charts & analysis
Translation
Image generation
PDFs
Code interpreter
Slide decks
Charts & analysis
Translation
Image generation
PDFs
Code interpreter
Slide decks
Privacy

Nothing retained. Nothing trained on.

Privacy here is not a switch in an admin panel, it is what the system does by default. Zero data retention and no training are in the contract on every plan, and a private deployment runs open-source models on machines you control, so there is no third party in the path at all.
  • Nothing is retained
    Content goes to the model to answer you and is dropped when the request completes, under contractual zero data retention on every plan, the free one included. What stays is your own workspace, and deleting a chat deletes it.
  • Nothing trains a model
    Your conversations never become training data, for us or for anyone else. There is no opt-out to find in the settings, because there is nothing to opt out of.
  • Open models on machines you control
    A private deployment runs open-source models on your own hardware, or on infrastructure we operate for you alone. No proprietary API sits behind the prompt, and no outside provider ever sees it.
Security review

Built for the security review, not around it

The questions a security team asks are the ones the product was designed to answer. Enterprise adds the identity, governance and evidence a review needs.
  • SSO and SCIM
    SAML single sign-on with Okta, Entra ID or Ping, and automatic provisioning and deprovisioning.
  • Audit logs and retention controls
    Immutable user audit logs, SIEM export, custom retention windows and legal holds.
  • Standard APIs for agents
    Coding agents and internal tools connect to the same private models by changing a base URL.

Put AI where the work happens

Talk to us about your deployment, or start on the free plan today.
Talk to usSee pricing