Fast decisions

Does a conversation contain something worth remembering? Does a new memory repeat something already saved? What does “last month” mean in a search? Fast decisions lets Mem use a dedicated decision model for these small judgments. Your chat model continues to write answers and extract memories.

This setting is optional. You can keep using Mem without it. To try it, open Settings → Providers → Fast decisions.

Turn it on

If the row already shows Nowledge AI, your account has configured it for you. You do not need another API key. Follow the steps below to use your own provider.

Fast decisions requires Remote mode in the model switch above the assignments. Changing this mode also affects the models used for chat and background work. Local mode pauses Fast decisions, even when a provider is saved. If you want to keep using only the built-in local model, leave this optional feature off.

1. Create an API key in the TypeSafe AI console.
2. In Mem, click Set up beside Fast decisions to open the TypeSafe AI settings. If your version does not have this button, search for TypeSafe AI in the provider list below and select it.
3. Enter your API key, click Fetch models, and select the Jev model offered in the list.
4. Click Verify. Once the connection succeeds, click Save.
5. Confirm that the model switch above is set to Remote, then select TypeSafe AI in the Fast decisions dropdown. The row now shows your provider and model, and the selection takes effect immediately.

Saving the provider stores its connection details. Step 5 assigns it to Fast decisions. TypeSafe AI is not offered under Default, Agents, or Vision because it only answers decision questions.

Check the connection

For your own provider, click Test beside Fast decisions. A result such as “Answered in … ms” confirms that the selected model responded. The test sends a short example question, which your provider may charge for. A Nowledge AI row has no Test button and needs no manual connection test.

That time measures one test call. It is not the time taken by memory retrieval or a complete Deep Search.

Once enabled, Mem uses the model in supported steps, including screening conversations for extraction, checking for duplicate memories, and interpreting time references in Deep Search. Ordinary fast search does not make extra decision-model calls by default. Time ranges inferred during Deep Search help rank results; explicit date filters remain under your control.

Where your data goes

When you choose TypeSafe AI, the conversation excerpts, memory content, or search queries needed for a judgment are sent to TypeSafe AI and billed to your account. These calls still go to TypeSafe AI if Default or Agents uses LM Studio or Ollama. To pause them, turn Fast decisions off or switch to the built-in Local mode.

To keep all model calls on your device, leave Fast decisions off and check the other settings in the fully local models guide.

For Nowledge AI, use the configuration shown by your account. Hosted Cloud workspaces manage their models for you and do not expose this local Providers screen.

Turn it off or troubleshoot

To disable your own configuration, select Off in the Fast decisions dropdown (Not configured in older versions). The change saves automatically. Your existing memories, chat model, and saved provider API key remain in place. If the row shows Nowledge AI, click Use my own provider first, then leave Fast decisions off.

Switching to Local mode also pauses Fast decisions while preserving its configuration. The selected decision model resumes when you switch back to Remote.

If TypeSafe AI is missing from the dropdown, check that you have selected a model, verified the connection, and saved the provider. Entering an API key alone does not complete setup.

If the test fails, check your API key, available provider credit, and network connection, then test again. You can return here to check the connection after setup, too.

See LLM Providers for your chat, agent, and vision model settings.