> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nemu.cc/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat

> An assistant that uses the models you configured, and keeps working after you close the tab

Chat is an assistant called Nemu that runs on the models you connected in the
console. It searches the web, reads your files, queries your databases, drives a
real machine, and hands work to subagents that run in parallel.

The model list is entirely yours. There is no curated set. Whatever providers
and models you enabled in the console are what the picker offers, so what chat
can do is decided by what you connected.

## It keeps running without you

Work does not happen in your browser. Sending a message enqueues a job, and the
job runs on our side whether or not the tab is open.

Close it, put the laptop to sleep, come back later. When you reopen the chat it
reattaches to the running job and replays everything that happened while you
were gone.

Two honest caveats. The pointer to a running job is stored in that browser, so
another device sees the answer once it is saved rather than watching it stream.
And the live replay buffer is kept for one hour, after which the finished
message is still there but the keystroke by keystroke replay is not.

If the agent needs an answer from you, it waits 90 seconds and then suspends
rather than holding a worker open. The message is saved as suspended and you
pick it back up with `/resume`.

## Modes

Five, from the composer. They change how long the agent may work, how many
subagents it runs at once, and which tools it may touch.

| Mode   | For                        | Notes                                   |
| ------ | -------------------------- | --------------------------------------- |
| Normal | Everyday work              | The default                             |
| Plan   | Thinking a problem through | Cannot write files or build artifacts   |
| Fast   | Getting an answer quickly  | Runs 5 subagents at once. Pro and above |
| Eco    | Cheap, short answers       | Output capped, heavy tools off          |
| Max    | Long, hard tasks           | Up to 90 minutes. Pro and above         |

Normal, Plan and Fast and Eco run up to 300 steps and 45 minutes. Max runs up to
600 steps and 90 minutes.

## What it can reach

<CardGroup cols={2}>
  <Card title="Files and search" href="/chat/files">
    Attach a document and the agent searches inside it rather than pasting it.
  </Card>

  <Card title="Web research" href="/chat/web">
    Search, read pages, and dispatch a research agent that comes back with sources.
  </Card>

  <Card title="Connectors" href="/chat/connectors">
    Your own Postgres, MySQL, SSH hosts and MCP servers, behind an approval gate.
  </Card>

  <Card title="Integrations" href="/chat/integrations">
    GitHub, Slack, Notion, Drive, Linear, Jira, Dropbox and more over OAuth.
  </Card>

  <Card title="Subagents" href="/chat/subagents">
    Parallel workers for research, repositories and long documents.
  </Card>

  <Card title="Custom agents" href="/chat/agents">
    Save your own agent with its own prompt, tools and model.
  </Card>

  <Card title="Artifacts" href="/chat/artifacts">
    Documents, websites, diagrams, charts and PDFs, with version history.
  </Card>

  <Card title="Memories" href="/chat/memories">
    Standing facts it carries between conversations.
  </Card>

  <Card title="Computer" href="/computer">
    A real machine it can build in and put online.
  </Card>

  <Card title="Indexed sites" href="/chat/indexes">
    Crawl documentation you rely on so it is searched before the open web.
  </Card>

  <Card title="Skills and knowledge" href="/chat/skills">
    The procedures it loads and the reference it searches, without being asked.
  </Card>

  <Card title="Prompting" href="/prompting">
    How to ask for what you actually want.
  </Card>
</CardGroup>

## Slash commands

| Command    | What it does                               |
| ---------- | ------------------------------------------ |
| `/model`   | Switch model                               |
| `/agents`  | Manage and attach custom agents            |
| `/compact` | Summarise the conversation to free context |
| `/clear`   | Archive the conversation and start fresh   |
| `/resume`  | Continue a suspended turn                  |

With a Computer attached you also get `/logs`, `/stop`, `/upgrade` and
`/publish`.

## Context

The header shows how full the context window is, broken down by messages, tools,
input, output and reasoning. At 90% the conversation is compacted automatically
and older turns are archived. Nothing is lost: the agent can still search the
archive when it needs something from earlier.

## When we are busy

Chat jobs queue. If the queue is deep you see your position. Plans from Pro up
have a priority queue and bypass the load shedding that protects the platform
when it is under pressure.