> ## Documentation Index
> Fetch the complete documentation index at: https://comis-feature-skill-archive-import.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents

> What agents are and how they work inside Comis

An agent is your AI assistant -- it reads messages, thinks about what to do,
uses tools, and responds. Comis can run multiple agents, each with its own
personality, skills, and memory.

## What is an agent?

Think of an agent as an AI employee that lives inside your chat channels. You
give it a name, a personality, and a set of tools -- then it goes to work. It
can answer questions, search the web, manage your schedule, send messages across
platforms, and remember your preferences over time.

Every agent runs independently. It has its own conversation history, its own
memory, and its own set of instructions. You can have one agent handling your
Discord server and another managing your Telegram chats -- each behaving
differently based on how you set them up.

## What agents can do

<CardGroup cols={2}>
  <Card title="Identity" icon="id-card" href="/agents/identity">
    Give your agent a name, personality, and set of instructions using
    workspace files -- simple Markdown documents that shape who your agent is.
  </Card>

  <Card title="Lifecycle" icon="arrows-spin" href="/agents/lifecycle">
    Understand the journey of a message from arrival to response, including
    memory recall, tool use, and safety checks along the way.
  </Card>

  <Card title="Memory" icon="brain" href="/agents/memory">
    Your agent remembers past conversations, learns facts over time, and uses
    that knowledge to give better answers.
  </Card>

  <Card title="Tools" icon="screwdriver-wrench" href="/skills/index">
    Agents can search the web, manage schedules, send cross-platform messages,
    analyze images, and much more through built-in and custom skills.
  </Card>

  <Card title="Safety" icon="shield-halved" href="/agents/safety">
    Built-in cost protection stops your agent from spending too much. Budget
    limits, a safety fuse, and step counters keep things under control.
  </Card>

  <Card title="Models" icon="microchip" href="/agents/models">
    Catalog-driven access to every provider in the pi-ai SDK (see `comis models list`
    for the current count — Anthropic, OpenAI, Google, Mistral, Groq, xAI, Cerebras,
    OpenRouter, DeepSeek, Bedrock, Vercel AI Gateway, and more), plus custom OpenAI-
    compatible endpoints. Switch models per agent, set up automatic
    failover, and rotate API keys.
  </Card>
</CardGroup>

## How it all fits together

When someone sends a message to your agent, here is what happens at a high
level:

1. **The message arrives** from any connected platform (Discord, Telegram,
   Slack, WhatsApp, or the web dashboard)
2. **Comis routes it** to the right agent based on your routing rules
3. **The agent recalls** relevant memories from past conversations
4. **The agent thinks** and optionally uses tools (web search, scheduling, file
   management, and more)
5. **A reply is sent** back to the same chat

The whole process takes just a few seconds. For the full walkthrough with a
diagram, see the [Agent Lifecycle](/agents/lifecycle) page.

## Slash commands

While chatting, you can control your agent with slash commands -- short
instructions that start with `/`. For example:

* `/think high` -- Tell your agent to think harder about the next response
* `/status` -- See session info, token usage, and model details
* `/model switch openai gpt-4o` -- Switch to a different AI model mid-conversation
* `/new` -- Start a fresh conversation

There are 17 built-in commands plus user-defined `/skill:name` invocations.
See the full list on the [Slash Commands](/agents/slash-commands) page.

## Running multiple agents

You do not need routing rules if you only run one agent -- the default agent
handles everything automatically. But if you want different agents for different
situations, Comis supports that out of the box.

For example, you might run:

* A **support agent** on Slack that answers team questions
* A **research agent** on Telegram that finds and summarizes information
* A **scheduler agent** on Discord that manages reminders and recurring tasks

Each agent only sees messages meant for it. Routing rules control which agent
handles which channels, platforms, or users. See
[Routing](/agents/routing) for details.

## Explore agents

<CardGroup cols={2}>
  <Card title="Agent Lifecycle" icon="arrows-spin" href="/agents/lifecycle">
    How your agent processes messages from arrival to response.
  </Card>

  <Card title="Identity" icon="id-card" href="/agents/identity">
    The workspace files that shape your agent's personality.
  </Card>

  <Card title="Models" icon="microchip" href="/agents/models">
    Choosing and configuring AI providers for your agents.
  </Card>

  <Card title="Safety" icon="shield-halved" href="/agents/safety">
    Budget limits, safety fuses, and cost protection.
  </Card>
</CardGroup>