Skip to main content
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

Identity

Give your agent a name, personality, and set of instructions using workspace files — simple Markdown documents that shape who your agent is.

Lifecycle

Understand the journey of a message from arrival to response, including memory recall, tool use, and safety checks along the way.

Memory

Your agent remembers past conversations, learns facts over time, and uses that knowledge to give better answers.

Tools

Agents can search the web, manage schedules, send cross-platform messages, analyze images, and much more through built-in and custom skills.

Safety

Built-in cost protection stops your agent from spending too much. Budget limits, a safety fuse, and step counters keep things under control.

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.

​
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 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 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 for details.

​
Explore agents

Agent Lifecycle

How your agent processes messages from arrival to response.

Identity

The workspace files that shape your agent’s personality.

Models

Choosing and configuring AI providers for your agents.

Safety

Budget limits, safety fuses, and cost protection.