Skip to main content

​
Requirements

​
Install and launch

1

Clone and install

git clone https://github.com/openlegion-ai/openlegion.git && cd openlegion
./install.sh                     # checks deps, creates venv, makes CLI global
First install downloads ~70 packages and takes 2-3 minutes. Subsequent installs are fast.
2

Run guided setup

openlegion setup
The setup wizard walks you through:
  • Entering your LLM API key
  • Describing your project (loaded into every agent’s system prompt)
  • Choosing a team template
Team Templates:
TemplateAgentsUse Case
starterassistantSingle general-purpose agent
salesresearcher, qualifier, outreachSales pipeline
devteampm, engineer, reviewerSoftware development
contentresearcher, writer, editorContent creation
3

Start your fleet

openlegion start
This launches the mesh host, spins up agent containers, and drops you into the interactive REPL. Start chatting with your agents immediately.

​
Common operations

# Add more agents later
openlegion agent add researcher

# Check status
openlegion status

# Run in background
openlegion start -d
openlegion chat researcher   # connect from another terminal
openlegion stop              # clean shutdown

​
Connect a channel

openlegion channels add telegram    # prompts for bot token from @BotFather
openlegion channels add discord     # prompts for bot token
On next openlegion start, a pairing code appears — send it to your bot to link.

​
Next steps

Architecture

Understand how agents, the mesh host, and trust zones work together.

CLI Reference

All CLI commands and interactive REPL commands.

Configuration

Customize agents, permissions, models, and budgets.

Workflows

Chain agents together with deterministic DAG workflows.