Prerequisites
Required
Python 3.11+ — the runtime for Octo itself
Node.js 18+ — required for MCP servers (most use
npx)At least one LLM provider — Anthropic, AWS Bedrock, OpenAI, Azure, or GitHub Models
Optional
Claude Code — enables project workers that delegate tasks via
claude -p. Without it, Octo still works with standard and deep research agents.skills.sh — the open skills ecosystem. Install the CLI with
npm install -g skills to use /skills import and /skills find from chat. Local skills (.octo/skills/) work without it.Installation
- pip
- uv
- From source
The PyPI package is called
Bare
octo-agent, but the CLI command and Python import are just octo.Installation extras:| Extra | What it adds |
|---|---|
cli | Rich terminal UI, Click, prompt_toolkit (recommended) |
telegram | Telegram bot transport |
s3 | S3-compatible storage backend |
postgres | PostgreSQL checkpointing |
all | Everything above |
pip install octo-agent installs the core engine only — use [cli] for the terminal experience, or [all] for everything.Run the setup wizard
- Provider selection (Anthropic, Bedrock, OpenAI, Azure, GitHub Models)
- Credential entry and validation
- Workspace scaffolding (creates
.octo/directory)

