The canvas is not the ceiling
Models, vector stores, document loaders, text splitters, output parsers, memory, retrievers and toolkits — plus anything you write yourself, which is a component like the rest.
Paste and ship
Paste this into any agent. It reads the skill manifest and calls Flow from there.
Agent prompt
Read https://hanzo.ai/skill.md and use Hanzo Flow in my project. Start with: hanzo flow workflows list
PythonEvery component
RESTOr JSON, or MCP
:7860On your machine
MITSelf-hosted
Open source royalty
20% to the author of the code that runs
Verify that you own a repository, and every org that deploys a project built from it pays you 20% of its metered spend, accrued each period.
Run it locally first
uv pip install hanzoflow, then uv run hanzoflow run. It opens on 127.0.0.1:7860. Docker works too.