zooqueenandHanzo Dev
1e1310e05a
The upstream merge left the backend unable to start: lfx.memory imported has_flow_db_backend, which did not exist, and appended a second import-time dispatch that named an unimported function. Around it, 17 modules referenced names whose imports were gone, several re-export packages were empty or pointed at modules that no longer exist, and settings/base.py still held the monolithic Settings class the groups replaced (without cache_dir and mcp_base_url). Each file now matches its upstream counterpart at the merge point, with this fork's own changes kept: the /v1 and /v2 API paths, the org_id columns, Hanzo IAM in auth, and product naming. Empty leftover packages from the rename are removed, and the assistant flow file is FlowAssistant.json to match FLOW_ASSISTANT_FLOW. python -m flow run --backend-only starts on SQLite and answers /health, /health_check and /v1/version. Co-authored-by: Hanzo Dev <[email protected]>
Hanzo Flow
Hanzo Flow is a powerful platform for building and deploying AI-powered agents and workflows. It provides developers with both a visual authoring experience and built-in API and MCP servers that turn every workflow into a tool that can be integrated into applications built on any framework or stack. Hanzo Flow comes with batteries included and supports all major LLMs, vector databases and a growing library of AI tools.
Highlight features
- Visual builder interface to quickly get started and iterate.
- Source code access lets you customize any component using Python.
- Interactive playground to immediately test and refine your flows with step-by-step control.
- Multi-agent orchestration with conversation management and retrieval.
- Deploy as an API or export as JSON for Python apps.
- Deploy as an MCP server and turn your flows into tools for MCP clients.
- Observability with LangSmith, LangFuse and other integrations.
- Enterprise-ready security and scalability.
Quickstart
Install locally (recommended)
Requires Python 3.10-3.13 and uv (recommended package manager).
Install
From a fresh directory, run:
uv pip install hanzoflow -U
Run
To start Hanzo Flow, run:
uv run hanzoflow run
Hanzo Flow starts at http://127.0.0.1:7860.
Other install options
Run from source
If you've cloned this repository and want to contribute, run this command from the repository root:
make run_cli
For more information, see DEVELOPMENT.md.
Docker
Start a Hanzo Flow container with default settings:
docker run -p 7860:7860 hanzoai/flow:latest
Hanzo Flow is available at http://localhost:7860/.
Deployment
Hanzo Flow is completely open source and you can deploy it to all major deployment clouds.
Contribute
We welcome contributions from developers of all levels. If you'd like to contribute, please check our contributing guidelines and help make Hanzo Flow more accessible.