3d685dab14
* fix: enable agent-lifecycle-toolkit (altk) on Python 3.14 agent-lifecycle-toolkit 0.10.x dropped its own requires-python <3.14 cap (now >=3.10) and does not depend on OpenDsStar, so the `python_version < '3.14'` gate on the altk extra is stale. - Remove the python_version < '3.14' marker from the altk extra in langflow-base, keeping the macOS x86_64 platform exclusion. - Regenerate uv.lock: agent-lifecycle-toolkit resolves on 3.14 and coexists with the onnxruntime>=1.26 langflow forces there (verified agent-lifecycle-toolkit 0.10.1 + onnxruntime 1.26.0). OpenDsStar (the separate OpenDsStarAgent component) stays gated: all its releases still cap requires-python at <3.14 upstream. * test: correct stale <3.14 comment in ALTK test import guards The module-level import skips in the ALTK agent tests carried an outdated comment claiming "agent-lifecycle-toolkit is gated to python_version<'3.14' upstream". That is no longer accurate: agent-lifecycle-toolkit 0.10.1 dropped the <3.14 cap (now requires >=3.10), and this PR removes the langflow <3.14 marker on the altk extra. The skip itself is preserved -- altk is an optional extra (langflow-base[altk]) that may be absent from a given environment, so the ImportError guard is still required. Only the comment is corrected, to state the real reason for the skip plus the upstream change. Applied to all four files carrying the identical comment (test_altk_agent, test_altk_agent_logic, test_altk_agent_tool_conversion, test_conversation_context_ordering). Also tag a pre-existing fake test key (api_key="sk-test") with `# pragma: allowlist secret`; the comment shift re-staged the file and surfaced it to detect-secrets. Validated (Python 3.13, altk installed): ruff clean; the three logic modules run (64 passed, 4 skipped) and test_altk_agent collects (13).
Langflow 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. Langflow 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.
🖥️ Langflow Desktop
Langflow Desktop is the easiest way to get started with Langflow. All dependencies are included, so you don't need to manage Python environments or install packages manually. Available for Windows and macOS.
⚡️ Quickstart
Install locally (recommended)
Requires Python 3.10–3.14 and uv (recommended package manager).
Install
From a fresh directory, run:
uv pip install langflow -U
The latest Langflow package is installed. For more information, see Install and run the Langflow OSS Python package.
Run
To start Langflow, run:
uv run langflow run
Langflow starts at http://127.0.0.1:7860.
That's it! You're ready to build with Langflow! 🎉
📦 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 Langflow container with default settings:
docker run -p 7860:7860 langflowai/langflow:latest
Langflow is available at http://localhost:7860/. For configuration options, see the Docker deployment guide.
🛡️ Security
For security information, see our Security Policy.
🚀 Deployment
Langflow is completely open source and you can deploy it to all major deployment clouds. To learn how to deploy Langflow, see our Langflow deployment guides.
⭐ Stay up-to-date
Star Langflow on GitHub to be instantly notified of new releases.
👋 Contribute
We welcome contributions from developers of all levels. If you'd like to contribute, please check our contributing guidelines and help make Langflow more accessible.