
by Langflow
Langflow is a visual builder for AI agents, RAG applications and workflows. You assemble components by drag and drop, extend them in Python, and deploy flows as APIs or MCP servers.
Web appFree
Step 1: Install Langflow, or start with Langflow Desktop or a free cloud account.
Step 2: Create a flow and add components such as a model, a data source or a vector store.
Step 3: Connect the components and edit any component in Python if you need custom logic.
Step 4: Test the flow in the Playground and inspect component responses and logs.
Step 5: Deploy the flow as an API using Docker, Langflow Cloud or watsonx Orchestrate.
Yes. Every component exposes its configuration, and you can use Python to customize components or create new tools.
You can run it locally in Langflow Desktop, deploy it as a REST service with Docker, or publish it to Langflow Cloud or watsonx Orchestrate.
Yes. The pages describe building and deploying your own MCP server in Langflow.
It is meant for local development, quick prototyping and offline or isolated workflows, with local LLM support and export to a cloud-ready format.
AgentverseAgentverse is Fetch.ai's platform for hosting AI agents and making them discoverable, including through ASI:One. You can build hosted agents in the browser or connect agents that run on your own infrastructure.
DelysiumDelysium is building a blockchain-based network where AI agents collaborate. Its first agent, Lucy, is an AI-powered Web3 operating system on the YKILY Network.
FlowiseFlowise is an open source platform for building AI agents and LLM workflows with a visual builder. It offers chat assistants, multi-agent workflows, tracing and an API.