Langflow

by DataStax

Open Source Self-Hostable Cloud Free Tier freemium API Available

Visual low-code platform for building AI agents and RAG applications with drag-and-drop components Langflow is a visual, low-code platform for building AI agents, retrieval-augmented generation (RAG) pipelines, and multi-step AI workflows using a drag-and-drop interface. Originally created as an open-source project in 2023, Langflow was acquired by DataStax in 2024 and integrated with the Astra DB vector database platform.

Performance Scores

7.5

2 rankings evaluated

Score range: 6.8 – 8.2

Key Facts

pricing

pricing facts about Langflow
AttributeValueAs ofSource
Langflow pricing (July 2026)Langflow is free (verified July 2026): the open-source project self-hosts free, Langflow Desktop is a free local app, and a free Langflow Cloud account is available. Hosted Cloud/Enterprise is custom-priced and not publicly listed. Running costs are infrastructure plus LLM API fees.Jul 2026Langflow
LicenseOpen-source MIT license; free to self-hostApr 2026GitHub

General

General facts about Langflow
AttributeValueAs ofSource
Origin2023 (open-source project)Mar 2026Langflow
Acquired ByDataStax (2024); DataStax itself acquired by IBM, deal completed 28 May 2025Jul 2026IBM Newsroom
GitHub Stars150,000+ (as of July 2026)Jul 2026GitHub API (langflow-ai/langflow)
InterfaceVisual drag-and-drop node editorJul 2026Langflow official site
RAG SupportNative RAG pipeline componentsJul 2026Langflow official site
Cloud PricingOpen-source core is free; Langflow Cloud offers a free account, with no public paid price list (as of July 2026)Jul 2026Langflow official site
Self-HostingOpen-source, pip/Docker installJul 2026Langflow docs — installation

capability

capability facts about Langflow
AttributeValueAs ofSource
Platform TypeVisual low-code builder for AI agents and RAG workflows (Python); framework-agnostic since 1.x, no longer limited to LangChainJul 2026Langflow GitHub README
Cloud OptionDataStax's Astra-hosted managed Langflow was shut down in April 2026; as of July 2026 there is no managed cloud — self-hosted Langflow OSS is the recommended optionJul 2026DataStax Docs — DataStax Langflow

company

company facts about Langflow
AttributeValueAs ofSource
SponsorMaintained by DataStax (acquired Langflow in 2024); DataStax was acquired by IBM in May 2025, bringing Langflow into IBM's watsonx portfolioJul 2026IBM Newsroom

Strengths

  • Open-source under MIT, runs locally with no vendor lock-in
  • Visual canvas maps cleanly to LangChain primitives developers already know
  • Active community with frequent component updates
  • Self-hosted option meets strict data-residency requirements
  • Arbitrary unsandboxed Python components with full host filesystem and network access
  • Any model provider including local Ollama and vLLM
  • MCP in both directions, with flows auto-exposed as MCP tools, plus an A2A server
  • Self-hosts and air-gaps cleanly, with 73 pip-installable provider bundles carrying stable extension identifiers

Limitations

  • Self-hosted operators handle their own audit logs, RBAC, and security posture
  • Tied to LangChain abstractions, which evolve quickly and can break flows
  • Managed cloud is newer than the open-source project — feature parity still settling
  • The open-source authorization service allows every action for every authenticated user, ships no enforcement plugin and provides no tenant isolation
  • No SOC 2, ISO 27001 or HIPAA position is published
  • Two unauthenticated remote-code-execution-class CVEs were reported against Langflow in 2026
  • IBM Langflow Cloud is in private preview, so the only production path is infrastructure the team stands up itself
  • The connector set covers AI infrastructure rather than business SaaS, and there is no extension marketplace

Based on evaluations in 2 rankings: Best LLM App Platforms for Building AI Agents in 2026, Most Customizable AI Agent Platforms 2026

About Langflow

Langflow is a visual, low-code platform for building AI agents, retrieval-augmented generation (RAG) pipelines, and multi-step AI workflows using a drag-and-drop interface. Originally created as an open-source project in 2023, Langflow was acquired by DataStax in 2024 and integrated with the Astra DB vector database platform. IBM completed its acquisition of DataStax on 28 May 2025, so Langflow now sits under IBM.

The platform provides a node-based visual editor where users connect components representing LLMs, vector stores, document loaders, text splitters, embedding models, and custom Python code. Each component has configurable inputs and outputs, allowing users to build complex AI pipelines without writing infrastructure code. As of early 2026, Langflow supports connections to OpenAI, Anthropic Claude, Google Gemini, Cohere, HuggingFace models, and local LLMs via Ollama.

Langflow can be self-hosted (open-source, available on GitHub with 150,000+ stars) or used through the DataStax-hosted cloud version. The cloud version includes a free tier with limited executions, no publicly listed paid-tier price, and enterprise pricing for teams needing dedicated infrastructure and support. The platform targets developers and technical teams building AI-powered applications who want a visual development environment rather than pure code.

Integrations (6)

Anthropic Claude native
HuggingFace native
LangChain native
OpenAI native
Pinecone native
Weaviate native

Written & reviewed by Rafal Fila · Last updated: · Last verified:

Other AI Agent Platforms Tools

See How It Ranks

Questions About Langflow

Can you build AI agents in n8n?

Yes. As of May 2026, n8n ships an AI Agent node that wraps LangChain tools, memory, and vector stores, allowing visual or code-based construction of ReAct-style agents with branching, retries, and human-in-the-loop steps. The free Community Edition supports the AI Agent node with no usage cap when self-hosted.

What is the best LLM app platform in 2026?

As of April 2026, the leading LLM app platforms are LangChain (most-used Python and JS framework), Vellum (production prompt and eval platform), Langflow (open-source visual builder), Dust (workspace assistants), and LlamaIndex (data-framework for RAG). Choice depends on visual versus code preference and whether teams need eval, RAG, or workspace assistants.

How does Vellum compare to Langflow in 2026?

As of April 2026, Vellum is a developer platform for production LLM apps focused on prompt management, evaluation, and deployment, while Langflow is an open-source visual builder for LangChain flows. Vellum wins on eval, observability, and prompt versioning; Langflow wins on visual prototyping and zero-cost self-hosting.

What are the best Vellum alternatives in 2026?

As of April 2026, the leading Vellum alternatives are Langflow (open-source visual LangChain builder), LangSmith (LangChain observability and eval), Dust (workspace-grade AI assistants), Relevance AI (low-code AI agents), and Humanloop (prompt management and evaluation). Selection depends on whether teams need prompt eval, agent orchestration, or production deployment.

Learn More