Langflow — Visual Agent & Workflow Builder
Low-code visual builder for LLM-powered agents and multi-step AI workflows with 100+ pre-built components.
Langflow
Langflow is a powerful low-code platform for building, testing, and deploying AI-powered agents and multi-step workflows. Its drag-and-drop canvas and Python-based component model let you wire together LLMs, retrieval systems, memory stores, tools, and output parsers without boilerplate.
Key Features
- Visual canvas for composing agentic pipelines
- 100+ built-in components: LLMs, vector stores, agents, tools, memory
- One-click export to Python and REST API
- Multi-agent support: supervisor, parallel, hierarchical patterns
- Playground for rapid iteration with live logs
- Integrates with LangChain, OpenAI, Anthropic, Ollama, and more
Quick Start
pip install langflow
langflow run
# Opens visual canvas at http://127.0.0.1:7860
from langflow.load import run_flow_from_json
result = run_flow_from_json(
flow="my_agent.json",
input_value="Summarise the latest AI news",
)
print(result)
Install via ai-supply
npx ai-supply add langflow-visual-agent-builder
Curated mirror of the open-source Langflow (MIT). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/langflow-visual-agent-builder/check). Click a policy:
Consume Langflow — Visual Agent & Workflow Builder programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/langflow-visual-agent-builder
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/langflow-visual-agent-builder/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add langflow-visual-agent-builder
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/langflow-visual-agent-builder/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "langflow-visual-agent-builder" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.