Analytics cookies only (Google Analytics, PostHog). No ad networks, no cross-site tracking. See our privacy policy.
A visual builder for AI agents and workflows: connect models, vector stores and tools as components on a canvas, then serve each flow through an API or as an MCP server. Runs on SQLite by default, or PostgreSQL for production.
Runs on a VPS from $12/mo (Kamatera 4GB, 4 GB RAM) · prices checked Nov 2026
Fits home hardware (1,229 MB measured idle, RAM only): Raspberry Pi 4 (4 GB) (arm64 untested), Raspberry Pi 5 (8 GB) (arm64 untested), Repurposed laptop (8 GB), Intel N100 mini PC (16 GB), AMD Ryzen mini PC (32 GB).
Paid link — we earn a commission if you shop through it.
Run these commands on your server:
# Langflow — official image (docs.langflow.org → Deploy Langflow on Docker), pinned to the 1.12.3 release
# the image sets LANGFLOW_AUTO_LOGIN=false, so a superuser password is required; generate one and keep it
export LANGFLOW_SUPERUSER_PASSWORD="$(openssl rand -hex 16)" && echo "$LANGFLOW_SUPERUSER_PASSWORD"
docker run -d --name langflow --restart unless-stopped \
-p 7860:7860 \
-e LANGFLOW_SUPERUSER=admin -e LANGFLOW_SUPERUSER_PASSWORD \
-e LANGFLOW_CONFIG_DIR=/app/langflow -v langflow-data:/app/langflow \
langflowai/langflow:1.12.3
# SQLite in the langflow-data volume; for PostgreSQL use the repo's docker_example/docker-compose.yml
# log in as admin → http://SERVER_IP:7860The team LLM-app platform vs. the Python-component canvas.
A TypeScript visual agent builder whose repository has been archived by its owner, or a Python canvas you can edit component by component.
Langflow used 1229 MB of RAM at idle on GCP e2-standard-2 · Ubuntu 26.04 LTS · Docker 29.8.1 (first boot, measured Sep 2026). We list a minimum of 2048 MB.
The Langflow install snippet is marked verified on Ubuntu 26.04 (Nov 2026).