A
Langflow
96.8
156,720 stars · MIT
AI Agents
Open WebUI leads by 2.3 · narrow
A
96.8
156,720 stars · MIT
B · leads
99.1
158,922 stars · MIT
Langflow versus Open WebUI is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. Langflow is written mainly in Python; Open WebUI is written mainly in Svelte. The composite score is 96.8 for Langflow and 99.1 for Open WebUI.
Open WebUI has 158,922 GitHub stars to Langflow's 156,720, a gap of 2,202 (1.01×). Forks are 10,426 for Langflow and 23,097 for Open WebUI. On the log scale used inside this pair, adoption is 100 versus 100, and the fork community is 92 versus 100.
Push history: Langflow was last pushed on 17 November 2026 (0 days ago), and Open WebUI was last pushed on 17 November 2026 (0 days ago). Open issues stand at 1,340 for Langflow (0.009 per star) and 208 for Open WebUI (0.001 per star). Issue-health scores are 84 and 96; activity scores are 100 and 100.
Both Langflow and Open WebUI are listed as MIT. A permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. The license score is therefore level at 96 versus 96, and the decision moves to adoption, activity, and hosting. This is a procurement signal, not legal advice.
In AI Agents, both Langflow (156,720 stars) and Open WebUI (158,922 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: Langflow is open source, Open WebUI is open source.
Open WebUI is ahead on every scored dimension that is not level. Level dimensions: recent activity, license flexibility, self-hosting. The widest gap is issue health at 12 points (84 vs 96), and the tightest is self-hosting at 0 points (100 vs 100).
Open WebUI finishes ahead at 99.1 against Langflow at 96.8, a 2.3 point narrow margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | Langflow | Open WebUI |
|---|---|---|
| GitHub stars | 156,720 | 158,922 |
| Forks | 10,426 | 23,097 |
| Open issues | 1,340 | 208 |
| Adoption | 100 | 100 |
| Activity | 100 | 100 |
| Community | 92 | 100 |
| Issue health | 84 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 96.8 | 99.1 |
Langflow is a visual environment for composing language-model flows and agents. It exports the graph as code and is used to prototype retrieval and tool-using apps.
Open WebUI is a self-hosted chat interface for local and remote language models, including Ollama. It adds users, documents, and tools around the model endpoint.
Open WebUI has more GitHub stars: 158,922 versus 156,720 for Langflow. The gap is 2,202 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both Langflow and Open WebUI as self-hostable. Confirm each project's deploy docs before you plan a migration.
Langflow is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Open WebUI is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
Open WebUI scores 99.1 and Langflow scores 96.8. This page calls that a narrow lead for Open WebUI.