Agent Workflow Platformvslangflow
Two self-hosted AI Agents projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.
| Agent Workflow Platform | langflow | |
|---|---|---|
| Score | 39/100 | 90/100 |
| Rank in category | #172 of 208 in AI Agents | #2 of 208 in AI Agents |
| GitHub stars | 106 | 156 689 |
| Stars, last 30 days | +1 | +1 126 |
| Stable releases, 12 months | 1 | 24 |
| Latest release | v0.1.0 · 23 Aug 2026 | v1.13.2 · 8 Nov 2026 |
| Setup | Advanced | Moderate |
| Official Docker image | No | Yes |
| License | MIT | MIT |
| Main language | Typescript | Python |
Which one should you pick?
langflow scores 90/100 against 39/100 for Agent Workflow Platform, so it is the safer default.
langflow ships more often: 24 stable releases in the past year, against 1 for Agent Workflow Platform.
If you want the quickest setup, langflow is easier to run; Agent Workflow Platform needs more configuration.
langflow is growing faster right now (+1 126 stars in 30 days).
Key differences
- Language: Agent Workflow Platform is written mainly in Typescript, langflow in Python.
- Only langflow ships an official Docker image.
- Features only Agent Workflow Platform lists: Agent CLI Protocol, Crash Recovery Verification, Cross-platform CI Validation, Docker Compose Deployment and 10 more.
- Features only langflow lists: Deploy as API, Desktop application, Interactive playground, Major LLM support and 5 more.
Agent Workflow Platform details →langflow details →All AI Agents projects →
Swap a project
Keep Agent Workflow Platform, compare it with
Keep langflow, compare it with