We just published the demo video from our latest @DBOS_Inc user group! Big thanks to Adrian Lyjak from @llama_index for walking through the …

We just published the demo video from our latest @DBOS_Inc user group! Big thanks to Adrian Lyjak from @llama_index for walking through the DBOS integration with LlamaAgents, an open-source Python framework for building and deploying document-centric AI agents. One thing I really like about this integration is how transparent and lightweight it feels for developers. To make workflows and steps with durable DBOS, you simply drop in a DBOSRuntime. From there, every workflow becomes a DBOS durable workflow, and every step becomes a DBOS durable step automatically. That means your LlamaAgent workflows become resilient to restarts and failures, while also making it easy to distribute work across multiple workers connected to the same database. All without rewriting your existing LlamaAgent workflows. The live demo on parsing tax forms to reduce meticulous manual work was especially impressive too. Check out the video and give LlamaAgents a try. Links below!

Source: Jerry Liu (X) | 2026-05-11