Powering Memory in Foundry Agent Service with Azure Cosmos DB
adnan_hashmi · x · 2026-08-25
This post details how to use Azure Cosmos DB to provide memory capabilities for agents deployed in Microsoft Foundry Agent Service. It builds on the previously introduced CosmosMemoryContextProvider, moving from a locally composed agent to a cloud-deployed service. The featured sample uses azd up for provisioning and includes a browser app to visualize the difference between conversation history and long-term memory.
More from coding & agent
- Toyota scales AI delivery from 6 months to 4 days using LangGraph and LangSmith — LangChain · 2026-08-25
- The Winchester Mystery House in AI: DSPy, Flex optimizer, and the cost of feedback loops — dbreunig · 2026-08-25
- Unified Agent benchmarks: Same task, same browser, same tools — SucceededMind · 2026-08-25
- Astra's Continual Learning Blueprint from GPT's Goblin Problem — imjustnewatai · 2026-08-25
- Expert Validation Becomes Bottleneck in AI Projects — anmarasovic · 2026-08-25
- RocketRide: Visually build AI pipelines inside your IDE — abhishek__AI · 2026-08-25