Store persistent user profiles and chat summaries in Azure AI Foundry.
npx skills add https://github.com/aiappsgbb/awesome-gbb --skill foundry-memory
Please help me install this Agent Skill. Skill: foundry-memory Source: https://github.com/aiappsgbb/awesome-gbb/tree/main/skills/foundry-memory Command: npx skills add https://github.com/aiappsgbb/awesome-gbb --skill foundry-memory
Foundry agent teams need a reliable way to remember user-specific preferences and cross-session conversation context without bolting on external memory middleware.
Example use case: build a hosted Foundry agent that personalizes responses for each user by recalling their stored preferences and maintaining a rolling summary of the discussion over multiple sessions.
Configure a Foundry Memory Store with your chat and embedding model deployments, attach the memory tool to your agent with scope set to {{$userId}}, and then have the agent use stored memories while updating them after inactivity.
High-intent search queries and answers about installing and using this skill.
You add persistent memory to an Azure AI Foundry agent by attaching the Foundry Memory tool to store durable user profiles and cross-session chat summaries, enabling long-term personalization without external memory middleware.
Scope isolation restricts memory access to specific users by setting the scope to {{$userId}} or an explicit header, ensuring Azure AI Foundry agents retrieve and write user-specific memories securely across sessions.
Yes, using Foundry persistent memory requires an embedding deployment like text-embedding-3-small or text-embedding-3-large for semantic retrieval, plus azure-ai-projects version 2.0.0 or higher.
Chat summaries store distilled context of prior threads so later conversations can resume without replaying the full transcript. The agent updates these rolling summaries automatically after periods of inactivity.
Yes, you can build a Foundry agent that remembers user preferences without external memory sidecars. The native Foundry Memory tool directly stores stable facts and UI choices within the Azure AI environment.
The best way to store user profile facts for conversational agents is using the Foundry Memory Store, which persists stable preferences like units and role context, allowing agents to automatically retrieve relevant memories.
evanfang0054Builds RAG pipelines with LangChain.jsUTE, including data ingestion, vectorization and semantic search retrieval.
PsqasimManage AI agent memory across sessions with LangChain-compatible vector stores.
Aaron-TawilCreate conversational chat interfaces in Streamlit with st.chat_message and st.chat_input.
krzysztofsurdyReference LangChain components for building agents, RAG pipelines, and LangGraph workflows.
