From a5c7416496e905364ebf67fde23ce1a703966278 Mon Sep 17 00:00:00 2001 From: mahdi Date: Tue, 27 Jan 2026 11:56:56 +0800 Subject: [PATCH 1/2] clarifies the doc about short term nature of the memory --- docs/examples/python/memory_agent.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/docs/examples/python/memory_agent.md b/docs/examples/python/memory_agent.md index eacf5178f..366849170 100644 --- a/docs/examples/python/memory_agent.md +++ b/docs/examples/python/memory_agent.md @@ -18,7 +18,7 @@ The memory agent utilizes two primary tools: 1. **memory**: Enables storing and retrieving information with capabilities for: - - Storing user-specific information persistently + - Storing user-specific information, either persistently or temporarily - Retrieving memories based on semantic relevance - Listing all stored memories for a user - Setting relevance thresholds and result limits @@ -30,7 +30,10 @@ The memory agent utilizes two primary tools: ## Memory-Enhanced Response Generation Workflow -This example demonstrates a workflow where memories are used to generate contextually relevant responses: +> [!NOTE] +> The memory used in this workflow is short-term and scoped to the current session. See [memory types](https://docs.mem0.ai/core-concepts/memory-types) for more details. Update the [configuration](https://docs.mem0.ai/components/vectordbs/config) to enable persistent storage across sessions. + +This example demonstrates a workflow where memories are used to generate contextually relevant responses. ```mermaid flowchart TD From 8575597256dfe15281ba4afa5320256ea35d4e47 Mon Sep 17 00:00:00 2001 From: Mahdi Azarboon <21277296+azarboon@users.noreply.github.com> Date: Fri, 20 Mar 2026 14:18:11 +0800 Subject: [PATCH 2/2] update to incorporate maintainer feedback --- docs/examples/python/memory_agent.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/examples/python/memory_agent.md b/docs/examples/python/memory_agent.md index 366849170..03ea16d59 100644 --- a/docs/examples/python/memory_agent.md +++ b/docs/examples/python/memory_agent.md @@ -18,7 +18,7 @@ The memory agent utilizes two primary tools: 1. **memory**: Enables storing and retrieving information with capabilities for: - - Storing user-specific information, either persistently or temporarily + - Storing user-specific information persistently - Retrieving memories based on semantic relevance - Listing all stored memories for a user - Setting relevance thresholds and result limits @@ -31,7 +31,7 @@ The memory agent utilizes two primary tools: ## Memory-Enhanced Response Generation Workflow > [!NOTE] -> The memory used in this workflow is short-term and scoped to the current session. See [memory types](https://docs.mem0.ai/core-concepts/memory-types) for more details. Update the [configuration](https://docs.mem0.ai/components/vectordbs/config) to enable persistent storage across sessions. +> By default, mem0 persists memories to local storage at `~/.mem0/`. See [mem0 vector store configuration](https://docs.mem0.ai/components/vectordbs/config) for options on using a different backend for production use. This example demonstrates a workflow where memories are used to generate contextually relevant responses.