# Crew AI memory and chatbot

**URL:** <https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372>\
**Category:** General\
**Created:** [March 4, 2025, 8:14am UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372 "2025-03-04T08:14:22Z")\
**Posts on this page:** 9\
**Page:** 1

<div class="post-metadata">

**Author:** ![spronin](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/spronin/32/2802_2.png) [@spronin](https://community.crewai.com/u/spronin)\
**Post date:** [March 4, 2025, 8:14am UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372/1 "2025-03-04T08:14:22Z")

</div>

Hey all.

I have a chat app. I’m using crews to respond to user inquiries in the chat.

I would like crews to provide answers and rely on a context from a previous questions.

My expectation is that Memory feature can help with that.

I configured my crew in the following way:

```auto
dynamic_crew = Crew(
                agents=crew_agents,
                tasks=crew_tasks,
                verbose=True,
                memory=True,
                embedder={
                    "provider": "google",
                    "config": {
                        "api_key": os.getenv("GEMINI_API_KEY"),
                        "model": "models/text-embedding-004"
                    }
                },
                long_term_memory=LongTermMemory(storage=LTMSQLiteStorage(
                    db_path=
                    "./memorydb/dynamic_crew_%s/long_term_memory_storage.db" %
                    user_id)),
                short_term_memory=ShortTermMemory(storage=RAGStorage(
                    type="short_term",
                    embedder_config={
                        "provider": "google",
                        "config": {
                            "api_key": os.getenv("GEMINI_API_KEY"),
                            "model": "models/text-embedding-004"
                        }
                    },
                    path="./memorydb/dynamic_crew_%s/" % user_id)),
                entity_memory=EntityMemory(storage=RAGStorage(
                    type="short_term",
                    embedder_config={
                        "provider": "google",
                        "config": {
                            "api_key": os.getenv("GEMINI_API_KEY"),
                            "model": "models/text-embedding-004"
                        }
                    },
                    path="./memorydb/dynamic_crew_%s/" % user_id)),
            )

```

As you see for each user the memory is stored in a different folder.  
I see the files are stored in the folder and memories are written, but at the same time I don’t see context being used.

Like I ask a simple question: How old is Nike brand? - got a response.  
The next question is: “What about Columbia?” - the crew response is not about the age at all.

Are my expectations wrong? I saw [this article](https://www.zinyando.com/building-a-conversational-chatbot-with-crewai-groq-chromadb-and-mem0/) from @zinyando that makes sense for my use case, but I’m curious if I can have built-in memory to work for this use case.

---

<div class="post-metadata">

**Author:** ![Ishmeet](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/ishmeet/32/3302_2.png) [@Ishmeet](https://community.crewai.com/u/Ishmeet)\
**Post date:** [April 8, 2025, 1:55pm UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372/2 "2025-04-08T13:55:06Z")

</div>

I am also interested in this use case

---

<div class="post-metadata">

**Author:** ![zinyando](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/zinyando/32/4435_2.png) [@zinyando](https://community.crewai.com/u/zinyando)\
**Post date:** [April 8, 2025, 2:00pm UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372/3 "2025-04-08T14:00:24Z")

</div>

This is a bit difficult to achieve with just built in memory, you need a combination of short-term memory (conversation history) and long term memories to have a proper chatbot that understand the context of the conversation.

This this thread is a bit old, did you manage to achieve what you wanted?

---

<div class="post-metadata">

**Author:** ![spronin](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/spronin/32/2802_2.png) [@spronin](https://community.crewai.com/u/spronin)\
**Post date:** [April 14, 2025, 8:00am UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372/4 "2025-04-14T08:00:04Z")

</div>

@zinyando frankly no. I had multiple attempts, but memory is still not working as I would expect.

I just want to have some clarity about memory in CrewAI. What are the intended use cases if not the context enrichment from previous requests.

---

<div class="post-metadata">

**Author:** ![Serge\_B](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/serge_b/32/3407_2.png) [@Serge\_B](https://community.crewai.com/u/Serge_B)\
**Post date:** [April 29, 2025, 6:58pm UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372/5 "2025-04-29T18:58:40Z")

</div>

I’m not sure what the level of solution you work on, but there are a couple of techs for mids and enterprise grade providing long memory in specific cases - one works like a cognitive memory within the chat, another like business intent memory in specific product context.

---

<div class="post-metadata">

**Author:** ![spronin](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/spronin/32/2802_2.png) [@spronin](https://community.crewai.com/u/spronin)\
**Post date:** [April 29, 2025, 7:45pm UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372/6 "2025-04-29T19:45:58Z")

</div>

@Serge_B yeah, I get it. like mem0 or smth.  
I can use those.

But I’m still interested what is the goal of memory feature in CrewAI. Is it not working as intended or I’m trying to misuse it?

---

<div class="post-metadata">

**Author:** ![David\_Ryan](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/david_ryan/32/2503_2.png) [@David\_Ryan](https://community.crewai.com/u/David_Ryan)\
**Post date:** [June 23, 2025, 8:43pm UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372/7 "2025-06-23T20:43:30Z")

</div>

Hey, did you make any progress on this? I’m also looking into options around long term and short term memory for conversational interactions

---

<div class="post-metadata">

**Author:** ![zinyando](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/zinyando/32/4435_2.png) [@zinyando](https://community.crewai.com/u/zinyando)\
**Post date:** [July 1, 2025, 12:06pm UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372/8 "2025-07-01T12:06:26Z")

</div>

Hey, did you get a solution to your issue? For long term memory, I usually just use Mem0/Zep and for short term I just store the conversation history and return x last chats.

I don’t know your particular use case and situation but I’d be happy to help you figure something out if you haven’t yet.

---

<div class="post-metadata">

**Author:** ![moryachok](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/moryachok/32/4591_2.png) [@moryachok](https://community.crewai.com/u/moryachok)\
**Post date:** [November 1, 2025, 6:29pm UTC](https://community.crewai.com/t/crew-ai-memory-and-chatbot/4372/9 "2025-11-01T18:29:09Z")

</div>

It looks like the build in memory doesnt provide conversation history like functionality and you need to implement that yourself.
