```python
from langchain.memory import ConversationBufferMemory
```
```python
memory = ConversationBufferMemory()
memory.save_context({"input": "hi"}, {"output": "whats up"})
```
```python
memory.load_memory_variables({})
```
```
    {'history': 'Human: hi\nAI: whats up'}
```
We can also get the history as a list of messages (this is useful if you are using this with a chat model).
```python
memory = ConversationBufferMemory(return_messages=True)
memory.save_context({"input": "hi"}, {"output": "whats up"})
```
```python
memory.load_memory_variables({})
```
```
    {'history': [HumanMessage(content='hi', additional_kwargs={}),
      AIMessage(content='whats up', additional_kwargs={})]}
```
## Using in a chain
Finally, let's take a look at using this in a chain (setting `verbose=True` so we can see the prompt).
```python
from langchain.llms import OpenAI
from langchain.chains import ConversationChain
llm = OpenAI(temperature=0)
conversation = ConversationChain(
    llm=llm, 
    verbose=True, 
    memory=ConversationBufferMemory()
)
```
```python
conversation.predict(input="Hi there!")
```
```
    
    
    > Entering new ConversationChain chain...
    Prompt after formatting:
    The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
    
    Current conversation:
    
    Human: Hi there!
    AI:
    
    > Finished chain.
    " Hi there! It's nice to meet you. How can I help you today?"
```
```python
conversation.predict(input="I'm doing well! Just having a conversation with an AI.")
```
```
    
    
    > Entering new ConversationChain chain...
    Prompt after formatting:
    The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
    
    Current conversation:
    Human: Hi there!
    AI:  Hi there! It's nice to meet you. How can I help you today?
    Human: I'm doing well! Just having a conversation with an AI.
    AI:
    
    > Finished chain.
    " That's great! It's always nice to have a conversation with someone new. What would you like to talk about?"
```
```python
conversation.predict(input="Tell me about yourself.")
```
```
    
    
    > Entering new ConversationChain chain...
    Prompt after formatting:
    The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
    
    Current conversation:
    Human: Hi there!
    AI:  Hi there! It's nice to meet you. How can I help you today?
    Human: I'm doing well! Just having a conversation with an AI.
    AI:  That's great! It's always nice to have a conversation with someone new. What would you like to talk about?
    Human: Tell me about yourself.
    AI:
    
    > Finished chain.
    " Sure! I'm an AI created to help people with their everyday tasks. I'm programmed to understand natural language and provide helpful information. I'm also constantly learning and updating my knowledge base so I can provide more accurate and helpful answers."
```
And that's it for the getting started! There are plenty of different types of memory, check out our examples to see them all