> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Agent Memory
> Understanding how agents maintain context and learn
Memory lets agents remember conversations and learn from past interactions. Without memory, every message is like starting fresh.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Without Memory"
A1[❓ Who am I?] --> A2[🤖 I don't know]
end
subgraph "With Memory"
B1[👤 I'm Alex] --> B2[💾 Saved]
B2 --> B3[❓ Who am I?]
B3 --> B4[🤖 You're Alex!]
end
classDef question fill:#8B0000,stroke:#7C90A0,color:#fff
classDef memory fill:#2E8B57,stroke:#7C90A0,color:#fff
classDef agent fill:#189AB4,stroke:#7C90A0,color:#fff
class A1,B1,B3 question
class B2 memory
class A2,B4 agent
```
***
## Quick Start
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
# Enable memory with one parameter
agent = Agent(
instructions="You are a personal assistant",
memory=True # Remember conversations
)
agent.start("My name is Alex and I love Python")
# Later...
agent.start("What's my name?") # Agent remembers: "Alex"
```
Just add `memory=True` to enable conversation memory.
***
## Types of Memory
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph TB
subgraph "Memory Types"
Short[💬 Short-Term
Current conversation]
Long[💾 Long-Term
Across sessions]
Knowledge[📚 Knowledge
Documents & data]
end
Short --> Agent[🤖 Agent]
Long --> Agent
Knowledge --> Agent
classDef short fill:#8B0000,stroke:#7C90A0,color:#fff
classDef long fill:#189AB4,stroke:#7C90A0,color:#fff
classDef knowledge fill:#2E8B57,stroke:#7C90A0,color:#fff
class Short short
class Long long
class Knowledge knowledge
class Agent long
```
Remembers current chat
Persists across sessions
Access to documents
***
## Memory Options
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
agent = Agent(
instructions="You are helpful",
memory=True # Remembers the conversation
)
```
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
agent = Agent(
instructions="You are a personal assistant",
memory={
"provider": "sqlite", # Store in database
"db_path": "memory.db"
}
)
```
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
agent = Agent(
instructions="Answer from documents",
knowledge=["docs/"], # Load documents
memory=True
)
```
***
## How Memory Works
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Memory Flow"
Input[📥 Your Message] --> Process[🧠 Process]
Memory[💾 Memory] --> Process
Process --> Response[💬 Response]
Process --> Save[💾 Save to Memory]
end
classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
classDef memory fill:#2E8B57,stroke:#7C90A0,color:#fff
class Input input
class Process,Response process
class Memory,Save memory
```
| Step | What Happens |
| ------------ | ------------------------------- |
| **Input** | You send a message |
| **Retrieve** | Agent checks memory for context |
| **Process** | Combines memory + new input |
| **Respond** | Generates informed response |
| **Save** | Stores important info for later |
***
## Complete Example
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
# Personal assistant with memory
assistant = Agent(
name="PersonalAssistant",
instructions="""You are a personal assistant.
Remember user preferences and past conversations.
Be helpful and personalized.""",
memory=True
)
# First conversation
assistant.start("I prefer short, bullet-point answers")
assistant.start("My favorite programming language is Python")
# Later conversation - agent remembers!
assistant.start("Explain how to read a file")
# Agent will give short, bullet-point answer about Python
```
***
## Multi-Agent Memory
Agents can share memory or have private memory:
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph TB
subgraph "Shared Memory"
A1[🤖 Agent 1] --> Shared[💾 Shared Memory]
A2[🤖 Agent 2] --> Shared
end
classDef agent fill:#189AB4,stroke:#7C90A0,color:#fff
classDef memory fill:#2E8B57,stroke:#7C90A0,color:#fff
class A1,A2 agent
class Shared memory
```
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, AgentTeam
# Agents with shared memory
researcher = Agent(instructions="Research topics", memory=True)
writer = Agent(instructions="Write summaries", memory=True)
team = AgentTeam(
agents=[researcher, writer],
memory=True # Shared team memory
)
```
***
## Best Practices
Use `memory=True` first, add complexity later
Tell the agent what to remember in instructions
For documents, use `knowledge=` not memory
Verify the agent remembers correctly
***
Learn how multiple agents work together.