# Agno

Adding persistent memory to Agno agents with the SurrealDB Agent Memory SDK.

[Agno](https://www.agno.com/) is a high-performance Python framework for building agents. SurrealDB Agent Memory adds long-term memory that persists across sessions and agents. There is no dedicated adapter. The [Python SDK](/docs/agent-memory/integrations/sdks/python.md) (`surrealdb`) exposes the memory operations you attach as Agno tools.

> [!NOTE]
> This is an integration guide. It wires the SurrealDB Agent Memory SDK into Agno's tool interface; adapt to your installed Agno version.

## Installation

> [!NOTE]
> `Spectron` was the project name for SurrealDB Agent Memory. These type names
> will be renamed in a future release.

```bash
pip install agno openai
pip install --pre surrealdb
```

```bash
export SPECTRON_ENDPOINT="https://api.spectron.example"
export SPECTRON_CONTEXT="acme-prod"
export SPECTRON_API_KEY="sk-spec-..."
```

## Memory as tools

Agno agents take a `tools` list. Pass functions that call the SurrealDB Agent Memory client, and Agno exposes them to the model:

```python
import os
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from surrealdb import Spectron

memory = Spectron(
    endpoint=os.environ["SPECTRON_ENDPOINT"],
    context=os.environ["SPECTRON_CONTEXT"],
    api_key=os.environ["SPECTRON_API_KEY"],
)
scope = ["org/acme/user/alice"]

def remember(text: str) -> str:
    """Store a durable fact for later recall."""
    memory.remember(text, scopes=scope)
    return "stored"

def recall(query: str) -> str:
    """Retrieve relevant memory for a query."""
    return memory.query_context(query, k=8, lens=scope)

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    tools=[remember, recall],
    instructions="Use recall before answering and remember anything worth keeping.",
    markdown=True,
)

agent.print_response("What do you know about Alice's role?")
```

## Recall around a run

Recall first, add the context to the agent's instructions, then store the exchange after the response:

```python
block = memory.query_context(user_message, k=8, lens=scope)

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    instructions=f"You are a helpful assistant.\n\n## Memory\n{block}",
)
response = agent.run(user_message)

memory.remember_many(
    [{"role": "user", "content": user_message}, {"role": "assistant", "content": response.content}],
    scopes=scope,
)
```

> [!NOTE]
> Agno ships its own session storage and user-memory primitives (`enable_user_memories=True`). Use SurrealDB Agent Memory when you want a shared, provenance-first memory that several agents or services read and write, with server-side extraction and hybrid recall.

## Scope per user

Pass a `scope` on every call to isolate memory. A scope is a slash path or an array of paths, for example `["org/acme/user/alice"]`. Register paths with `spectron scopes create` before first use.

## Next steps

- [Python SDK](/docs/agent-memory/integrations/sdks/python.md): the full client surface
- [MCP server](/docs/agent-memory/integrations/mcp-server/install.md): if your host speaks MCP instead