> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Learning Demo: AgentOS Server

> Serves the ops assistant on an AgentOS instance, which exposes the /learnings CRUD endpoints and powers the Learning pages at os.agno.com.

```python run.py theme={null}
"""
Learning Demo: AgentOS Server
=============================
Serves the ops assistant on an AgentOS instance, which exposes the
/learnings CRUD endpoints and powers the Learning pages at os.agno.com.

Requires the pgvector container:
    ./cookbook/scripts/run_pgvector.sh

Run seed.py first so the Learning pages have data:
    .venvs/demo/bin/python cookbook/08_learning/10_demo/seed.py

Then start the server:
    .venvs/demo/bin/python cookbook/08_learning/10_demo/run.py

Then open https://os.agno.com, connect to http://localhost:7777, and
browse the Learning section: User Profiles, User Memories, Entity
Memories, Session Context, and Decision Logs.

Interactive API docs are at http://localhost:7777/docs.
"""

from agents import ops_assistant
from agno.os import AgentOS

agent_os = AgentOS(
    description="Learning demo: one agent with every learning store enabled",
    agents=[ops_assistant],
)
app = agent_os.get_app()


if __name__ == "__main__":
    agent_os.serve(app="run:app", reload=True)
```

The example imports this helper module from the same directory:

```python agents.py theme={null}
"""
Learning Demo: Shared Agent
===========================
A single ops assistant with every learning store enabled:

- User Profile: structured fields (name, role, preferences)
- User Memory: unstructured observations about the user
- Session Context: a running summary of each session
- Entity Memory: facts, events, and relationships about external things
- Learned Knowledge: insights that transfer across users (pgvector)
- Decision Log: significant decisions with reasoning

Requires the pgvector container:
    ./cookbook/scripts/run_pgvector.sh
"""

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.knowledge import Knowledge
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.learn import (
    LearningMachine,
)
from agno.models.openai import OpenAIResponses
from agno.vectordb.pgvector import PgVector, SearchType

# ---------------------------------------------------------------------------
# Database
# ---------------------------------------------------------------------------
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
db = PostgresDb(id="learning-demo-db", db_url=db_url)

# Learned Knowledge needs a vector store for semantic search.
knowledge = Knowledge(
    vector_db=PgVector(
        db_url=db_url,
        table_name="learning_demo_knowledge",
        search_type=SearchType.hybrid,
        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
    ),
)

# ---------------------------------------------------------------------------
# Learning Machine: all six stores enabled
# ---------------------------------------------------------------------------
learning = LearningMachine(
    db=db,
    model=OpenAIResponses(id="gpt-5.5"),
    knowledge=knowledge,
    user_profile=True,
    user_memory=True,
    session_context=True,
    entity_memory=True,
    learned_knowledge=True,
    decision_log=True,
)

# ---------------------------------------------------------------------------
# Agent
# ---------------------------------------------------------------------------
ops_assistant = Agent(
    id="ops-assistant",
    name="Ops Assistant",
    model=OpenAIResponses(id="gpt-5.5"),
    db=db,
    learning=learning,
    instructions=[
        "You are an engineering operations assistant.",
        "Keep answers short and practical.",
        "Search your learnings before answering substantive questions.",
        "When the user shares a team-wide insight or asks you to remember one, save it with the save_learning tool.",
        "When you make a significant recommendation, record it with the log_decision tool, including your reasoning and the alternatives you considered.",
    ],
    markdown=True,
)
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[os]" fastmcp openai pgvector psycopg-binary starlette
    ```
  </Step>

  <Step title="Export your API keys">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export JWT_VERIFICATION_KEY="your_jwt_verification_key_here"
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:JWT_VERIFICATION_KEY="your_jwt_verification_key_here"
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Snippet file="run-pgvector-step.mdx" />

  <Step title="Run the example">
    Save the code blocks above as `run.py` and `agents.py` in the same directory, then run:

    ```bash theme={null}
    python run.py
    ```
  </Step>
</Steps>

Full source: [cookbook/08\_learning/10\_demo/run.py](https://github.com/agno-agi/agno/blob/main/cookbook/08_learning/10_demo/run.py)