Back to Agno

Build an Agent That Can Act, Remember, and Improve

cookbook/00_quickstart/README.md

2.8.27.7 KB
Original Source

Build an Agent That Can Act, Remember, and Improve

Start with one useful Gemini-powered agent. Add typed outputs, sessions, memory, state, knowledge, learning, safety, teams, and workflows. Then launch the whole system in AgentOS.

One API key. No Docker. Every example runs independently.

This is a capability ladder, not a collection of unrelated demos. Each file upgrades the same market-research partner and ends with something you can inspect: a tool call, typed object, stored session, recalled memory, state change, knowledge result, learning, blocked request, approval, team response, or workflow output.

Start Here

From the repository root:

bash
uv venv .venvs/quickstart --python 3.12
source .venvs/quickstart/bin/activate
uv pip install -r cookbook/00_quickstart/requirements.txt
export GOOGLE_API_KEY=your-google-api-key
python cookbook/00_quickstart/agent_with_tools.py

The first example is the complete minimum:

python
from agno.agent import Agent
from agno.models.google import Gemini
from agno.tools.yfinance import YFinanceTools

agent = Agent(
    model=Gemini(id="gemini-3.6-flash"),
    tools=[YFinanceTools()],
)

agent.print_response("What's AAPL's current price?", stream=True)

Gemini 3.6 Flash is the stable default for this quickstart. It supports the tool calling, structured output, and multi-step agent work used throughout the folder. See the official model page.

The Capability Ladder

Follow the files in order for the full journey, or jump directly to the capability you need. Every example is standalone.

1. Core — Make the Agent Useful

#CookbookWhat You AddProof
01agent_with_tools.pyLive toolsThe agent chooses and calls Yahoo Finance tools
02agent_with_structured_output.pyTyped outputThe run returns a validated Pydantic object
03agent_with_typed_input_output.pyInput and output contractsBoth sides of the agent boundary are validated

2. Context — Make It Durable

#CookbookWhat You AddProof
04agent_with_storage.pyConversation storageA fixed session continues across runs
05agent_with_memory.pyUser memoryPreferences survive across sessions
06agent_with_state_management.pyStructured stateThe agent updates and restores a watchlist
07agent_search_over_knowledge.pySearchable knowledgeThe answer is grounded in a versioned local Agno overview
08agent_with_learning.pyShared learned knowledgeOne user teaches a rule another user can reuse

3. Trust — Keep the Human in Control

#CookbookWhat You AddProof
09agent_with_guardrails.pyBuilt-in and custom guardrailsPII, injection, and spam inputs end with RunStatus.error
10human_in_the_loop.pyApproval gatesThe run pauses before a simulated publish action

4. Scale — Move Beyond One Agent

#CookbookWhat You AddProof
11multi_agent_team.pyDynamic collaborationBull and bear researchers are coordinated by a leader
12sequential_workflow.pyExplicit orchestrationGather, analyze, and write steps run in order

5. Ship — Run the Complete System

run.py registers every agent, the team, and the workflow in one AgentOS runtime. config.yaml adds ready-to-run prompts for the AgentOS chat interface.

The Mental Model

These concepts sound similar until you ask what each one owns:

ConceptWhat It OwnsUse It For
ToolsActions the model can chooseAPIs, search, code, database operations
Structured outputThe response contractPipelines, APIs, UIs, reliable parsing
StorageThe conversation recordContinue the same thread later
MemoryDurable facts about a userPreferences and personalization
StateMutable structured dataLists, counters, carts, task progress
KnowledgeInformation the agent can searchDocs, policies, product data, RAG
LearningReusable lessons from prior workShared heuristics and better future behavior
GuardrailsInput and output boundariesPrivacy, policy, and validation
Human in the loopApproval for a pending actionPublishing, writes, payments, deployments
TeamDynamic delegation between agentsMultiple perspectives or specialists
WorkflowExplicit execution orderRepeatable multi-step processes

Start with one agent. Add a team only when independent specialists improve the answer. Add a workflow when the order of operations must be predictable.

Run the Complete System in AgentOS

Load the local Agno overview used by the knowledge agent once:

bash
python cookbook/00_quickstart/agent_search_over_knowledge.py

Start AgentOS:

bash
python cookbook/00_quickstart/run.py

Open os.agno.com, add http://localhost:7777 as an endpoint, and choose any quickstart agent, team, or workflow. You can chat, inspect sessions, view traces, and explore memory and knowledge from the same interface.

https://github.com/user-attachments/assets/aae0086b-86f6-4939-a0ce-e1ec9b87ba1f

Why Market Research?

The scenario makes agent behavior visible: facts change, tools matter, comparisons benefit from structure, and opposing researchers have a real reason to collaborate. Yahoo Finance also works without a second API key.

The examples teach agent architecture, not investment advice. Replace the tools and instructions with your own domain while keeping the same patterns.

Swap Models

Each file declares its own model so it stays copy-pasteable:

python
from agno.models.google import Gemini

model = Gemini(id="gemini-3.6-flash")

Replace that model in the example you are using. The memory example also has a dedicated memory model, while the knowledge and learning examples use GeminiEmbedder; those components can be configured independently.

Browse cookbook/90_models/ for other providers and provider-specific capabilities.

Local State

Persistent examples write only to tmp/quickstart/, with a separate SQLite database or Chroma collection per capability. This keeps examples independent and prevents one run from contaminating another. Delete that directory when you want a completely fresh start.

Verify the Folder

Check the cookbook structure and compile every file:

bash
python3 cookbook/scripts/check_cookbook_pattern.py \
  --base-dir cookbook/00_quickstart
python -m compileall -q cookbook/00_quickstart

Use TEST_PROMPT.md for the live behavioral test plan and TEST_LOG.md for the latest verified results.

Go Deeper

  • Agents — tools, multimodal input, reasoning, hooks, and advanced patterns
  • Teams — delegation, collaboration, and team coordination
  • Workflows — conditions, loops, routers, and parallel steps
  • AgentOS — production runtime, interfaces, and deployment
  • Knowledge — readers, chunking, embedders, and vector databases
  • Learning — profiles, entity memory, learned knowledge, and decision logs
  • Agno documentation