Skip to main content
A new class of research is emerging where giving models tools for structured thinking, like a scratchpad, greatly improves their reasoning capabilities. For example, by giving a model reasoning tools, we can greatly improve its reasoning capabilities by providing a dedicated space for working through the problem. This is a simple, yet effective approach to add reasoning to non-reasoning models. First published by Anthropic in this blog post, this technique has been practiced by many AI Engineers (including our own team) long before it was published.

​
Reasoning Tools

The first version of the Reasoning Tools, previously known as Thinking tools, was published by Anthropic in this blog post.
claude_reasoning_tools.py
from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.reasoning import ReasoningTools
from agno.tools.duckduckgo import DuckDuckGoTools

# Setup our Agent with the reasoning tools
reasoning_agent = Agent(
    model=Claude(id="claude-3-7-sonnet-latest"),
    tools=[
        ReasoningTools(add_instructions=True),
        DuckDuckGoTools(),
    ],
    instructions="Use tables where possible",
    markdown=True,
)

# Run the Agent
reasoning_agent.print_response(
    "What are the fastest cars in the market? Only the report, no other text.",
    stream=True,
    show_full_reasoning=True,
    stream_intermediate_steps=True,
)
See the Reasoning Tools documentation for more details.

​
Knowledge Tools

The Knowledge Tools take the Reasoning Tools one step further by allowing the Agent to search a knowledge base and analyze the results of their actions. KnowledgeTools = think + search + analyze
knowledge_tools.py
import os
from agno.agent import Agent
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIChat
from agno.tools.knowledge import KnowledgeTools
from agno.vectordb.lancedb import LanceDb, SearchType


agno_docs = Knowledge(
    vector_db=LanceDb(
        uri="tmp/lancedb",
        table_name="agno_docs",
        search_type=SearchType.hybrid,
        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
    ),
)


knowledge_tools = KnowledgeTools(
    knowledge=agno_docs,
    think=True,
    search=True,
    analyze=True,
    add_few_shot=True,
)


agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[knowledge_tools],
    markdown=True,
)


agno_docs.add_content(
    url="https://docs.agno.com/llms-full.txt"
)


agent.print_response("How do I build multi-agent teams with Agno?", stream=True)
See the Knowledge Tools documentation for more details.

​
Memory Tools

The Memory Tools allow the Agent to use memories to reason about the question and work through it step by step.
memory_tools.py
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.tools.memory import MemoryTools

# Create a database connection
db = SqliteDb(
    db_file="tmp/memory.db"
)

memory_tools = MemoryTools(
    db=db,
)

agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[memory_tools],
    markdown=True,
)

agent.print_response(
    "My name is John Doe and I like to hike in the mountains on weekends. "
    "I like to travel to new places and experience different cultures. "
    "I am planning to travel to Africa in December. ",
    user_id="john_doe@example.com",
    stream=True
)

# This won't use the session history, but instead will use the memory tools to get the memories
agent.print_response("What have you remembered about me?", stream=True, user_id="john_doe@example.com")
See the Memory Tools documentation for more details.

​
Workflow Tools

The Workflow Tools allow the Agent to execute a workflow and reason about the results.
workflow_tools.py
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.workflow import WorkflowTools

# Create your workflow
# ...

workflow_tools = WorkflowTools(
    workflow=blog_post_workflow,
)

agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[workflow_tools],
    markdown=True,
)

agent.print_response("Create a blog post on the topic: AI trends in 2024", stream=True)
See the Workflow Tools documentation for more details.

​
Developer Resources

⌘I