Couchbase

Agno

**Agno is a full-stack framework for building Multi-Agent Systems.**

What is Agno?

Learn how to build AI agents with Agno - from basic agents to advanced teams with tools, reasoning, knowledge, storage, and memory capabilities.

Your first Agents

**Agno provides a beautiful Agent UI for interacting with your agents and teams.**

Agno Playground

Track and monitor your Agno agents in real-time.

Agent Monitoring

Register and visualise your components in real-time on Agno Platform.

Agent Registry

Join the Agno community to connect with builders, get support, and explore AI development opportunities.

Community & Support

Install & Setup

Learn how to contribute to Agno through our fork and pull request workflow.

Contributing to Agno

Migrate from Phidata to Agno

Explore Agno's example gallery showcasing everything from single-agent tasks to sophisticated multi-agent workflows.

Examples

Examples Gallery

Overview

Standardized Codebases for Agentic Systems

Introduction

Development Application

Production Application

Add Python Libraries

Add Secrets

Environment variables

Database Tables

CI/CD

Custom Domain & HTTPS

Use Custom Domain and HTTPS

SSH Access

Workspace Settings

Create Git Repo

Add New Users

Setup workspace for new users

Format & Validate

Environment Variables Setup

Setting Environment Variables

TPM rate limiting

Tokens-per-minute rate limiting

Command line authentication

Connecting to Tableplus

Docker Connection Error

Could Not Connect To Docker

OpenAI Key Request While Using Other Models

Structured outputs

When to use a Workflow vs a Team in Agno

Memory V2

Product updates

User Guide

Workspaces

FAQs

API reference

Changelog

Discord

Community

Learn what Agno Agents are and how they work.

What are Agents?

Learn how to run an agent and get the response.

Agent.run()

Understanding agent run and session metrics in Agno

Metrics

Sessions

Agent State

Memory

Learn how to use tools in Agno to build AI agents.

Tools

Structured Output

Multimodal Agents

Learn how to control the flow of an agent's execution in Agno. This is also called "Human in the Loop".

User Control Flows

Prompts

Knowledge

Session Storage

Agent Context

Agent Teams [Deprecated]

Build autonomous multi-agent systems with Agno Agent Teams.

What are Agent Teams?

Learn how to run a team and get the response.

Team.run()

Learn about the shared state of Agent Teams.

Team State

Playground App

FastAPI App

Whatsapp App

Language Models are machine-learning programs that are trained to understand natural language and code.

What are Models?

Models Compatibility

Learn how to use OpenAI-like models in Agno.

OpenAI Like

AI/ML API

Learn how to use Anthropic Claude models in Agno.

Anthropic Claude

Cohere

Learn how to use DeepInfra models in Agno.

DeepInfra

Learn how to use DeepSeek models in Agno.

DeepSeek

Learn how to use Fireworks models in Agno.

Fireworks

Gemini

Groq

Learn how to use HuggingFace models in Agno.

HuggingFace

Learn how to use IBM WatsonX models in Agno.

IBM WatsonX

LM Studio

Mistral

Nvidia

Ollama

OpenAI

Learn how to use OpenAI Responses with Agno.

OpenAI Responses

OpenRouter

Perplexity

Sambanova

Together

Learn how to use Vercel v0 models with Agno.

Vercel v0

Tools are functions that helps Agno Agents to interact with the external world.

What are Tools?

Learn how to write your own tools and how to use the `@tool` decorator to modify the behavior of a tool.

Writing your own tools

Exceptions

Learn how to use tool hooks to modify the behavior of a tool.

Hooks

Human in the loop

Writing your own Toolkit

Selecting tools

Async Tools

Tool Result Caching

Reasoning gives Agents the ability to "think" before responding and "analyze" the results of their actions (i.e. tool calls), greatly improving the Agents' ability to solve problems that require sequential tool calls.

What is Reasoning?

Reasoning Models

Reasoning Tools

Reasoning Agents

Memory gives an Agent the ability to recall relevant information.

What is Memory?

User Memories

Memory Storage

Knowledge is domain-specific information that the Agent can search at runtime to make better decisions (dynamic few-shot learning) and provide accurate responses (agentic RAG).

What is Knowledge?

Agentic Search

Understanding Hybrid Search and its benefits in combining keyword and vector search for better results.

Hybrid Search- Combining Keyword and Vector Search

Learn how to implement a custom retriever for precise control over document retrieval in your knowledge base.

Custom Retriever

Implementing a Custom Retriever

Learn how to use ArXiv articles in your knowledge base.

ArXiv

ArXiv Knowledge Base

Learn how to combine multiple knowledge bases into one.

Combined

Combined Knowledge Base

Learn how to use local CSV files in your knowledge base.

CSV Knowledge Base

Learn how to use remote CSV files in your knowledge base.

CSV URLs

CSV URL Knowledge Base

Learn how to use local docx files in your knowledge base.

Docx

Docx Knowledge Base

Learn how to use local documents in your knowledge base.

Document

Document Knowledge Base

Learn how to use local JSON files in your knowledge base.

JSON

JSON Knowledge Base

Learn how to use a LangChain retriever or vector store as a knowledge base.

LangChain

LangChain Knowledge Base

Learn how to use a LlamaIndex retriever or vector store as a knowledge base.

LlamaIndex

LlamaIndex Knowledge Base

Learn how to use Markdown files in your knowledge base.

Markdown

Markdown Knowledge Base

Learn how to use local PDF files in your knowledge base.

PDF Knowledge Base

Learn how to use remote PDFs in your knowledge base.

PDF URLs

PDF URL Knowledge Base

Learn how to use PDFs from an S3 bucket in your knowledge base.

S3 PDF

S3 PDF Knowledge Base

Learn how to use text files from an S3 bucket in your knowledge base.

S3 Text

S3 Text Knowledge Base

Learn how to use text files in your knowledge base.

Text

Text Knowledge Base

Learn how to use websites in your knowledge base.

Website

Website Knowledge Base

Learn how to use Wikipedia topics in your knowledge base.

Parameter	Type	Description	Default
`bucket_name`	`str`	Name of the Couchbase bucket	Required
`scope_name`	`str`	Name of the scope within the bucket	Required
`collection_name`	`str`	Name of the collection within the scope	Required
`couchbase_connection_string`	`str`	Couchbase cluster connection string	Required
`cluster_options`	`ClusterOptions`	Options for configuring the Couchbase cluster connection	Required
`search_index`	`Union[str, SearchIndex]`	Search index configuration, either as index name or SearchIndex definition	Required
`embedder`	`Embedder`	Embedder instance for generating embeddings	`OpenAIEmbedder()`
`overwrite`	`bool`	Whether to overwrite existing collection	`False`
`is_global_level_index`	`bool`	Whether the search index is at global level	`False`
`wait_until_index_ready`	`Optional[float]`	Time in seconds to wait until the index is ready	`None`
`batch_limit`	`int`	Maximum number of documents to process in a single batch (applies to both sync and async operations)	`500`

Reference