Phidata

Phidata (now Agno) is a framework for building AI agents with built-in memory, knowledge bases, and tool use that maintain context across conversations. It provides a batteries-included approach to building intelligent assistants.

Key use cases include:

• Building persistent AI assistants that remember previous interactions
• Agents with knowledge bases — connecting to PDFs, databases, and websites for RAG
• Multi-tool agents — web search, code execution, file I/O, and database queries
• Building teams of agents that collaborate on complex tasks
• Creating production-ready AI APIs with built-in serving infrastructure

Phidata is used by developers who want a higher-level abstraction for building AI agents — less boilerplate than LangChain, with more built-in capabilities like structured output, memory storage, and team coordination.

The framework supports all major LLM providers and includes pre-built tool integrations for common tasks.

1. Install Phidata:

   pip install phidata

2. Set your LLM provider key:

   export OPENAI_API_KEY='sk-...'

3. Build an agent with tools:

   from phi.agent import Agent
   from phi.model.openai import OpenAIChat
   from phi.tools.duckduckgo import DuckDuckGo
   
   agent = Agent(
       model=OpenAIChat(id='gpt-4o'),
       tools=[DuckDuckGo()],
       show_tool_calls=True
   )
   agent.print_response('What are the latest AI trends?')

4. Read the docs at docs.phidata.com for memory, knowledge bases, and team patterns.

Pricing: Phidata is free and open source. You pay only for the LLM API calls and any infrastructure you use (databases for memory, vector stores for knowledge).