# Phidata — AI Agents with Memory, Knowledge & Tools

> Python framework for building AI agents with built-in memory (PostgreSQL), knowledge bases (RAG), and 50+ tool integrations. Production-ready with monitoring dashboard. 18,000+ GitHub stars.

## Install

Save as a script file and run:

## Quick Use

```bash
pip install phidata
```

```python
from phi.agent import Agent
from phi.model.anthropic import Claude
from phi.tools.duckduckgo import DuckDuckGo

agent = Agent(
    model=Claude(id="claude-sonnet-4-20250514"),
    tools=[DuckDuckGo()],
    show_tool_calls=True,
    markdown=True,
)
agent.print_response("What are the top AI coding tools in 2026?")
```

---

## Intro

Phidata is a Python framework for building production AI agents with built-in memory, knowledge bases, and 50+ tool integrations with 18,000+ GitHub stars. Unlike minimal agent frameworks, Phidata includes everything out of the box — PostgreSQL-backed memory for conversation persistence, vector database integration for RAG, pre-built tools for web search, email, SQL, and more, plus a monitoring dashboard. Best for Python developers who want production-ready agents without assembling pieces from multiple libraries. Works with: Claude, GPT-4, Gemini, Ollama, Groq. Setup time: under 2 minutes.

---

## Core Features

### Built-In Memory
Agents remember conversations across sessions:

```python
from phi.agent import Agent
from phi.model.anthropic import Claude
from phi.storage.agent.postgres import PgAgentStorage

agent = Agent(
    model=Claude(id="claude-sonnet-4-20250514"),
    storage=PgAgentStorage(table_name="agent_sessions", db_url="postgresql://..."),
    add_history_to_messages=True,
)
# Agent remembers previous conversations automatically
```

### Knowledge Base (RAG)

```python
from phi.knowledge.pdf import PDFUrlKnowledgeBase
from phi.vectordb.pgvector import PgVector

knowledge = PDFUrlKnowledgeBase(
    urls=["https://example.com/docs.pdf"],
    vector_db=PgVector(table_name="docs", db_url="postgresql://..."),
)

agent = Agent(knowledge=knowledge, search_knowledge=True)
agent.print_response("What does the documentation say about authentication?")
```

### 50+ Pre-Built Tools

| Category | Tools |
|----------|-------|
| Search | DuckDuckGo, Tavily, Exa |
| Data | SQL, CSV, Pandas |
| Communication | Email, Slack |
| Web | Crawl4AI, Newspaper |
| Code | Python, Shell |
| Finance | YFinance, Alpha Vantage |
| Storage | S3, GCS |

```python
from phi.tools.sql import SQLTools
from phi.tools.email import EmailTools

agent = Agent(tools=[
    SQLTools(db_url="postgresql://..."),
    EmailTools(sender="bot@company.com"),
])
```

### Team of Agents

```python
from phi.agent import Agent
from phi.model.anthropic import Claude

researcher = Agent(name="Researcher", tools=[DuckDuckGo()], role="Research topics")
writer = Agent(name="Writer", role="Write articles based on research")

team = Agent(
    team=[researcher, writer],
    instructions=["Researcher finds data", "Writer creates the article"],
)
team.print_response("Write an article about AI agent trends")
```

### Monitoring Dashboard
Built-in UI at [app.phidata.com](https://app.phidata.com):
- Agent session history
- Tool call traces
- Token usage and costs
- Error tracking

### Key Stats
- 18,000+ GitHub stars
- PostgreSQL-backed memory
- RAG with pgvector
- 50+ pre-built tools
- Monitoring dashboard

### FAQ

**Q: What is Phidata?**
A: A Python framework for building production AI agents with built-in memory (PostgreSQL), knowledge bases (RAG), 50+ tools, and monitoring.

**Q: Is Phidata free?**
A: Open-source under Apache 2.0. Monitoring dashboard has a free tier.

**Q: How is Phidata different from LangChain?**
A: Phidata is batteries-included — memory, RAG, tools, and monitoring are built in. LangChain requires assembling these from separate packages.

---

## Source & Thanks

> Created by [Phidata](https://github.com/phidatahq). Licensed under Apache 2.0.
>
> [phidata](https://github.com/phidatahq/phidata) — stars 18,000+

Thanks for making production agents batteries-included.

---

<!-- ZH -->

## 快速使用

```bash
pip install phidata
```

```python
from phi.agent import Agent
from phi.model.anthropic import Claude
from phi.tools.duckduckgo import DuckDuckGo

agent = Agent(model=Claude(id="claude-sonnet-4-20250514"), tools=[DuckDuckGo()])
agent.print_response("2026 年最火的 AI 编码工具有哪些?")
```

---

## 简介

Phidata 是一个 Python Agent 框架，GitHub 18,000+ stars。内置 PostgreSQL 记忆、RAG 知识库、50+ 工具集成和监控面板。适合需要生产级 Agent 的 Python 开发者。

---

## 来源与感谢

> Created by [Phidata](https://github.com/phidatahq). Licensed under Apache 2.0.
>
> [phidata](https://github.com/phidatahq/phidata) — stars 18,000+

---
Source: https://tokrepo.com/en/workflows/67988bf9-9e52-4878-ad19-16dc90b43bea
Author: Agent Toolkit