> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Migration Guide v1.0

> Migrate to the new Agent* prefix naming convention

## Overview

PraisonAI v1.0 introduces a consistent **Agent\*** prefix naming convention for core orchestration classes. This makes the API more intuitive and agent-centric.

> [!NOTE]
>
> **Backward Compatible**: All old names continue to work as silent aliases. No code changes are required for existing projects.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
flowchart LR
    subgraph Old["Old Names"]
        AM[AgentManager]
        WF[Workflow]
        APP[AgentAppProtocol]
    end
    subgraph New["New Names (v1.0+)"]
        AT[AgentTeam]
        AF[AgentFlow]
        AOS[AgentOSProtocol]
    end
    AM --> AT
    WF --> AF
    APP --> AOS
    style Old fill:#8B0000,color:#fff
    style New fill:#189AB4,color:#fff
```

## What Changed

> [card] AgentTeam
>
> Manages a team of agents working together on tasks.
>
> **Old**: `AgentManager`, `Agents`

> [card] AgentFlow
>
> Defines step-by-step workflows with routing and patterns.
>
> **Old**: `Workflow`, `Pipeline`

> [card] AgentOSProtocol
>
> Protocol for production deployment of agents.
>
> **Old**: `AgentAppProtocol`

> [card] AgentOSConfig
>
> Configuration for AgentOS deployments.
>
> **Old**: `AgentAppConfig`

## Quick Reference

| Old Name | New Name | Purpose |
| - | - | - |
| `AgentManager` | **`AgentTeam`** | Multi-agent orchestration |
| `Agents` | **`AgentTeam`** | Multi-agent orchestration |
| `Workflow` | **`AgentFlow`** | Step-based workflows |
| `Pipeline` | **`AgentFlow`** | Step-based workflows |
| `AgentAppProtocol` | **`AgentOSProtocol`** | Deployment protocol |
| `AgentAppConfig` | **`AgentOSConfig`** | Deployment config |

## Migration Examples

> [tab] Python
>
> ```python AgentTeam (Before) theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> from praisonaiagents import Agent, Agents
>
> agent1 = Agent(name="researcher", instructions="Research topics")
> agent2 = Agent(name="writer", instructions="Write content")
>
> team = Agents(agents=[agent1, agent2])
> result = team.start()
> ```
>
> ```python AgentTeam (After - Recommended) theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> from praisonaiagents import Agent, AgentTeam
>
> agent1 = Agent(name="researcher", instructions="Research topics")
> agent2 = Agent(name="writer", instructions="Write content")
>
> team = AgentTeam(agents=[agent1, agent2])
> result = team.start()
> ```

> [tab] TypeScript
>
> ```typescript AgentTeam (Before) theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> import { Agent, Agents } from 'praisonai';
>
> const researcher = new Agent({ instructions: "Research topics" });
> const writer = new Agent({ instructions: "Write content" });
>
> const team = new Agents([researcher, writer]);
> await team.start();
> ```
>
> ```typescript AgentTeam (After - Recommended) theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> import { Agent, AgentTeam } from 'praisonai';
>
> const researcher = new Agent({ instructions: "Research topics" });
> const writer = new Agent({ instructions: "Write content" });
>
> const team = new AgentTeam([researcher, writer]);
> await team.start();
> ```

> [tab] AgentFlow
>
> ```python Python (Before) theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> from praisonaiagents import Workflow
>
> flow = Workflow(steps=[...])
> result = flow.start()
> ```
>
> ```python Python (After - Recommended) theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> from praisonaiagents import AgentFlow
>
> flow = AgentFlow(steps=[...])
> result = flow.start()
> ```
>
> ```typescript TypeScript (Before) theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> import { Workflow } from 'praisonai';
>
> const flow = new Workflow('my-workflow');
> await flow.run(input);
> ```
>
> ```typescript TypeScript (After - Recommended) theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
> import { AgentFlow } from 'praisonai';
>
> const flow = new AgentFlow('my-workflow');
> await flow.run(input);
> ```

## No Breaking Changes

> [!TIP]
>
> All old names work exactly as before. They are **silent aliases** with no deprecation warnings.

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Both work identically
from praisonaiagents import AgentManager  # ✓ Still works (silent alias)
from praisonaiagents import AgentTeam     # ✓ New recommended name

# They are the same class
assert AgentManager is AgentTeam  # True
```

## Why the Change?

> [accordion] Consistency
>
> All orchestration classes now follow the `Agent*` prefix pattern, making the API more predictable.

> [accordion] Clarity
>
> * **AgentTeam** clearly indicates a team of agents
> * **AgentFlow** clearly indicates a flow/workflow of agent steps
> * **AgentOS** clearly indicates an operating system for agents

> [accordion] Agent-Centric
>
> The naming reinforces that PraisonAI is an agent-first framework where everything revolves around agents.

## Recommended Actions

**1. No Immediate Action Required**

Your existing code will continue to work without any changes.

**2. Update New Code**

Use the new names (`AgentTeam`, `AgentFlow`, `AgentOSProtocol`) in new projects.

**3. Gradual Migration**

When updating existing code, switch to the new names for consistency.

## Class Hierarchy

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
flowchart TB
    subgraph Core["Core Classes"]
        A[Agent]
        AT[AgentTeam]
        AF[AgentFlow]
    end
    
    subgraph Aliases["Silent Aliases"]
        AM[AgentManager → AgentTeam]
        AG[Agents → AgentTeam]
        WF[Workflow → AgentFlow]
        PL[Pipeline → AgentFlow]
    end
    
    A --> AT
    A --> AF
    
    style Core fill:#189AB4,color:#fff
    style Aliases fill:#8B0000,color:#fff
```

## Need Help?

> [card] [Documentation](https://praison.ai/docs/concepts/agents.md)
>
> Learn more about agents and orchestration

> [card] [Examples](https://praison.ai/docs/examples)
>
> See working examples with the new names


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.