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

# CrewAI-Integration

> Multi-Agenten-KI-Systeme mit Venice AI und CrewAI bauen

[CrewAI](https://www.crewai.com/) ermöglicht den Aufbau autonomer Multi-Agenten-Systeme, in denen spezialisierte KI-Agenten bei komplexen Aufgaben zusammenarbeiten. Venice AI funktioniert dank OpenAI-Kompatibilität als Drop-in-LLM-Provider.

## Einrichtung

```bash theme={"dark"}
pip install crewai crewai-tools
```

## Basis-Konfiguration

Konfiguriere Venice als LLM-Provider in CrewAI über die OpenAI-kompatible Schnittstelle:

```python theme={"dark"}
import os

os.environ["OPENAI_API_KEY"] = "your-venice-api-key"
os.environ["OPENAI_API_BASE"] = "https://api.venice.ai/api/v1"
os.environ["OPENAI_MODEL_NAME"] = "venice-uncensored"
```

Oder pro Agent mit dem LLM-Objekt konfigurieren:

```python theme={"dark"}
from crewai import LLM

venice_llm = LLM(
    model="openai/venice-uncensored",
    api_key="your-venice-api-key",
    base_url="https://api.venice.ai/api/v1",
    temperature=0.7,
)

# Für komplexe Reasoning-Aufgaben
venice_flagship = LLM(
    model="openai/zai-org-glm-5-1",
    api_key="your-venice-api-key",
    base_url="https://api.venice.ai/api/v1",
    temperature=0.3,
)
```

## Deine erste Crew

Erstelle eine einfache Research-Crew mit zwei Agenten:

```python theme={"dark"}
from crewai import Agent, Task, Crew

# Agent 1: Researcher
researcher = Agent(
    role="Senior Research Analyst",
    goal="Find comprehensive, accurate information on the given topic",
    backstory="You are an expert researcher with a keen eye for detail. "
              "You excel at finding and synthesizing information from multiple sources.",
    llm=venice_flagship,
    verbose=True,
)

# Agent 2: Writer
writer = Agent(
    role="Content Strategist",
    goal="Create engaging, well-structured content from research findings",
    backstory="You are a skilled writer who transforms complex research "
              "into clear, compelling content that readers love.",
    llm=venice_llm,
    verbose=True,
)

# Task 1: Research
research_task = Task(
    description="Research the topic: {topic}. "
                "Find key facts, recent developments, and expert opinions. "
                "Provide a structured summary with sources.",
    expected_output="A detailed research summary with key findings, "
                    "organized by subtopic, with at least 5 key points.",
    agent=researcher,
)

# Task 2: Artikel schreiben
write_task = Task(
    description="Using the research provided, write a compelling blog post "
                "about {topic}. Include an introduction, main sections, and conclusion.",
    expected_output="A well-written blog post of 500-800 words with clear sections.",
    agent=writer,
    context=[research_task],  # Nutzt die Ausgabe von research_task
)

# Crew erstellen und ausführen
crew = Crew(
    agents=[researcher, writer],
    tasks=[research_task, write_task],
    verbose=True,
)

result = crew.kickoff(inputs={"topic": "The future of privacy-preserving AI"})
print(result)
```

## Multi-Agenten-Crew für Produktanalyse

Ein komplexeres Beispiel mit spezialisierten Agenten:

```python theme={"dark"}
from crewai import Agent, Task, Crew, Process

# Unterschiedliche Modelle für unterschiedliche Agent-Fähigkeiten
fast_llm = LLM(model="openai/qwen3-5-9b", api_key="your-key", base_url="https://api.venice.ai/api/v1")
smart_llm = LLM(model="openai/zai-org-glm-5-1", api_key="your-key", base_url="https://api.venice.ai/api/v1")
uncensored_llm = LLM(model="openai/venice-uncensored-1-2", api_key="your-key", base_url="https://api.venice.ai/api/v1")

# Market Analyst – braucht Intelligenz
market_analyst = Agent(
    role="Market Research Analyst",
    goal="Analyze market trends and competitive landscape",
    backstory="You are a veteran market analyst with 15 years of experience "
              "in tech markets. You provide unbiased, data-driven insights.",
    llm=smart_llm,
    verbose=True,
)

# Red Team – profitiert von unzensiertem Denken
red_team = Agent(
    role="Red Team Critic",
    goal="Find weaknesses, risks, and potential failures in business strategies",
    backstory="You are a brutally honest critic who stress-tests ideas. "
              "You find every possible flaw and risk, no matter how uncomfortable.",
    llm=uncensored_llm,  # Unzensiert für ehrliche Kritik
    verbose=True,
)

# Stratege – braucht Reasoning
strategist = Agent(
    role="Business Strategist",
    goal="Synthesize analysis into actionable strategy recommendations",
    backstory="You are a McKinsey-trained strategist who creates clear, "
              "actionable plans from complex analyses.",
    llm=smart_llm,
    verbose=True,
)

# Tasks
market_task = Task(
    description="Analyze the market opportunity for: {product_idea}. "
                "Cover market size, competitors, trends, and target audience.",
    expected_output="Structured market analysis with TAM/SAM/SOM estimates, "
                    "top 5 competitors, and 3 key market trends.",
    agent=market_analyst,
)

critique_task = Task(
    description="Critically evaluate this product idea and market analysis. "
                "Find every weakness, risk, and potential failure mode. Be brutally honest.",
    expected_output="A list of at least 5 critical risks, 3 potential failure modes, "
                    "and honest assessment of whether this idea will succeed.",
    agent=red_team,
    context=[market_task],
)

strategy_task = Task(
    description="Based on the market analysis and red team critique, "
                "create a go-to-market strategy that addresses the identified risks.",
    expected_output="A clear go-to-market strategy with: positioning statement, "
                    "3 key differentiators, launch timeline, and risk mitigations.",
    agent=strategist,
    context=[market_task, critique_task],
)

crew = Crew(
    agents=[market_analyst, red_team, strategist],
    tasks=[market_task, critique_task, strategy_task],
    process=Process.sequential,
    verbose=True,
)

result = crew.kickoff(inputs={
    "product_idea": "A privacy-first AI coding assistant that runs on Venice API"
})
print(result)
```

## Tools verwenden

Erweitere Agenten mit Web-Search und weiteren Tools:

<Note>
  `SerperDevTool` benötigt eine Umgebungsvariable `SERPER_API_KEY` von [serper.dev](https://serper.dev). Als Alternative kannst du Venices integrierte Websuche nutzen, indem du `venice_parameters: {"enable_web_search": "auto"}` über `model_kwargs` übergibst — kein zusätzlicher API-Schlüssel erforderlich. Ein Beispiel findest du in der [Web Search Integration](/guides/integrations/langchain#web-search-integration) des LangChain-Guides.
</Note>

```python theme={"dark"}
from crewai_tools import SerperDevTool, WebsiteSearchTool
from crewai import Agent, Task, Crew

# Web-Search-Tool (erfordert die Umgebungsvariable SERPER_API_KEY)
search_tool = SerperDevTool()

researcher = Agent(
    role="Web Researcher",
    goal="Find the latest information on any topic",
    backstory="You are an expert web researcher.",
    llm=venice_flagship,
    tools=[search_tool],
    verbose=True,
)

task = Task(
    description="Research the latest developments in {topic} from the past week.",
    expected_output="A summary of 5 recent developments with dates and sources.",
    agent=researcher,
)

crew = Crew(agents=[researcher], tasks=[task], verbose=True)
result = crew.kickoff(inputs={"topic": "decentralized AI"})
```

## Modellauswahl-Guide für CrewAI

Wähle für jede Agent-Rolle das passende Venice-Modell:

| Agent-Rolle                       | Empfohlenes Modell                                       | Warum                                                                     |
| --------------------------------- | -------------------------------------------------------- | ------------------------------------------------------------------------- |
| Komplexes Reasoning / Strategie   | `zai-org-glm-5-1`                                        | Bestes privates Reasoning-Modell                                          |
| Unzensierte Analyse / Red Team    | `venice-uncensored-1-2`                                  | Keine Inhaltsfilterung                                                    |
| Hohes Volumen / schnelle Aufgaben | `qwen3-5-9b`                                             | Günstigstes Modell mit \$0,10/1M Input-Tokens und \$0,15/1M Output-Tokens |
| Code-Generierungs-Agenten         | `qwen3-coder-480b-a35b-instruct`                         | Für Code optimiert                                                        |
| Vision/Multimodal                 | `qwen3-vl-235b-a22b`                                     | Fortschrittliches Vision-Verständnis                                      |
| Budgetbewusste Teams              | `qwen3-5-9b` (schnell) + `venice-uncensored-1-2` (Haupt) | Kostengünstige Kombination                                                |

## Tipps zur Kostenoptimierung

1. **Günstigere Modelle für einfachere Agenten nutzen**: Nicht jeder Agent braucht ein Flaggschiff-Modell. Verwende `qwen3-4b` zum Formatieren, Zusammenfassen oder einfachen Extrahieren.

2. **`venice-uncensored` für kreative/kritische Rollen nutzen**: Schnell, günstig und verweigert auch unbequeme Analysen nicht.

3. **Flaggschiff-Modelle für Reasoning reservieren**: Nutze `zai-org-glm-5-1` nur für Agenten, die komplexes Reasoning oder zuverlässiges Function Calling brauchen.

4. **Maximale Iterationen begrenzen**: Setze `max_iter` an Agenten, um unkontrollierten Token-Verbrauch zu vermeiden:
   ```python theme={"dark"}
   agent = Agent(role="...", goal="...", backstory="...", llm=venice_llm, max_iter=5)
   ```

## Privacy-Vorteil

Venices Privacy-Garantien machen es ideal für CrewAI-Anwendungsfälle wie:

* **Vertrauliche Geschäftsstrategien** — Zero Data Retention bedeutet, dass deine Wettbewerbsanalysen privat bleiben
* **Verarbeitung sensibler Daten** — Private Modelle loggen oder speichern deine Daten nicht
* **Red-Team-Übungen** — Unzensierte Modelle liefern ehrliches Feedback ohne Inhaltsfilterung

<CardGroup cols={2}>
  <Card title="CrewAI Docs" icon="book" href="https://docs.crewai.com/">
    Offizielle CrewAI-Dokumentation
  </Card>

  <Card title="Venice-Modelle" icon="database" href="/models/overview">
    Alle Venice-Modelle durchsuchen
  </Card>
</CardGroup>