@samitouri / QOSami_Agents_Zero-2
Code Commits Issues Pulls Sessions CI/CD
main
main
md 71 lines 2.97 KB
Rendered Raw
1 # First-Run Onboarding
2
3 Use onboarding the first time you open Agent Zero, or any time the Web UI says
4 your models still need setup. The wizard helps you pick Cloud, AI account, or
5 Local access, configure a main model, choose a utility model, and start
6 chatting.
7
8 This example uses **OpenRouter** with a masked demo key. Replace the demo key
9 with your own key.
10
11 ## Open Onboarding
12
13 Open the Web UI. The welcome screen can show account shortcuts, and the message
14 composer is ready immediately.
15
16 ![Welcome screen with account and channel setup cards](../res/usage/onboarding/onboarding-start.png)
17
18 If you send a message before models are configured, Agent Zero creates the chat,
19 holds the message, and shows the model gate inside the conversation. Choose
20 **Cloud provider**, **AI account**, or **Local model** to open onboarding.
21
22 ![Chat model gate with Cloud provider, AI account, and Local model choices](../res/usage/onboarding/onboarding-model-gate.png)
23
24 ## Choose A Provider Path
25
26 Choose **Cloud** when you want to paste an API key for OpenRouter, OpenAI,
27 Anthropic, Google, Venice, or another hosted provider.
28
29 ![Cloud provider picker with hosted providers](../res/usage/onboarding/onboarding-cloud-provider.png)
30
31 Choose **Account** when you want to sign in with Codex/ChatGPT, GitHub Copilot,
32 Google Cloud Gemini, or xAI Grok instead of pasting a provider key.
33
34 ![AI account picker with Codex, Copilot, Google Cloud Gemini, and Grok](../res/usage/onboarding/onboarding-account-provider.png)
35
36 Choose **Local** when you want to connect to Ollama, LM Studio, oMLX, llama.cpp,
37 vLLM, or another model server running on your machine.
38
39 ![Local model provider picker with Ollama, LM Studio, oMLX, llama.cpp, and vLLM](../res/usage/onboarding/onboarding-local-ollama-main.png)
40
41 ## Configure The Main Model
42
43 For API-key providers, choose the main model and paste the provider key. The
44 screenshot uses a masked demo key.
45
46 ![OpenRouter setup with main model and masked API key](../res/usage/onboarding/onboarding-agent-zero-api-key-model.png)
47
48 After the main model is selected, click **Choose utility model**.
49
50 ## Choose The Utility Model
51
52 The utility model handles quick internal tasks such as summaries, naming, and
53 memory. A small, fast, cheap model usually works best here. The wizard may
54 prefill a utility provider and model, but it remains an explicit choice.
55
56 ![Utility model step with OpenRouter and a fast Gemini model](../res/usage/onboarding/onboarding-utility-same-model.png)
57
58 Click **Finish setup** when the utility model looks right.
59
60 ## Start Chatting
61
62 The ready screen confirms that model setup is done. Optional setup cards may
63 appear for integrations such as Telegram, Email, WhatsApp, or plugins.
64
65 ![Onboarding ready screen after setup](../res/usage/onboarding/onboarding-ready.png)
66
67 Click **Start Chatting** to create a chat and begin using Agent Zero.
68
69 > [!IMPORTANT]
70 > Do not reuse the fake key shown in this guide. Paste your own provider key,
71 > and do not share screenshots that reveal real keys or private account details.