Skip to main content
Interactive wizard that stores your LLM provider API key so every subsequent praisonai command works without extra configuration.

​
Quick Start

1

Run the setup wizard

praisonai setup
The interactive wizard walks you through provider selection and key entry.
2

Choose a provider

🚀 PraisonAI Setup Wizard

1. Choose your LLM provider:
  1) OpenAI (GPT-4o, GPT-4, GPT-3.5)
  2) Anthropic (Claude)
  3) Google (Gemini)
  4) Ollama (Local models)
  5) Custom provider

Select provider [1]:
3

Enter your API key

2. Enter your OpenAI API key:
Enter API key (hidden):
The key is stored securely in ~/.praisonai/.env with permissions 0600.
4

Verify it works

praisonai "Say hello in one sentence"

​
CLI Flags

praisonai setup [OPTIONS] [COMMAND]
OptionDescription
--non-interactiveRun without prompts (requires --provider and --api-key)
--provider TEXTProvider: openai, anthropic, google, ollama, custom
--api-key TEXTAPI key for the provider
--model TEXTDefault model to use

​
Subcommands

CommandDescription
setup wizardExplicitly run the interactive wizard
setup config --showShow current configuration (API keys masked)
setup config --editOpen configuration in $EDITOR
setup resetRemove stored credentials
setup reset --forceRemove without confirmation

​
Non-interactive Mode

For CI/CD or scripted setup: 
praisonai setup --non-interactive \
  --provider openai \
  --api-key "$OPENAI_API_KEY" \
  --model gpt-4o-mini
Supported providers and their required env vars:
Provider--provider valueEnv var written
OpenAIopenaiOPENAI_API_KEY
AnthropicanthropicANTHROPIC_API_KEY
GooglegoogleGEMINI_API_KEY
Ollamaollama(no key needed)
Customcustom(user-defined)

​
Where Credentials Are Stored

praisonai setup writes two files:
FilePurposePermissions
~/.praisonai/.envAPI keys as KEY=value lines0600
~/.praisonai/config.yamlProvider name, default model, telemetry flag0600
The credential store (CredentialStore) reads ~/.praison/credentials.json as an additional fallback path consulted by resolve_llm_endpoint_with_credentials().
All sensitive files are written with chmod 600 and are never included in any telemetry data.

​
When Does Setup Run Automatically?

If you skip setup at install time (or run --no-prompt), the first praisonai or praisonai run command detects the missing credentials and offers to launch this wizard for you. See First-run Onboarding for the full flow.

​
Best Practices

praisonai setup is idempotent — running it again overwrites the previous configuration. Use it whenever you switch providers or need to rotate an API key.
In CI environments set OPENAI_API_KEY (or the provider-specific key) as a secret. On developer workstations use praisonai setup so you don’t have to set env vars in every shell session.
praisonai setup config --show
# Output: OPENAI_API_KEY=***
API keys are masked in the output. Only non-sensitive settings (provider, model) appear in plaintext.

First-run Onboarding

Auto-detects missing credentials at first invocation

Run Command

Run agents from files or prompts

CLI Reference

Complete command tree and flag reference

Installer Internals

How the installer sets up credentials at install time