Documentation Index
Fetch the complete documentation index at: https://nikcli.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Configuration Commands
NikCLI provides comprehensive configuration management for AI models, environment variables, system settings, and application preferences. These commands help you customize and optimize your development environment.
Core Configuration Commands
/config
Display current system configuration and settings.
Syntax:
/config [section] [options]
Parameters:
section - Specific configuration section to display
Options:
--detailed - Show detailed configuration
--json - Output in JSON format
--export - Export configuration to file
Examples:
# Show all configuration
/config
# Show specific section
/config models
# Detailed configuration view
/config --detailed
# Export configuration
/config --export config-backup.json
Configuration Sections:
models - AI model settings
environment - Environment variables
security - Security settings
performance - Performance tuning
integrations - External integrations
ui - User interface preferences
/model [name]
Switch AI model or show current model configuration.
Syntax:
/model [model-name] [options]
Parameters:
model-name - Name of AI model to switch to
Options:
--provider <provider> - Specify AI provider
--temperature <value> - Set model temperature
--max-tokens <count> - Set maximum tokens
--show-available - Show available models
Available Models:
claude-3-5-sonnet - Anthropic Claude 3.5 Sonnet
claude-3-opus - Anthropic Claude 3 Opus
gpt-4 - OpenAI GPT-4
gpt-4-turbo - OpenAI GPT-4 Turbo
gpt-3.5-turbo - OpenAI GPT-3.5 Turbo
gemini-pro - Google Gemini Pro
mistral-large - Mistral Large
ollama/* - Local Ollama models
Examples:
# Show current model
/model
# Switch to Claude 3.5 Sonnet
/model claude-3-5-sonnet
# Switch with custom temperature
/model gpt-4 --temperature 0.7
# Switch with token limit
/model claude-3-opus --max-tokens 4000
# Show available models
/model --show-available
/models
List all available AI models with details and capabilities.
Syntax:
Options:
--provider <provider> - Filter by provider
--capability <capability> - Filter by capability
--detailed - Show detailed model information
--benchmark - Show performance benchmarks
Examples:
# List all models
/models
# List OpenAI models only
/models --provider openai
# List models with code capability
/models --capability code
# Detailed model information
/models --detailed
# Show performance benchmarks
/models --benchmark
Model Information Display:
🤖 Available AI Models:
┌─────────────────────┬─────────────┬─────────────┬─────────────┬─────────────┐
│ Model │ Provider │ Context │ Capabilities│ Cost/1K │
├─────────────────────┼─────────────┼─────────────┼─────────────┼─────────────┤
│ claude-3-5-sonnet │ Anthropic │ 200K │ Code, Text │ $3.00 │
│ claude-3-opus │ Anthropic │ 200K │ Reasoning │ $15.00 │
│ gpt-4-turbo │ OpenAI │ 128K │ Code, Vision│ $10.00 │
│ gpt-4 │ OpenAI │ 8K │ General │ $30.00 │
│ gemini-pro │ Google │ 32K │ Multimodal │ $0.50 │
└─────────────────────┴─────────────┴─────────────┴─────────────┴─────────────┘
/set-key [provider]
Set API keys for AI providers interactively.
Syntax:
/set-key [provider] [options]
Parameters:
provider - AI provider name
Supported Providers:
anthropic - Anthropic Claude models
openai - OpenAI GPT models
google - Google Gemini models
mistral - Mistral AI models
openrouter - OpenRouter proxy
ollama - Local Ollama instance
perplexity - Perplexity AI
coinbase - Coinbase AgentKit
browserbase - Browser automation
Examples:
# Set Anthropic API key
/set-key anthropic
# Set OpenAI API key
/set-key openai
# Set all keys interactively
/set-key
# Set key with validation
/set-key anthropic --validate
Interactive Key Setup:
🔑 API Key Configuration
Provider: Anthropic
Current Status: ❌ Not configured
Please enter your Anthropic API key:
Key: sk-ant-api03-... (hidden)
✅ API key validated successfully
✅ Model access confirmed
✅ Configuration saved
Available models: claude-3-5-sonnet, claude-3-opus, claude-3-haiku
/router [action]
Configure model routing and load balancing.
Syntax:
/router <action> [options]
Available Actions:
status - Show routing configuration
set - Set model for specific use case
balance - Configure load balancing
fallback - Set fallback models
reset - Reset routing configuration
Examples:
# Show routing status
/router status
# Set model for code tasks
/router set code claude-3-5-sonnet
# Set model for reasoning tasks
/router set reasoning claude-3-opus
# Configure load balancing
/router balance --models "gpt-4,claude-3-5-sonnet" --weights "50,50"
# Set fallback model
/router fallback gpt-3.5-turbo
# Reset to defaults
/router reset
Routing Configuration:
🔀 Model Routing Configuration:
Use Case Routing:
├── Code Generation: claude-3-5-sonnet
├── Text Analysis: claude-3-opus
├── Quick Tasks: gpt-3.5-turbo
└── Reasoning: claude-3-opus
Load Balancing:
├── Primary: gpt-4 (60%)
├── Secondary: claude-3-5-sonnet (40%)
└── Fallback: gpt-3.5-turbo
Health Status:
✅ All models operational
⚠️ Rate limits: OpenAI (80% used)
Environment Management
/env [var] [value]
Manage environment variables and configuration.
Syntax:
/env [variable] [value] [options]
Parameters:
variable - Environment variable name
value - Variable value to set
Options:
--list - List all environment variables
--unset <var> - Unset variable
--export - Export to .env file
--load <file> - Load from file
Examples:
# List all environment variables
/env --list
# Show specific variable
/env NODE_ENV
# Set environment variable
/env NODE_ENV production
# Set multiple variables
/env DATABASE_URL "postgresql://..." API_KEY "abc123"
# Unset variable
/env --unset TEMP_VAR
# Export to .env file
/env --export .env.backup
# Load from file
/env --load .env.production
Environment Variable Categories:
System Variables:
NODE_ENV - Node.js environment
PATH - System path
HOME - Home directory
USER - Current user
AI Provider Keys:
ANTHROPIC_API_KEY - Anthropic Claude
OPENAI_API_KEY - OpenAI GPT
GOOGLE_API_KEY - Google Gemini
MISTRAL_API_KEY - Mistral AI
Application Settings:
NIKCLI_LOG_LEVEL - Logging level
NIKCLI_CACHE_DIR - Cache directory
NIKCLI_CONFIG_DIR - Configuration directory
/temp [value]
Set AI model temperature for response creativity.
Syntax:
/temp [temperature] [options]
Parameters:
temperature - Temperature value (0.0-2.0)
Options:
--model <model> - Set for specific model
--reset - Reset to default
--show - Show current temperature
Temperature Guidelines:
0.0-0.3 - Deterministic, factual responses
0.4-0.7 - Balanced creativity and accuracy
0.8-1.2 - Creative, varied responses
1.3-2.0 - Highly creative, experimental
Examples:
# Show current temperature
/temp
# Set conservative temperature
/temp 0.2
# Set balanced temperature
/temp 0.7
# Set creative temperature
/temp 1.0
# Set for specific model
/temp 0.5 --model claude-3-5-sonnet
# Reset to default
/temp --reset
System Configuration
/system [action]
Manage system-level configuration and settings.
Syntax:
/system <action> [options]
Available Actions:
info - Show system information
limits - Configure resource limits
cache - Cache management
logs - Logging configuration
performance - Performance settings
Examples:
# Show system information
/system info
# Configure memory limits
/system limits --memory 4GB --tokens 100000
# Clear system cache
/system cache clear
# Set logging level
/system logs --level debug
# Performance optimization
/system performance --mode balanced
System Information Display:
💻 System Information:
Environment:
├── OS: macOS 14.2.1 (arm64)
├── Node.js: v18.19.0
├── Memory: 16GB (4.2GB used)
└── Disk: 512GB SSD (234GB free)
NikCLI:
├── Version: 1.6.0
├── Config: ~/.nikcli/config.json
├── Cache: ~/.nikcli/cache (1.2GB)
└── Logs: ~/.nikcli/logs
Performance:
├── CPU Usage: 12%
├── Memory Usage: 26%
├── Cache Hit Rate: 89%
└── Response Time: 1.2s avg
/stats
Show detailed system and usage statistics.
Syntax:
/stats [category] [options]
Parameters:
category - Statistics category
Categories:
usage - Usage statistics
performance - Performance metrics
models - Model usage stats
tokens - Token consumption
sessions - Session statistics
Examples:
# Show all statistics
/stats
# Show usage statistics
/stats usage
# Show performance metrics
/stats performance
# Show model usage
/stats models
# Export statistics
/stats --export stats-report.json
/dashboard [action]
Control the system dashboard display.
Syntax:
/dashboard [action] [options]
Available Actions:
start - Start dashboard
stop - Stop dashboard
expand - Expand dashboard view
collapse - Collapse dashboard view
refresh - Refresh dashboard data
Options:
--interval <seconds> - Refresh interval
--compact - Compact view
--metrics <list> - Specific metrics to show
Examples:
# Start dashboard
/dashboard start
# Start with auto-refresh
/dashboard start --interval 5
# Compact dashboard
/dashboard start --compact
# Show specific metrics
/dashboard start --metrics "cpu,memory,tokens"
# Stop dashboard
/dashboard stop
Advanced Configuration
Configuration Profiles
Manage Configuration Profiles:
# Create configuration profile
/config profile create development
# Switch to profile
/config profile switch production
# List profiles
/config profile list
# Export profile
/config profile export development dev-config.json
# Import profile
/config profile import production-config.json
Predefined Profiles:
Development Profile:
- Relaxed security settings
- Debug logging enabled
- Higher token limits
- Development model preferences
Production Profile:
- Strict security settings
- Error logging only
- Conservative token limits
- Stable model preferences
Testing Profile:
- Isolated environment
- Verbose logging
- Test-specific settings
- Mock integrations
Model Configuration
Advanced Model Settings:
# Configure model parameters
/model config claude-3-5-sonnet --temperature 0.7 --max-tokens 4000 --top-p 0.9
# Set model aliases
/model alias fast gpt-3.5-turbo
/model alias smart claude-3-opus
# Configure model routing rules
/model route "code generation" claude-3-5-sonnet
/model route "data analysis" claude-3-opus
# Model performance tuning
/model tune --optimize-for speed
/model tune --optimize-for quality
Integration Configuration
Configure External Integrations:
# GitHub integration
/config github --token ghp_xxx --org myorg
# Docker integration
/config docker --host unix:///var/run/docker.sock
# Database integration
/config database --url postgresql://localhost/mydb
# Cloud provider integration
/config aws --profile default --region us-east-1
Configuration Files
Configuration File Locations
System Configuration:
~/.nikcli/config.json - Main configuration
~/.nikcli/profiles/ - Configuration profiles
~/.nikcli/cache/ - Cache directory
~/.nikcli/logs/ - Log files
Project Configuration:
.nikcli/config.json - Project-specific config
.nikcli/profiles/ - Project profiles
.env - Environment variables
.nikcli-ignore - Ignore patterns
Configuration Schema
Main Configuration Structure:
{
"models": {
"default": "claude-3-5-sonnet",
"routing": {
"code": "claude-3-5-sonnet",
"reasoning": "claude-3-opus"
},
"parameters": {
"temperature": 0.7,
"max_tokens": 4000
}
},
"security": {
"approval_required": true,
"safe_mode": false,
"dev_mode": false
},
"performance": {
"cache_enabled": true,
"max_memory": "4GB",
"token_limit": 100000
},
"integrations": {
"github": {
"enabled": true,
"token": "ghp_xxx"
}
}
}
Troubleshooting Configuration
Common Configuration Issues
API Key Problems:
# Validate API keys
/set-key --validate-all
# Test model access
/model test claude-3-5-sonnet
# Check key permissions
/config check-permissions
Model Access Issues:
# Check model availability
/models --check-access
# Test model connection
/model test --all
# Reset model configuration
/model reset
Configuration Corruption:
# Validate configuration
/config validate
# Repair configuration
/config repair
# Reset to defaults
/config reset --confirm
# Restore from backup
/config restore config-backup.json
Debug Commands
# Configuration diagnostics
/diagnostic config
# Debug model issues
/debug models
# Check system health
/system health
# Validate environment
/env validate
Best Practices
Configuration Management
- Regular configuration backups
- Use profiles for different environments
- Document configuration changes
- Validate configuration regularly
- Keep sensitive data secure
Model Selection
- Choose appropriate models for tasks
- Monitor token usage and costs
- Use routing for optimization
- Set appropriate temperature values
- Configure fallback models
Environment Variables
- Use .env files for projects
- Keep secrets secure
- Document required variables
- Use consistent naming conventions
- Regular cleanup of unused variables
- Monitor resource usage
- Configure appropriate limits
- Use caching effectively
- Optimize model routing
- Regular performance reviews
Security
- Protect API keys
- Use secure configuration storage
- Regular security audits
- Appropriate access controls
- Monitor configuration changes