Troubleshooting

Common issues and how to fix them.

Prerequisites

Node.js is Required

MyLocalCLI requires Node.js 18 or higher.

Check your version:

node --version

Install Node.js:

• Download from nodejs.org (LTS version recommended)
• Or use a version manager:
  • Windows: nvm-windows
  • macOS/Linux: nvm

Windows Issues

PowerShell Execution Policy Error

Error:

mlc : File C:\...\mlc.ps1 cannot be loaded because running scripts is disabled on this system.

Fix: Run PowerShell as Administrator and execute:

Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser

Then try mlc again.

'mlc' is not recognized

Error:

'mlc' is not recognized as an internal or external command

Causes & Fixes:

1. npm not in PATH:

   • Close and reopen your terminal
   • Or run: npm config get prefix and add that path to your system PATH

2. npm bin not linked globally:

   npm config set prefix "C:\Users\YourName\AppData\Roaming\npm"
   

3. Try using npx instead:

   npx mylocalcli
   npx mylocalcli init
   

Permission Denied on Install

Error:

EACCES: permission denied

Fix: Don't use sudo with npm. Instead, fix npm permissions:

# Option 1: Change npm's default directory
mkdir ~/.npm-global
npm config set prefix '~/.npm-global'
# Add to ~/.bashrc or ~/.zshrc:
export PATH=~/.npm-global/bin:$PATH

Connection Issues

"Connection refused" Error

Error:

Error: connect ECONNREFUSED 127.0.0.1:1234

Causes & Fixes:

1. LM Studio server not running:

   • Open LM Studio → Load a model → Start Local Server

2. Ollama not running:

   ollama serve
   

3. Wrong port configured:

   • LM Studio default: 1234
   • Ollama default: 11434
   • Run mlc init to reconfigure

API Key Invalid (OpenRouter/Groq)

Error:

Error: 401 Unauthorized

Fix:

1. Check your API key is correct
2. Run mlc init and re-enter your API key
3. Verify the key works on the provider's website

Model Issues

"Model not found" Error

For LM Studio:

• Make sure a model is loaded in LM Studio before starting the server

For Ollama:

# List available models
ollama list

# Pull a model if needed
ollama pull llama3.2

Slow Responses

Possible causes:

1. Model too large for your hardware:

   • Try a smaller model (7B instead of 70B)
   • Use quantized versions (Q4_K_M)

2. Not using GPU:

   • LM Studio: Check GPU layers setting
   • Ollama: Ensure CUDA/Metal is enabled

3. Context too long:

   • Run /clear to reset conversation
   • Use smaller files in context

Configuration Issues

Config File Corrupted

Fix: Delete and recreate:

# Windows
del %USERPROFILE%\.mylocalcli\config.json

# macOS/Linux
rm ~/.mylocalcli/config.json

# Then reconfigure
mlc init

Skills Not Loading

Check:

1. Ensure src/skills/builtin/ folder exists
2. Restart the CLI after adding custom skills
3. Run /skills to see loaded skills

Getting More Help

• GitHub Issues: Report a bug
• Check README: Full documentation

Quick Fixes Summary