ManyLLM v1.0.0

Local-first AI platform

Documentation

Introduction

v1.0.0

Welcome to ManyLLM documentation. Learn how to run, manage, and integrate multiple local LLMs in one unified workspace.

Quick Start

Get up and running with ManyLLM in under 5 minutes.

1

Install & Launch

Download and run ManyLLM on your system.

2

Add Models

Configure your first local model via the UI.

3

Start Chatting

Use the chat interface or API endpoints.

bash

# 1. Start ManyLLM
./ManyLLM

# 2. Configure your first model (via UI or CLI)
manyllm model add llama3 --provider ollama

# 3. Test the API
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-local-key" \
  -d '{
    "model": "llama3",
    "messages": [{"role": "user", "content": "Hello!"}],
    "temperature": 0.7
  }'

Download ManyLLM Try Web Preview

Key Features

OpenAI-Compatible API

Drop-in replacement for OpenAI API with local models. Use your existing tools and scripts.

View API Reference

Workspaces & Context

Organize conversations with file context and local RAG capabilities for enhanced productivity.

Learn About Workspaces

Model Management

Automatic detection and management of Ollama, llama.cpp, and MLX runtimes.

Model Configuration

Privacy First

Local-first architecture ensures your data never leaves your device by default.

Next Steps

Continue your ManyLLM journey with these guides.

For Developers

• API Integration Guide
• Custom Model Configuration
• Workspace Automation

For Teams

• Shared Workspace Setup
• Model Performance Optimization
• Privacy & Security Best Practices

Documentation In Progress

Comprehensive documentation is being written alongside the desktop application. Check back soon for detailed guides, API references, and tutorials.