> ## Documentation Index
> Fetch the complete documentation index at: https://docs.neuralcleave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> NeuralCleave is your personal AI assistant — built on the AI stack, not bolted onto it.

## What is NeuralCleave?

NeuralCleave is an open-source personal AI assistant runtime that connects a large language model to **32 messaging platforms**, **13 AI providers**, **local voice**, **self-modifying skills**, and a **privacy mode** that keeps every byte on your machine.

Unlike tools that wrap an API behind a chatbot UI, NeuralCleave runs the model stack in-process — HuggingFace, faster-whisper, Kokoro TTS, OpenWakeWord, and sentence-transformers all execute locally alongside the Python gateway.

## Key Features

<CardGroup cols={2}>
  <Card title="32 Messaging Channels" icon="comments">
    Telegram, Discord, Slack, WhatsApp, Email, SMS, and 26 more. One gateway, all platforms.
  </Card>

  <Card title="13 AI Providers" icon="brain">
    OpenAI, Anthropic, Gemini, DeepSeek, Ollama, Mistral, xAI Grok, Cohere, and more — switchable at runtime.
  </Card>

  <Card title="Local Voice Pipeline" icon="microphone">
    Wake word (OpenWakeWord) → VAD → STT (faster-whisper) → LLM → TTS (ElevenLabs / Kokoro / pyttsx3). 100% local when using Ollama + Kokoro.
  </Card>

  <Card title="Self-Modifying Skills" icon="wand-magic-sparkles">
    Skills are Python files the agent can read, write, and reload at runtime. The assistant extends itself.
  </Card>

  <Card title="Semantic Memory" icon="database">
    Vector-embedded conversation memory with cosine similarity retrieval. In-process, no external vector DB required.
  </Card>

  <Card title="Privacy Mode" icon="shield">
    One flag routes everything — LLM, STT, TTS, embeddings — through local models. Zero external API calls.
  </Card>
</CardGroup>

## How it compares

| Feature | NeuralCleave | OpenClaw |
| - | - | - |
| Messaging channels | 32 | 8 |
| AI providers | 13 | 5 |
| Local voice | Wake word + STT + TTS | ElevenLabs plugin only |
| Privacy mode | Full local stack | Partial |
| Self-modifying skills | Yes | No |
| MCP server | Yes (stdio JSON-RPC 2.0) | No |
| Exec approval | Yes | No |

## Where to start

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Get a live agent in under five minutes.
  </Card>

  <Card title="Configuration" icon="gear" href="/configuration">
    Full `config.toml` reference.
  </Card>

  <Card title="Voice Setup" icon="microphone" href="/voice/overview">
    Enable wake word, STT, and TTS.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    REST API for all gateway operations.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.