Skip to content

Home

Jump to bottom
mrveiss edited this page Jul 22, 2026 · 2 revisions

AutoBot Wiki

Your data. Your AI. — Self-hosted AI automation platform: chat-driven fleet management, knowledge bases, voice, browser automation, and infrastructure automation. You choose where inference runs; your data stays on your infrastructure.

Quick Navigation

Page Description
Getting Started & Installation Docker quickstart, native install, system requirements
Architecture & System Design Component overview, data flows, tech stack
Feature Guides Chat, voice, browser automation, knowledge bases, fleet, workflows, approvals, modules
API Documentation REST endpoints, auth, request/response examples
Configuration Reference All environment variables and config options
Deployment Guide Production deployments, SSL, scaling, monitoring
Development Guide Dev setup, testing, contributing, git workflow
Troubleshooting Guide Common issues and fixes

What is AutoBot?

AutoBot is a self-hosted infrastructure automation platform that combines conversational AI with distributed automation. Deploy it on your own hardware, choose whether inference runs locally or through a provider you plug in, and keep your data on your infrastructure.

Key Capabilities

  • Natural Language Control — Issue commands in plain English; AutoBot handles the complexity
  • Chat Interface — Multi-turn conversations with function calling and streaming responses
  • Voice Conversations — Talk to AutoBot through a voice overlay or side-panel
  • Browser Automation — Vision-in-the-loop browsing: the agent sees the page and drives the next action
  • Visual Workflow Builder — Compose automations on a node-graph canvas
  • Human-in-the-Loop Approvals — Runs can pause on approval interrupts and resume once you confirm
  • Multi-User & RBAC — Full user management with role-based access control (single-user mode is retired)
  • Knowledge Bases & Knowledge Graph — RAG retrieval over your documents plus a structured knowledge graph
  • Fleet Management — Ansible-powered multi-server orchestration and monitoring
  • LLM Gateway — Route inference to local models (Ollama) or external providers (claude_api, openrouter) with fallback
  • Modules — AutoBot LLC (work-item coordination), Codebase Analytics (WIP), and Transcriber
  • Vision Processing — Analyze screenshots and diagrams
  • Your data, your choice — Run fully local or plug in a provider; your data stays on your infrastructure and no provider is contacted unless you configure one

Quick Start (3 Steps)

# 1. Clone
git clone https://github.com/mrveiss/AutoBot-AI.git
cd AutoBot-AI

# 2. Configure & Start
cp .env.example .env
docker compose up -d

# 3. Open
# Visit http://localhost in your browser

See Getting Started & Installation for full details.

System Requirements

Component Minimum Recommended
CPU 4 cores 8+ cores
RAM 8 GB 16+ GB
Storage 20 GB SSD 50+ GB SSD
GPU None (CPU-only) NVIDIA for faster inference
OS Ubuntu 20.04+ / Debian 11+ Ubuntu 22.04 LTS
Docker 24.0+ 25.0+

Getting Help

Clone this wiki locally