mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-05-22 19:47:15 +00:00
675afa8dee
Split the legacy core speech stack into two built-in, independently toggleable plugins: `_kokoro_tts` for TTS and `_whisper_stt` for STT. This refactor keeps dependency installation and bootstrap concerns in Docker/bootstrap/preload, while moving speech-specific tooling, APIs, prompts, UI, and runtime behavior into the plugins. Core now exposes engine-agnostic `tts-service` and `stt-service` brokers, with browser-native TTS preserved as the fallback when Kokoro is disabled. Included in this change: - add built-in `_kokoro_tts` plugin with plugin-owned synth API, config, status UI, and provider registration - add built-in `_whisper_stt` plugin with plugin-owned transcribe API, mic runtime, device UI, prompt injection, and provider registration - remove legacy core speech APIs/helpers/settings/UI and delete unused `webui/js/speech_browser.js` - replace the old hardcoded speech settings section with a generic voice surface backed by plugin extensions - update preload/docs/tests to match the new plugin-owned speech architecture Behavioral intent: - both plugins are built-in but not `always_enabled` - users can now hot-switch TTS and STT independently - browser TTS remains available when `_kokoro_tts` is off - Whisper mic UI only appears when `_whisper_stt` is enabled |
||
|---|---|---|
| .. | ||
| agents | ||
| developer | ||
| guides | ||
| res | ||
| setup | ||
| quickstart.md | ||
| README.md | ||
Agent Zero Documentation
Welcome to the Agent Zero documentation hub. Start with the practical guides below: install it, open the Web UI, connect your host machine when needed, and learn the main workflows by sight.
For architecture and source-linked internals, use DeepWiki for Agent Zero. The local docs focus on practical setup, screenshots, and user workflows.
Quick Start
- Quickstart Guide: Get up and running in 5 minutes with Agent Zero.
- First-Run Onboarding: Choose Cloud or Local, add a provider key, and select main and utility models.
- Installation Guide: Install scripts, updates, and advanced Docker setup (includes How to Update).
- A0 CLI Connector: Install the host connector for a running Agent Zero instance, use the command palette, and switch Browser modes.
- Self Update: How the in-app updater works (technical reference).
- VPS Deployment: Deploy Agent Zero on a remote server.
- Development Setup: Set up a local development environment.
User Guides
- Usage Guide: Practical tour of Agent Zero's main workflows.
- First-Run Onboarding: Set up OpenRouter, our proxy API or another provider with the guided wizard.
- Browser Guide: Use the built-in Browser, live Canvas surface, annotations, screenshots, host browser mode, and extensions.
- Desktop Guide: Use the built-in Linux desktop, GUI apps, and LibreOffice Writer/Calc/Impress Cowork.
- A0 CLI Connector: Terminal-first host connector for Agent Zero, with screenshots of the host picker, connected shell, command palette, and Browser modes.
- Create a Small Plugin: Build and review a tiny Web UI plugin that adds an unread dot to the chat list.
- Skills Guide: Open the Skills selector, add active skills, and remove prompt extras you no longer need.
- Agent Profiles: Switch the current chat profile or create a new guided profile from the chat input.
- Model Presets: Create simple named shortcuts for model setups.
- Memory Guide: Search, edit, delete, and curate memories so useful context does not become stale noise.
- Projects Tutorial: Learn to create isolated workspaces with dedicated context and memory.
- API Integration: Add external APIs without writing code.
- MCP Setup: Configure Model Context Protocol servers.
- A2A Setup: Enable agent-to-agent communication.
- Troubleshooting: Solutions to common issues and FAQs.
Technical Reference
- DeepWiki for Agent Zero: Architecture, Web UI internals, plugin lifecycle, backend APIs, deployment details, and source-linked explanations.
- Architecture: Short local handoff to DeepWiki plus practical starting points.
- Plugins: Compact plugin starting points and sharing checklist.
- Extensions: Short guide for when an extension is the right tool.
- Connectivity: Choose between A0 CLI, MCP, A2A, and external APIs.
- WebSockets: Short local handoff to DeepWiki and source files.
- MCP Configuration: Compact reference for MCP JSON.
- Notifications: Notification system architecture and setup.
- Contributing Skills: Create and share agent skills.
- Contributing Guide: Contribute to the Agent Zero project.
Community & Support
- Join the Community: Connect with other users on Discord to discuss ideas, ask questions, and collaborate.
- Share Your Work: Show off your Agent Zero creations and workflows in the Show and Tell area.
- Report Issues: Use the GitHub issue tracker to report bugs or suggest features.
- Follow Updates: Subscribe to the YouTube channel for tutorials and release videos.
Table of Contents
-
- Quickstart Guide
- First-Run Onboarding
- Installation Guide
- Self Update (technical)
- VPS Deployment
- Development Setup
- A0 CLI Connector
-
- Usage Guide
- Browser Guide
- Desktop Guide
- A0 CLI Connector
- Create a Small Plugin
- Skills Guide
- Agent Profiles
- Model Presets
- Memory Guide
- Projects Tutorial
- API Integration
- MCP Setup
- A2A Setup
- Troubleshooting
Documentation Ownership
| Content type | Home |
|---|---|
| Setup, screenshots, and everyday workflows | These docs |
| Architecture and source-linked internals | DeepWiki |
| Exact behavior | The current source code |
| Community help and examples | Discord, Skool, GitHub discussions |
Your journey with Agent Zero starts now!
Ready to dive in? Start with the Quickstart Guide for the fastest path to your first chat, or follow the Installation Guide for a detailed setup walkthrough.