SkillAgentSearch skills...

chatty

Open-source, self-hostable Zendesk and Intercom alternative for AI customer support: chat widget, shared inbox, real-time voice, Multimodal RAG, and MCP.

Install / Use

claude mcp add PersonaliAI -- npx -y github:PersonaliAI/chatty

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

75/100

Supported Platforms

Claude Code
Claude Desktop

Our assessment of chatty

chatty scores 75/100 on our quality scale, 307th of 333 Customer Support skills we index.

Its MCP Server is 55 KB long, well organised into 50 sections with 14 code examples: long enough that it reads more like full documentation than a focused instruction file, which agents can find harder to follow.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
21/30
Structure
20/20
Description
15/15
Adoption
4/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated today, so chatty is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 97/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

chatty compared with similar skills

All 4 of these similar skills score higher than chatty; compare them before choosing.

SkillScoreStarsUpdatedFormat
chatty (this skill)by PersonaliAI7510todayMCP Server
Agent-Reachby Panniantong100107.2k6d agoCLAUDE.md
headroomby headroomlabs-ai10078.5k1d agoCLAUDE.md
CowAgentby zhayujie10047.7ktodayCLAUDE.md
Scraplingby D4Vinci10090.9ktodayMCP Server

Frequently asked questions

How do I install chatty?
Run claude mcp add PersonaliAI -- npx -y github:PersonaliAI/chatty. The install tabs above show the steps for each supported agent.
Which AI agents does chatty work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is chatty safe to use?
It is MIT-licensed and scores 97/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is chatty still maintained?
The repository was last updated today, so chatty is actively maintained.
<div align="center">

<img src="https://raw.githubusercontent.com/PersonaliAI/chatty/main/backend/assets/chatty-icon.png" alt="Chatty" width="88" /> <img src="https://raw.githubusercontent.com/PersonaliAI/chatty/main/backend/assets/readme-icon.png" alt="Chatty" width="88" />

Chatty by PersonaliAI

<p> <a href="README.md">English</a> · <a href="README.zh-CN.md">简体中文</a> · <a href="README.ja.md">日本語</a> · <a href="README.es.md">Español</a> </p>

Open-source AI agent trained on your store and content.<br />Answers customer questions, captures leads, and books meetings on website, WhatsApp & Slack.

<p align="center"> <a href="https://chatty.personaliai.com"><b>🚀 Live Demo</b></a> &nbsp;·&nbsp; <a href="https://chatty.personaliai.com/signup"><b>☁️ Chatty Cloud (Free 14-day trial)</b></a> &nbsp;·&nbsp; <a href="#-quick-start-docker-compose"><b>⚡ Quickstart (5 min)</b></a> &nbsp;·&nbsp; <a href="https://docs.chatty.personaliai.com"><b>📖 Documentation</b></a> </p> <p align="center"> <a href="https://render.com/deploy?repo=https://github.com/PersonaliAI/chatty"><img src="https://render.com/images/deploy-to-render-button.svg" alt="Deploy to Render" /></a> &nbsp; <a href="https://railway.com/template/chatty-open-source-ai-customer-support-a"><img src="https://railway.com/button.svg" alt="Deploy on Railway" /></a> </p>

Chatty is an open-source, self-hostable Zendesk and Intercom alternative for stores and modern businesses that need autonomous AI customer support with human takeover, WooCommerce sync, and calendar scheduling.

Run the application containers on your own host while keeping Supabase Auth, Postgres, Storage, and Realtime managed. The same deployment contract works on a VPS, Railway, Render, or another Docker host without touching the live Supabase project.

License: MIT CI GDPR Compliant Next.js FastAPI Supabase MCP Docker PRs Welcome

Chatty Cloud (hosted) · Documentation · Data Processing (DPA) · Sub-processors · Performance Scorecard · Flow Builder · Widget Embed · Secure customer identity · Quick Start · Platform Runbook · MCP Server · AI Plugins · Omnichannel · WooCommerce

<br /> <br /> <p align="center"> <a href="screenshots/real-01-overview.png"><img src="screenshots/real-01-overview.png" alt="Chatty Executive Overview & Live Telemetry" width="100%" style="border-radius: 8px;" /></a> </p> </div>

Table of contents

Why Chatty

Every hosted chatbot SaaS charges per-seat or per-message and holds your conversation data. Chatty is open-core: run it yourself for free, or use Chatty Cloud - our own hosted version of this exact repo, if you'd rather skip the ops work. Either way you get the same feature set - streaming chat, RAG over your own documents, meeting booking, lead capture, WhatsApp/Slack channels, and a full MCP server so an AI agent can run the whole dashboard for you.

| Capability | Closed-source SaaS chatbots | Chatty | |---|---|---| | Data Ownership | Stored on third-party servers, vendor locked | Cloud: Hosted on Chatty Cloud with zero AI training guarantee<br>Self-Host: 100% in your own private Supabase instance | | Pricing | High per-seat fees & message overages | Self-host for $0 forever (MIT), or predictable flat-rate hosted cloud tiers | | LLM Choice | Locked to vendor models | Bring your own (BYOK): Gemini, OpenAI, Claude, OpenRouter, or local models | | Agent / MCP Access | None, or expensive enterprise add-on | Official 81-tool FastMCP server included (OAuth 2.0 PKCE & API Keys) | | Source Code & License | Proprietary closed source | MIT Licensed — 100% open-source, forkable, auditable, run anywhere |

🖥️ Live Dashboard Showcase (4K Retina)

All 22 core modules are captured from live production (chatty.personaliai.com/dashboard) in crisp 4K Retina (3840×2160) resolution, representing real hydrated application state:

<table width="100%"> <tr> <td width="50%" align="center"> <a href="screenshots/real-06-inbox.png"><img src="screenshots/real-06-inbox.png" alt="Omnichannel Live Helpdesk & SLA Inbox" width="100%" /></a> <br /> <b>Omnichannel Live Helpdesk & SLA Inbox</b> <br /> <sub>Real-time visitor threads, SLA breach warnings & 1-click human takeover</sub> </td> <td width="50%" align="center"> <a href="screenshots/real-04-knowledge-base.png"><img src="screenshots/real-04-knowledge-base.png" alt="Knowledge Base & Vector Documents" width="100%" /></a> <br /> <b>Knowledge Base & Vector Documents</b> <br /> <sub>Multi-format ingestion, recursive crawler & 186k+ tokens indexed</sub> </td> </tr> <tr> <td width="50%" align="center"> <a href="screenshots/real-18-voice-agent.png"><img src="screenshots/real-18-voice-agent.png" alt="LiveKit WebRTC Voice Studio" width="100%" /></a> <br /> <b>LiveKit WebRTC Voice Studio</b> <br /> <sub>Sub-500ms bidirectional audio, dynamic visualizers & multi-platform SDKs</sub> </td> <td width="50%" align="center"> <a href="screenshots/real-08-flow-builder.png"><img src="screenshots/real-08-flow-builder.png" alt="Visual Conversation Flow Architect" width="100%" /></a> <br /> <b>Visual Conversation Flow Architect</b> <br /> <sub>Interactive decision tree graph with AI Flow Copilot & cycle validation</sub> </td> </tr> <tr> <td width="50%" align="center"> <a href="screenshots/real-03-customizer.png"><img src="screenshots/real-03-customizer.png" alt="Live Widget Customizer & Style Studio" width="100%" /></a> <br /> <b>Live Widget Customizer & Style Studio</b> <br /> <sub>WYSIWYG live preview with automated WCAG AA/AAA contrast engine</sub> </td> <td width="50%" align="center"> <a href="screenshots/real-16-analytics.png"><img src="screenshots/real-16-analytics.png" alt="Resolution Rates & Deflection Telemetry" width="100%" /></a> <br /> <b>Resolution Rates & Deflection Telemetry</b> <br /> <sub>Conversation volume, 100% deflection rate, and token usage heatmaps</sub> </td> </tr> </table> <details> <summary><b>📸 Click to explore all 22 High-Resolution Production Dashboard Views</b></summary> <br />

| # | Module | Description | High-Res Capture | | :---: | :--- | :--- | :---: | | 01 | Executive Overview | 5-pillar health score, deflection rate & live 30-day KPIs | View 4K Image | | 02 | Chatbot Workspace | Multi-bot management, model switching (GPT-4o, Claude, Gemini) | View 4K Image | | 03 | Widget Customizer | 6-part styling palette, brand logo, WCAG contrast pass/fail | View 4K Image | | 04 | Knowledge Base | 52+ sources, 186k chars indexed, HNSW vector search | View 4K Image | | 05 | AI Playground | Sandboxed simulator with citation inspect drawer | View 4K Image | | 06 | Omnichannel Inbox | Unified helpdesk, live visitor presence, SLA breach timers | View 4K Image | | 07 | Campaigns | Proactive announcement modals, exit-intent & scroll triggers | View 4K Image | | 08 | Flow Builder | Drag-and-drop conversation canvas with AI Flow Copilot | View 4K Image | | 09 | Visitor Leads CRM | Automated lead extraction, GeoIP country/city telemetry, CSV export | View 4K Image | | 10 | Feedback & CSAT | Post-chat customer ratings, sentiment analysis & friction tags | View 4K Image | | 11 | Visitor Map | Interactive Leaflet geolocation map showing regional traffic | View 4K Image | | 12 | Meeting Scheduler | 2-way Google Calendar OAuth sync & automated Meet links | View 4K Image | | 13 | Inbound Mailbox | Resend email routing converting incoming emails to tick

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars10
CategoryCustomer
Updated5h ago
Forks3

Languages

TypeScript

Trust signals

97/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 info
chatty — MCP Server: Install & Safety Check | SkillAgent