Hay.chat is self-hosted AI customer support software. Its AI agents resolve customer requests instead of just answering them: they look up orders, issue refunds and update orders through Shopify, WooCommerce and Stripe, and hand off to a human when they aren't confident. Run it on your own server with Docker, or use the hosted version at hay.chat.
Best for Shopify and WooCommerce stores that want AI to actually issue refunds and update orders, on a flat monthly plan with no per-seat fees, with a human approval step available on any action.
Website · Documentation
What is Hay.chat?
Hay.chat lets businesses deploy AI agents that handle customer support 24/7 across multiple channels. Agents are grounded in your documentation, follow structured playbooks, and seamlessly escalate to humans when needed.
Key capabilities:
- AI Assistant — One assistant per organization: configure its name, tone, instructions and hand-off behavior. Test before deploying.
- Knowledge Base — Upload PDFs, Word docs, text, markdown, or import from URLs. Agents use vector search to ground answers in your content.
- Playbooks — Step-by-step workflows for specific scenarios (refunds, order lookups, greetings, etc.).
- Multi-channel — Live chat widget, WhatsApp, Instagram DMs, Messenger and email, via plugins.
- Human Handoff — Automatic escalation with full conversation context, plus an approval step for refunds, cancellations and discounts.
- Plugin Ecosystem — Shopify, WooCommerce, Magento, Wix, Nuvemshop, Stripe, HubSpot, Zendesk and more via MCP (Model Context Protocol).
- Analytics — Resolution rate, response time, customer satisfaction, and conversation insights.
- Privacy — GDPR-compliant data handling with DSAR support.
Self-host Hay.chat
Hay.chat runs on one server with Docker Compose: PostgreSQL 16 with pgvector, Redis 7, RabbitMQ and a Caddy proxy with automatic HTTPS. Follow SELF_HOSTING.md for install, email, integrations, upgrades and backups. Getting Started below is for local development.
Chat models: OpenAI, Anthropic, Gemini, or any OpenAI-compatible endpoint (for example DigitalOcean Gradient, or a local server such as Ollama, which is untested). Embeddings use OpenAI text-embedding-3-small, so an OpenAI key is still required. No telemetry is sent unless you set POSTHOG_KEY.
Teams comparing Chatwoot, Zammad or Dify for self-hosted AI support use Hay.chat when they need the agent to take actions, not just reply.
Tech Stack
| Layer | Technology |
|---|
| Frontend | Nuxt 3 (Vue 3), Tailwind CSS, shadcn-vue, Pinia |
| Backend | Express 5, tRPC v11, TypeORM |
| Database | PostgreSQL 16 + pgvector |
| Cache | Redis 7 |
| AI | OpenAI, Anthropic, Gemini or OpenAI-compatible |
| Auth | JWT, API Keys, OAuth 2.0 |
| Plugins | Model Context Protocol (MCP) |
| Webchat | Vue 3 embeddable widget (Vite) |
| Testing | Vitest (frontend), Jest (backend), Playwright (E2E) |
Project Structure
├── dashboard/ # Nuxt 3 frontend
├── server/ # Express + tRPC backend
├── webchat/ # Embeddable chat widget
├── plugins/
│ ├── core/ # Built-in plugins (email, stripe, hubspot, etc.)
│ └── custom/ # User-created plugins
├── packages/
│ ├── plugin-sdk/ # @hay/plugin-sdk
│ └── server-sdk/ # @hay/server-sdk
├── docs/ # Technical and user documentation
├── tests/ # Playwright E2E tests
└── docker-compose.yml # PostgreSQL + Redis
Getting Started
Prerequisites
- Node.js 22.12 or newer
- npm >= 9
- Docker, running (for PostgreSQL, Redis and RabbitMQ)
- An OpenAI API key (embeddings always use OpenAI, even with another chat provider)
Setup
git clone https://github.com/hay-chat/hay-core.git
cd hay-core
# One-time setup (safe to re-run)
OPENAI_API_KEY=sk-... npm run setup
# Start development
npm run dev
npm run setup (scripts/setup-dev.sh):
- Starts PostgreSQL with pgvector, Redis and RabbitMQ with
docker compose up -d (the app itself runs on your machine, so you get hot reload).
- Runs
npm install.
- Creates
.env from .env.example with generated JWT secrets and REQUIRE_EMAIL_VERIFICATION=false (no SMTP locally). It keeps an existing .env and only fills in empty JWT secrets. If you don't pass OPENAI_API_KEY, set it in .env afterwards.
- Builds the plugin SDK (plugins are built on demand against it) and the webchat widget (served by the API).
- Runs database migrations.
- Creates a dev login,
[email protected] / hay-dev-password, that owns the "Hay Dev" organization (npm run dev:account in server/). It only runs with NODE_ENV=development against a local database.
Then open http://localhost:3000 and log in with the dev login, or sign up for a new organization. The API runs on http://localhost:3001 and the RabbitMQ admin UI on http://localhost:15672 (hay / hay_password).
以上为 README 的开头部分。其余内容请阅读原文。 查看完整 README ↗
