Install from PyPI

pip install restai-core
restai init      # Create database + admin user
restai migrate   # Run migrations
restai serve     # → http://localhost:9000/admin (admin / admin)

Use an env file for configuration:

restai serve -e .env -p 8080 -w 4

Available on PyPI — includes the pre-built React frontend, no Node.js required.

Docker

Pull the official prebuilt image (multi-arch — linux/amd64 and linux/arm64):

```bash docker run -p 9000:9000 apocas/restai:latest

Block (Visual Logic Builder)

Build processing logic visually using a Blockly-based IDE — no LLM required. Drag-and-drop blocks to define how input is transformed into output. Use the "Call Project" block to invoke other RESTai projects, enabling composition of AI pipelines without writing code.

Supported blocks: text operations, math, logic, variables, loops, and custom RESTai blocks (Get Input, Set Output, Call Project, Log).

Installation

RESTai uses uv for dependency management. Python 3.11+ required.

Docker

Prebuilt image (recommended — no build, no toolchain):

docker run -d --name restai -p 9000:9000 apocas/restai:latest

Pass an env file to inject configuration (API keys, DB host, etc.) and a volume to persist the SQLite DB / uploads across restarts:

docker run -d --name restai -p 9000:9000 --env-file .env \
  -v restai-data:/app/data \
  apocas/restai:6.2.13

Published on every release to both registries — pick whichever you prefer:

Built for linux/amd64 and linux/arm64 (Apple Silicon / Graviton). Pin a specific version in production (:6.2.13) rather than :latest. The publishing workflow lives in .github/workflows/docker-publish.yml — releases auto-build, or trigger manually with a tag input.

Build locally with compose (for development):

```bash

Quick Start

Live Demo

Try RESTai without installing — ai.restai.cloud

Login: demo / demodemo (restricted account — can browse and chat, but cannot create or modify projects)

---

Settings & Configuration

White-label the UI, configure currency for cost tracking, set agent iteration limits, manage LLM proxy, and more.

---

Edit .env with your configuration, then:

docker compose --env-file .env up --build

Optional profiles for additional services:

Environment Variables

LLM credentials (OpenAI, Anthropic, Gemini, Grok, Azure, etc.) live on each LLM in /admin/llms — encrypted per-LLM in the DB and scoped to teams. Image-generator credentials (DALL-E, Imagen) live in /admin/image-generators. GPU toggle, Redis (chat memory) and the vector backends (ChromaDB / PGVector / Weaviate / Pinecone) are configured in /admin/settings. None of these need env vars; GPU is auto-detected on first boot.

Full configuration in restai/config.py.

---

API

All endpoints are documented via Swagger.

Create a project:

curl -X POST http://localhost:9000/projects \
  -u admin:admin \
  -H 'Content-Type: application/json' \
  -d '{
    "name": "my-rag",
    "type": "rag",
    "llm": "gpt-4o",
    "embeddings": "text-embedding-3-small",
    "vectorstore": "chroma"
  }'

Chat with a project:

curl -X POST http://localhost:9000/projects/1/chat \
  -u admin:admin \
  -H 'Content-Type: application/json' \
  -d '{"message": "What is RESTai?"}'

---

WordPress Plugin

A full-featured WordPress plugin that turns any RESTai instance into the AI engine of a WordPress site. Each capability maps to its own RESTai project, so models, prompts and budgets stay tunable per task — and the plugin auto-provisions the starter projects on first connect, so there's nothing to wire up by hand.

What it does: - Generate post content, excerpts and SEO meta straight from Gutenberg — also wires title/description/focus keyphrase into Yoast and Rank Math fields - One-click featured image generation using whichever generator your team has access to (Flux, SDXL, DALL·E…) - Translate any post to N languages as drafts, with Polylang/WPML compatibility - AI comment moderation — auto-flag spam and toxic comments before they're approved, with optional suggested replies - WooCommerce product descriptions and FAQ generation from product attributes - Knowledge sync — every published post and page is auto-pushed into a Support Bot RAG project so the bot is always current - AI site search — replaces native WP search with semantic answers from the support bot - Embeddable chat widget — one toggle adds the chat bubble to public pages with the right widget key auto-provisioned - AI-personalised transactional emails via the wp_mail filter - Token usage and cost panel mirrored straight into the WP admin

One Make-style install: drop the plugin zip into Plugins → Add New → Upload Plugin, paste your RESTai URL + API key in Settings → RESTai, pick a team, click Auto-provision starter projects — done.