OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI APIs & Platforms

Restai

Restai is an open-source Python platform for creating AI projects and serving them through a REST API. It combines a web dashboard and chat playground with integrations for language models, retrieval-augmented generation, agents, inference, visual logic, and image and audio generation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Restai — OpenViST project profile in AI APIs & Platforms.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Restai when you need a platform to configure multiple AI projects and make them available to applications through a REST API, especially when RAG, model choice, project analytics or visual workflow composition matter.

Who it is for

  • Developers building applications that need AI capabilities behind REST endpoints.
  • Teams assembling RAG projects from documents and vector stores.
  • Operators who want to run the platform locally or in a container and connect hosted or self-hosted models.

Documented uses

  • Create and manage AI projects with individual model, prompt, tool and configuration settings.
  • Expose AI project functionality through REST endpoints for use in other applications.
  • Upload documents and build retrieval-based question-answering projects.
  • Monitor project token usage, costs, latency and activity in the dashboard.
  • Compose processing logic visually and call other Restai projects from a pipeline.
Before you choose

Requirements & limits

The repository documents installation from PyPI and Docker, as well as a hosted demo. The demo account can browse and chat but cannot create or modify projects. Local installation requires Python 3.11 or later.

  • Restai is an infrastructure platform that you run or access as a service, not just a chat interface.
  • Model connections span hosted providers and local-serving options; your intended provider affects configuration.
  • RAG supports multiple vector stores, including ChromaDB, PGVector, Weaviate and Pinecone.
  • The documented default database is SQLite; PostgreSQL and MySQL are also supported.
  • Local setup includes database initialization and migrations before starting the server.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and start Restai from PyPI

Set up the Restai service and open its local admin interface.

Before you start

  • Python 3.11 or later
  • The restai-core package from PyPI

Steps

  1. Install the package with pip install restai-core.

  2. Run restai init to create the database and admin user.

  3. Run restai migrate to apply database migrations.

  4. Run restai serve and open the local admin interface at http://localhost:9000/admin.

Expected outcome

A local Restai service with its admin interface available on port 9000.

Guide limitations

  • This recipe covers service setup only; it does not configure an AI project or connect a model.
  • The README lists admin/admin as the default credentials and says the default password can be configured.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
apocas/restai · Official homepage title · retained in its source language
How we review sourcesSuggest a correction