apocas/restai

RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generation with dynamic loading generators. Live chat deployment. Built-in block based graphical language. Prompt versioning and much more...

What it solves

RESTai is an AI-as-a-Service (AIaaS) platform that allows users to create, manage, and deploy AI projects—such as RAG systems, agents, and inference endpoints—and consume them via a simple REST API. It eliminates the need to build custom infrastructure for every AI application by providing a centralized dashboard for configuration, analytics, and deployment.

How it works

The platform provides a React-based dashboard where users can configure projects with specific LLMs, system prompts, and tools. It supports a wide range of LLM providers (OpenAI, Anthropic, Ollama, Gemini, etc.) and offers specialized modules for different AI tasks:

  • RAG & Knowledge Graphs: Ingests documents from various sources (S3, URLs, Google Drive) and uses vector stores and entity extraction for retrieval.
  • Agents: Implements zero-shot ReAct agents with support for the Model Context Protocol (MCP) and a headless Chromium browser for web automation.
  • Visual Logic: A Blockly-based IDE allows users to build processing pipelines without writing code.
  • Inference: Provides direct multimodal chat and completion endpoints, including OpenAI-compatible APIs.
  • Management: Includes built-in RBAC, team multi-tenancy, prompt versioning, and an evaluation framework powered by DeepEval.

Who it’s for

It is designed for developers and teams who want to deploy AI capabilities quickly without managing the underlying plumbing, as well as organizations needing a multi-tenant AI platform with enterprise features like audit logs, 2FA, and white-labeling.

Highlights

  • Comprehensive AI Toolset: Combines RAG, agents, visual logic, and multimodal inference in one platform.
  • Agentic Browser: Headless Chromium integration with encrypted secrets vault and domain allowlists for safe web automation.
  • Knowledge Graph RAG: Entity-aware retrieval and a visual graph explorer to improve recall on specific names and organizations.
  • Enterprise-Ready: Features RBAC, TOTP 2FA, white-label branding, and Kubernetes-native deployment.
  • MCP Support: Built-in MCP server to expose projects as tools for clients like Claude Desktop or Cursor.
  • Analytics & Eval: Detailed token tracking, cost/latency monitoring, and a built-in evaluation framework for prompt quality.

Related

  • Project
    jeremychone/rust-genai

    genai is a Rust crate offering a single, ergonomic async API to access dozens of LLM providers (OpenAI, Anthropic, Gemini, Ollama, Bedrock, etc.) using each provider's native protocol when possible. It supports chat, streaming, vision, function calling, custom endpoints, and prompt‑cache controls, with extensive examples and migration docs.

  • Project
    open-webui/open-webui

    A self-hosted, extensible AI platform that provides a unified interface for local and cloud-based models, featuring built-in RAG, agent creation, and enterprise-grade user management.

  • Project
    vstorm-co/full-stack-ai-agent-template

    A production-ready project generator that scaffolds full-stack AI agent applications using FastAPI and Next.js, featuring built-in RAG, authentication, and enterprise integrations.

  • Project
    CopilotKit/OpenTag

    An open-source, self-hosted knowledge-work agent for Slack and Microsoft Teams that integrates tools and generative UI to perform tasks directly in chat threads.