AIAny
AI Infra2021
Icon for item

Logto

Provides authentication and authorization infrastructure for SaaS and AI apps via OIDC/OAuth 2.1, offering multi-tenancy, SSO, RBAC, pre-built sign-in flows, and SDKs for 30+ frameworks.

Introduction

Modern SaaS products and agent-based AI systems need a standards-first identity layer that supports multi-tenancy, federated SSO, and programmatic integrations. This project delivers an OAuth/OIDC/SAML-compliant auth stack with production-grade features (multi-tenant isolation, RBAC, MFA, pre-built flows) and client SDKs to integrate web, mobile, APIs, and Model Context Protocol agents.

What Sets It Apart
  • Standards-first with broad protocol support (OIDC, OAuth 2.1, SAML) — so you can integrate with identity providers and industry tooling without custom protocol workarounds.
  • Built-in multi-tenancy and organization RBAC — so teams running SaaS or marketplace products get tenant isolation and role management out of the box.
  • Developer ergonomics: SDKs for 30+ frameworks and pre-built sign-in flows — so integration effort is focused on product UX instead of auth plumbing.
  • OSS plus hosted option — so you can self-host for control/compliance or use the managed cloud offering to avoid operational overhead.
Who It's For and Trade-offs

Great fit if you’re building multi-tenant SaaS, agent-enabled platforms, or AI services that need a standards-compliant identity layer and fast integrations across web/mobile/APIs. It reduces engineering time spent on auth and provides primitives (SSO, RBAC, MFA) needed in production.

Look elsewhere if you require a proprietary enterprise IdP with very specific vendor certifications or highly specialized legacy integrations; if you prefer a fully managed vendor with a single SLA and no self-hosting option, the hosted service may be preferable to running OSS yourself.

Information

  • Websitegithub.com
  • OrganizationsLogto
  • Published date2021/06/19

More Items

GitHub
AI Infra2022

Provides runtime support for reversible effects and reactive coeffects so components can be declared, composed, and hot-replaced safely; includes effect tracking, coeffect resolution, a declarative component loader and HMR — aimed at plugin-driven agent harnesses and dynamic systems.

GitHub

Provides a unified integration layer that lets AI agents call and manage third‑party service APIs while keeping credentials and approval workflows out of the agent's reach. Offers plugin-based integrations, per-tenant envelope encryption (KEK), configurable permission modes, and an optional Hub to host OAuth/webhook surfaces.

Frames LLM routing as a sequential decision process and introduces LLMRouter plus the xRouteBench benchmark to develop, evaluate, and deploy learned routing policies across heterogeneous LLMs, optimizing response quality versus inference cost.