novuhq/novu

The open-source communication infrastructure for agents and products

What it solves

Novu provides a unified communication infrastructure that eliminates the need for developers to build separate integrations for every messaging channel. It solves the problem of fragmented notification systems by offering a single API to manage multi-channel delivery across Email, SMS, Push, Chat, and In-App notifications.

How it works

Novu acts as an abstraction layer between a product or AI agent and various communication providers. It uses a unified conversation model and a single API to route messages. For standard products, it provides a workflow engine with branching and conditions, a digest engine for batching, and embeddable UI components like an Inbox and preferences center. For AI agents, the Agent Communication Infrastructure (ACI) normalizes inbound messages from different platforms into a consistent format, routes them to the agent, and sends responses back out.

Who it’s for

Developers building software products or AI agents that require bidirectional communication with users across multiple third-party platforms (e.g., Slack, Microsoft Teams, Telegram, WhatsApp).

Highlights

  • Unified API: One interface for all messaging providers across multiple channels.
  • Agent Communication Infrastructure (ACI): A specialized layer that connects any AI agent to communication channels without requiring per-platform webhook handlers.
  • Embeddable UI: Ready-to-use React components for a real-time notification center (Inbox) and user preferences.
  • ** uma Workflow Engine**: Tools for creating custom notification workflows, digests, and no-code email editing.
  • Extensive Provider Support: Integrations with dozens of providers for Email, SMS, Push, and Chat.

Related

  • Project
    micro/mu

    A self-hosted runtime for AI agents and services that allows users to run their own personal assistant, tools, and contextual memory in a single binary.

  • Project
    photon-hq/spectrum-ts

    A multi-channel agent framework that enables AI agents to communicate over real conversation surfaces like iMessage, SMS, and Slack instead of web chat.

  • Project
    ljquan/opentu

    Opentu is a canvas-based AI application platform that integrates multi-model generation and tool management into a single workspace for continuous AI task execution.

  • Project
    nutshellai-tech/mobius

    Mobius is a self-evolving Agent OS that connects teams, AI agents, and compute resources into a single workspace, allowing the system to rewrite its own code and UI based on user input.

  • Project
    langbot-app/LangBot

    LangBot is an open‑source, production‑grade platform that lets you attach LLMs to dozens of instant‑messaging services (Discord, Slack, Telegram, WeChat, etc.). It provides a web dashboard, built‑in RAG/tool‑calling, a plugin marketplace, and a Model Context Protocol (MCP) server so other AI agents can manage bots programmatically. Quick start options include a one‑line `uvx langbot` launch, Docker Compose, or hosted LangBot Cloud. The project targets use cases like AI‑driven customer support, internal workflow automation, and cross‑platform community bots.