LangChain + WhatsAppConnect your LangChain agent to WhatsApp
LangChain is the open-source framework for building agents and LLM apps in Python and JavaScript. Novu Connect gives it a voice in WhatsApp, with a real two-way conversation and reliable delivery. Build the agent once, reach users where they already work.
What is LangChain
LangChain gives developers the building blocks for agents: models, tools, memory, and control flow. You compose chains and agents, wire in your own tools, and keep the reasoning in your codebase. LangChain runs the agent. It does not carry the conversation to your users. That last mile, reaching a person in Slack and routing their reply back to your agent, is what Novu Connect adds.
- Tool calling and structured output for real agent actions
- Memory and retrieval for context across a conversation
- Runs in Python or JavaScript, in your own app
- A large ecosystem of integrations you already use
LangChain in WhatsApp
Novu Connect is the communication layer, the ACI, Agent Communication Infrastructure, bridge between your LangChain agent and WhatsApp. Your agent keeps running in your app. Novu delivers its messages to WhatsApp, maps each user, and forwards their replies back to your handler. We never run your agent's reasoning. That is the whole point.
One agent, WhatsApp, resolved in the thread
Novu Connect puts an existing AI agent on WhatsApp with secure two-way conversations, approved message templates, and delivery receipts. Novu is an official Meta Business Partner, so WhatsApp is working in about 5 minutes. A shopper asks where their order is. The agent finds the delay, offers options with quick replies, reroutes to a pickup point, and confirms.
How to connect LangChain to WhatsApp
Keep your LangChain agent
Your agent, tools, and memory stay in your codebase exactly as they are. Novu Connect wraps the input and output, so your LangChain logic does not change when you add WhatsApp.
Connect the channel
Run npx novu connect --channel whatsapp --runtime langchain. The CLI scaffolds a bridge route in your app and connects WhatsApp. You can also paste the prompt below into your coding agent and let it wire the bridge for you.
Wire the bridge handler
The CLI prints a requirements file with the bridge route and handler. Point it at your LangChain agent so messages from WhatsApp reach your agent and its replies route back to the same conversation.
Go live
Sign in to keep the agent live, then run your dev server. Your LangChain agent now holds a two-way conversation in WhatsApp, and the same agent can reach every other channel from one thread.
Every LangChain connect command
npx novu connect --channel whatsapp --runtime langchainPrompt for your coding agent
Connect this project's LangChain agent to WhatsApp with Novu using instructions from https://novu.co/agents.md
Full setup for LangChain lives in the LangChain connect guide.
LangChain and WhatsApp, common questions
Connect your LangChain agent to another channel
Same agent, built once. Pick where it talks next, and it holds one conversation across every channel.