ironclad/rivet

★ 4,577TypeScriptAudience · vibe coderComplexity · 3/5Setup · easy

Mindmap

mindmap
  root((rivet))
    What it does
      Visual AI agent builder
      Graph-based logic
      Run graphs in code
    Tech stack
      TypeScript
      NPM library
      Desktop app
    AI providers
      OpenAI GPT-4
      Anthropic Claude
      Pinecone search
    Use cases
      No-code AI design
      Production deployment
      Team collaboration

mindmap root((rivet)) What it does Visual AI agent builder Graph-based logic Run graphs in code Tech stack TypeScript NPM library Desktop app AI providers OpenAI GPT-4 Anthropic Claude Pinecone search Use cases No-code AI design Production deployment Team collaboration

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Design an AI chatbot workflow visually without writing code, then embed it in a live product.

USE CASE 2

Build a document Q&A agent that searches a knowledge base, by connecting nodes in the visual editor.

USE CASE 3

Let a designer or PM create the AI logic and hand it off to a developer to wire into production.

Tech stack

TypeScriptNode.jsNPM

Getting it running

Difficulty · easy Time to first run · 30min

Requires API keys for AI providers (OpenAI, Anthropic, etc.) to run graphs.

License details not mentioned in the explanation.

In plain English

Rivet is a desktop application and programming environment for building AI agents visually. Instead of writing code to chain together prompts and AI calls, you draw the logic as a graph, connecting nodes that represent different steps. The result is a visual diagram that shows exactly how your AI system works, which makes it much easier to understand, debug, and share with others. The application works with several AI providers out of the box. You can connect to OpenAI models like GPT-3.5 and GPT-4, Anthropic's Claude family of models, and AssemblyAI for converting speech to text. It also supports storing and searching information using OpenAI Embeddings and Pinecone, which lets you build agents that can look things up from a large document collection or knowledge base. Beyond the visual editor, Rivet ships a TypeScript library called Rivet Core that developers can drop into their own applications. Once a graph is designed in the desktop app, the library can run it inside a product without the user ever opening the visual tool. This means a non-technical person or designer can build the AI logic in the visual environment, and a developer can then wire it into a live product with a small amount of code. The library is published on NPM under the names @ironclad/rivet-core and @ironclad/rivet-node. Installation is straightforward. Prebuilt downloads are available for macOS, Windows, and Linux. There is no server to set up for the desktop app itself. Running it from source is covered in the contributing guide for anyone who wants to modify the code. The project is open source and welcomes contributions of all kinds, including bug reports, documentation improvements, and feature suggestions. A Discord server is available for questions and community discussion.

Copy-paste prompts

Prompt 1

I have a Rivet graph that chains a GPT-4 prompt with a Pinecone lookup. Show me how to run this graph in my Node.js app using @ironclad/rivet-node.

Prompt 2

Using Rivet Core in TypeScript, write code that loads a .rivet-project file and executes the 'main' graph with these input variables: [list your variables]

Prompt 3

What nodes should I connect in Rivet to build an agent that takes a user question, searches a Pinecone vector store, and returns a GPT-4 answer?

Prompt 4

Show me how to pass external data into a Rivet graph at runtime so the graph can use live values from my application.

Open on GitHub → Explain another repo

← ironclad on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.