Loading tool details…
Rivet is an open-source visual programming environment for building AI agents with LLMs, created and maintained by Ironclad. Developers design prompt graphs in a node-based desktop app, save them as version-controllable YAML files, and execute them from TypeScript/Node.js applications via the Rivet Node runtime. The remote debugger lets teams observe a graph running inside a production app in real time — the feature that sets Rivet apart from most agent-building tools.
Rivet is an open-source visual editor for building AI agents. You draw a graph of LLM calls and code steps, save it as a YAML file in Git, then run it inside your Node.js app.
Rivet was created by Ironclad to solve a specific problem: their team was building sophisticated LLM-powered features for their contract management platform and hitting the limits of purely code-based prompt engineering. Complex prompt chains were hard to visualize, harder to debug, and nearly impossible to review collaboratively. Rivet is the tool they built to fix that, then open-sourced. The desktop editor exposes a node-based canvas where each node is a step in a graph — Text nodes, Prompt nodes, Chat nodes for LLM calls, Code nodes for arbitrary JavaScript, Subgraph nodes for composition, plus control-flow nodes for branching, looping, and match/switch logic. LLM providers supported include OpenAI, Anthropic, Google, Anthropic's Claude via Bedrock, and any OpenAI-compatible endpoint (Ollama, LM Studio, vLLM, custom gateways). Graphs are stored as YAML: this makes them diff-friendly in Git, PR-reviewable, and portable across environments. The Rivet Node runtime (@ironclad/rivet-node on npm) loads a project YAML file and executes it programmatically inside a Node.js application. Together with the remote debugger — which uses websockets to stream graph execution back into the desktop editor — teams get a full loop from design to production observability. Rivet supports plugin extensibility: custom nodes, custom LLM providers, and custom plugins can be written in TypeScript and shared as npm packages. The project is MIT-licensed and actively maintained by Ironclad's engineering team, with regular releases on GitHub (run-llama... actually the repo is Ironclad-CX/rivet). Companies publicly using Rivet include Ironclad (contract AI), Attentive (marketing agents), AssemblyAI (transcription pipelines), and Willow Servicing. There is no hosted or commercial version — Rivet is free forever and self-hosted. Best positioned against: LangGraph (Python-first, more community), Flowise (broader no-code, less TypeScript-native), Langflow (Python + hosted option), and CrewAI (agent-team orchestration, Python-first). Rivet is the strongest fit when your team is TypeScript-shaped, needs a shared visual surface for prompt engineering, and wants strong production observability.
Rivet is a standout open-source visual IDE for teams building production LLM agents, offering a unique combination of node-graph editing, real-time remote debugging, and Git-friendly YAML graph storage — all at zero cost under the MIT license. Best suited for engineering teams that want visual prompt chain development with the same code review discipline they apply to application code.
Drag-and-drop nodes for LLM calls, code execution, control flow, and data transformation. The canvas maintains readability at high node counts through subgraph composition, comments, and grouping.
Every project is a plain YAML file. Diffing prompt changes in a PR looks like reviewing any other code file — a critical advantage over tools that lock graphs behind proprietary formats or cloud databases.
Connect the desktop editor to a running Node.js process over WebSocket. Each node lights up as it executes, showing inputs, outputs, LLM responses, and errors. This is Rivet's standout differentiator vs. text-based frameworks.
npm package that loads a Rivet project and executes graphs programmatically. Type-safe input/output contracts, streaming callbacks, and hooks for logging and metrics.
Built-in support for OpenAI, Anthropic, Google Gemini, AWS Bedrock, plus any OpenAI-compatible endpoint (Ollama, LM Studio, vLLM, Together, custom gateways).
$0
Ready to get started with Rivet?
View Pricing Options →Rivet works with these platforms and services:
We believe in transparent reviews. Here's what Rivet doesn't handle well:
Pricing and features change often. If anything on this Rivet page is wrong or missing, tell us and include a link to the source. We review every correction.