

Rivet
β Text source-checked Nov 15, 2026Visual programming environment for building AI agents with LLMs.
Source-checked against the vendor's site Β· rebuilt from the vendor's own pagesProfile updated Link checked How we rate
In short
Rivet is a cross-platform desktop app for visually building and debugging AI agents. It uses a node-based editor to create prompt chains and integrates with TypeScript.
Rivet is a visual programming environment for building AI agents with LLMs. Rivet is a desktop application for creating complex AI agents and prompt chaining, and embedding it in your application. Rivet core is a TypeScript library for running graphs created in Rivet.
Rivet's node-based editor enables users to create, configure, and debug complex AI prompt chains and AI agent chains visually. Rivet offers live debugging of AI chains as they run, allowing users to monitor the state of their AI agent in real-time and quickly identify any issues that may arise. Rivet also supports remote debugging, allowing users to debug AI chains running on a remote server.
Rivet graphs are YAML files that users can version in their team's repository and review using code review tools.
Rivet supports LLMs including OpenAI GPT-3.5 and GPT-4, Anthropic Claude Instant and Claude 2, Anthropic Claude 3 Haiku, Sonnet, and Opus, and the AssemblyAI LeMUR framework for voice data.
Rivet is available for MacOS, Linux, and Windows.
According to Rivet: Rivet is a visual programming environment for building AI agents with LLMs. Its pages list this strength: Live debugging allows monitoring the state of AI agents in real-time.
β The AI Tool Bible editorial team
Pros
- β Live debugging allows monitoring the state of AI agents in real-time.
- β Remote debugging supports debugging AI chains running on a remote server.
- β Graphs are YAML files that can be versioned in a repository and reviewed with code review tools.
- β Supports multiple LLM providers including OpenAI, Anthropic, and AssemblyAI.
Facts
- Platforms
- macos, linux, windows, web (not source-checked)
- API available
- Yes (not source-checked)
- Open source
- Yes (license: MIT)
- GitHub stars
- 4,727 (checked Nov 13, 2026) (not source-checked)
- Last GitHub push
- Aug 26, 2026 (not source-checked)
- First commit
- Apr 2023 (not source-checked)
- Company
- Ironclad, Inc. (not source-checked)
- Model used
- Multi-model (not source-checked)
- Docs pages indexed
- 145 pages we found in the docs (not source-checked)
- Hacker News
- 1 story Β· top 176 points Β· last Sep 8, 2023 Β· checked Nov 20, 2026
- Earliest Wayback capture
- 2023-09-07 (earliest archived capture of the site, not a launch date)
Where this tool sits
Use cases
Frequently asked
- How much does Rivet cost?
- Rivet is listed as free, though no specific pricing details are provided in the documentation. It is available as a desktop application for MacOS, Linux, and Windows.
- Which AI models does Rivet support?
- Rivet supports OpenAI GPT-3.5 and GPT-4, Anthropic Claude Instant, Claude 2, and Claude 3 (Haiku, Sonnet, Opus). It also supports the AssemblyAI LeMUR framework for voice data.
- Can I debug my AI agents in real-time?
- Yes, Rivet offers live debugging to monitor agent state in real-time. It also supports remote debugging for AI chains running on a remote server, helping users quickly identify issues.
- How do I integrate Rivet into my application?
- Rivet graphs are YAML files that can be versioned in your repository. Rivet core is a TypeScript library designed for running these graphs, allowing you to embed the agents in your application.
- What is the learning curve like for Rivet?
- Rivet uses a visual, node-based editor to create and configure chains. This visual approach allows users to build complex prompt and agent chains without writing code for the structure, though TypeScript is needed for integration.