# Ironclad/rivet

The open-source visual AI programming environment and TypeScript library

Repository: https://github.com/Ironclad/rivet
Canonical: https://ross.abutalabs.com/products/rivet
Homepage: https://rivet.ironcladapp.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, llm, openai, typescript
Last push: 2026-08-26T14:00:38+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 42, longevity 87
- inputs: {"age_days": 1229, "days_push": 7, "days_rel": 390, "gap_med": 7, "n_releases_24m": 14}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4680, forks 387 (observed 2026-08-28T04:08:56.863193+00:00)

## What it is
Rivet is an open-source visual AI programming environment consisting of a desktop IDE for building AI agents and prompt chains via a node-based graph editor, plus a TypeScript library (Rivet Core/Node) for executing those graphs in applications. It supports OpenAI, Anthropic, and AssemblyAI models, with vector database integrations like Pinecone.

## Use cases
- build ai agents visually without writing code
- design and debug complex llm prompt chains
- embed ai agent graphs into a node.js application
- collaborate on prompt graphs with version control
- remotely debug llm workflows running in production
- prototype and a/b test prompts with variations
- build rag pipelines with embeddings and vector databases

## When to choose
- you want a visual, node-based IDE for designing LLM agent workflows
- your team needs to collaborate on and version prompt graphs as YAML files
- you want to run designed graphs programmatically in a TypeScript/Node.js app
- you need real-time debugging of AI agent execution

## When to avoid
- you only need simple single-prompt LLM calls from code
- your stack is not TypeScript/Node.js for runtime integration
- you need models or providers not supported by Rivet
- you prefer writing agent logic directly in code rather than graphs

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, prompt-engineering, llm-inference, rag, machine-learning, developer-tools, sdk
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: windows, cross-platform
- tags: visual-programming, node-based-editor, prompt-chaining, llm-ide, graph-execution, openai, anthropic, ai-agents, natural-language-processing, macos, linux, nodejs, typescript, desktop

## Member repositories
- Ironclad/rivet (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:56.863193+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:19.687620+00:00, confidence not recorded.
  - readme: https://github.com/Ironclad/rivet (fetched 2026-08-28T04:08:56.863193+00:00, sha 0942adc9b8fb)
  - homepage: https://rivet.ironcladapp.com (fetched 2026-08-29T09:03:47.689669+00:00, sha 8f4ca87ea777)
  - site_page: https://rivet.ironcladapp.com/docs (fetched 2026-08-29T09:03:47.699726+00:00, sha e089187dde28)
  - site_page: https://rivet.ironcladapp.com/docs/getting-started/installation (fetched 2026-08-29T09:03:47.703443+00:00, sha 03f83fbe98dd)
  - site_page: https://rivet.ironcladapp.com/docs/api-reference/getting-started-integration (fetched 2026-08-29T09:03:47.704882+00:00, sha 9448a44ba7c1)
  - site_page: https://ironcladapp.com/product/ironclad-contract-ai (fetched 2026-08-29T09:03:47.701639+00:00, sha 2f26a341956a)
- Data as of 2026-08-30T08:39:29.467469+00:00.