Rivet: Visual AI Programming Environment and TypeScript Library for Agents

RepositoryIronclad/rivetTool

Rivet by Ironclad is an open-source visual IDE and TypeScript runtime for designing complex prompt chains and AI agents, allowing visual graphs to be embedded directly into software applications.

Key points

  1. Visual desktop IDE to build, inspect, and chain AI prompts and agents.
  2. TypeScript library (Rivet Core) for executing designed workflow graphs within host applications.
  3. LLM support for OpenAI GPT-3.5/GPT-4 and Anthropic Claude Instant, Claude 2, and Claude 3 (Haiku, Sonnet, Opus).
  4. Vector and embedding integrations covering OpenAI Embeddings and Pinecone.
  5. Audio and speech workflow support via AssemblyAI (Speech-to-Text and LeMUR).
  6. Published as open source under the MIT License with prebuilt application binaries.

Why it matters

Managing and debugging complex multi-step prompt workflows purely in code can quickly become unmanageable. Rivet addresses this by providing a visual graph-based canvas while offering a runtime library that executes those exact graphs inside TypeScript applications.

Analysis

Rivet bridges the gap between rapid prompt experimentation and production software engineering. By decoupling the visual graph editor from the executing runtime engine, teams can iterate on agent behaviours and prompt engineering visually before embedding the resulting workflows. Backed by Ironclad and carrying over 4,600 GitHub stars under an MIT licence, it represents a mature, practical tool specifically designed for TypeScript/Node.js developers deploying LLM-powered systems.

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Link:FlowiseAI

    Flowise: Open-Source Visual Builder for AI Agents

    Flowise is an open-source, low-code platform designed to build AI agents, chat assistants, and RAG workflows visually. It enables developers to orchestrate multi-agent architectures and integrate them using APIs or SDKs.

    AI & LLMs· Tool

  • Repository:earendil-works/pi

    Pi: Modular TypeScript Toolkit for AI Agents and Coding CLIs

    Pi by earendil-works is an open-source TypeScript ecosystem for autonomous AI agents. It bundles a unified multi-provider LLM API, an agent runtime with state management, a terminal UI library, and an interactive coding agent CLI.

    102kstarsTypeScript

    AI & LLMs· Tool

  • Repository:rohitg00/agentmemory

    agentmemory: Persistent Memory for AI Coding Agents

    agentmemory is an open-source TypeScript solution providing persistent memory for coding agents and MCP clients. Powered by the iii engine, it builds on Andrej Karpathy's LLM Wiki pattern by introducing confidence scoring, lifecycle management, knowledge graphs, and hybrid search.

    28kstarsTypeScript

    AI & LLMs· Tool

  • Repository:vercel/ai

    Vercel AI SDK: Provider-Agnostic TypeScript Toolkit for AI Applications and Agents

    Vercel's AI SDK is an open-source TypeScript library for developing AI-powered applications and agents. It provides a unified API across diverse model providers including OpenAI, Anthropic, and Google, and integrates directly with frameworks such as Next.js, React, Svelte, Vue, and Angular.

    26.6kstarsTypeScript

    AI & LLMs· Tool

  • Repository:EveryInc/compound-engineering-plugin

    Compound Engineering: 33-Skill Plugin for AI Coding Agents

    Compound Engineering is an open-source plugin for AI coding agents designed to structure development workflows and systematically preserve learned context. It runs on 14 platforms, including Claude Code, Cursor, and Codex.

    24.9kstarsTypeScript

    AI & LLMs· Tool

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.