Open-source LLM app development platform combining visual agentic workflows, RAG pipelines, model management and observability in one workspace.
giselles-ai/giselle
Open-source AI app builder for creating and running agentic workflows with a visual drag-and-drop editor and multiple LLM providers.
Open-source alternative to:Zapier
- Stars
- 558
- Forks
- 124
- Open issues
- 6
- Last commit
- 20 days ago
What is it?
Giselle is an open source platform for building AI agents and agentic workflows through a visual, drag-and-drop interface. It is aimed at letting teams design agents collaboratively, with humans and AI working together on tasks.
Agents can combine models from OpenAI, Anthropic, and Google AI, selecting a model for each step. The project includes a knowledge store for searching code and data, with GitHub vector store integration, and offers GitHub-related automation for issues, pull requests, and deployments.
Giselle is written in TypeScript and built on Next.js with pnpm and Turbo. It can be run locally with at least one AI provider API key, or used through the hosted cloud service at giselles.ai.
Key features
- 01Drag-and-drop visual builder for creating and modifying agents
- 02Supports GPT, Claude, Gemini and other models within one workflow
- 03Knowledge store for searching code and data, with GitHub vector store integration
- 04GitHub AI operations for automating issues, PRs, and deployments
- 05Runs locally with OpenAI, Anthropic, or Google AI API keys
Use cases
- Automating code review and pull request workflows on GitHub
- Building research agents that gather information from the web and internal documents
- Generating PRDs, specs, or release notes from a codebase
- Chaining multiple AI models to handle multi-step business processes
Quick start
- 1
Clone the repository
git clone https://github.com/giselles-ai/giselle.git - 2
Enter the project folder
cd giselle - 3
Install dependencies
pnpm install - 4
Start the development server, then add at least one AI provider API key in .env.local
pnpm turbo dev
Things to know
- Requires at least one paid AI provider API key (OpenAI, Anthropic, or Google AI).
- Still in active development, and some features such as team collaboration and template hub are in development.
- Self-hosting requires setting up a local development environment with pnpm.
Topics
FAQ
- What is giselle?
- Open-source AI app builder for creating and running agentic workflows with a visual drag-and-drop editor and multiple LLM providers. Giselle is an open source platform for building AI agents and agentic workflows through a visual, drag-and-drop interface. It is aimed at letting teams design agents collaboratively, with humans and AI working together on tasks.
- Is giselle free to use? What license does it have?
- giselle is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is giselle still maintained?
- Actively maintained. The last commit to giselle was on Oct 1, 2026.
- What can I use giselle for?
- Automating code review and pull request workflows on GitHub Building research agents that gather information from the web and internal documents Generating PRDs, specs, or release notes from a codebase Chaining multiple AI models to handle multi-step business processes
- How do I install giselle?
- Clone the repository: git clone https://github.com/giselles-ai/giselle.git Enter the project folder: cd giselle Install dependencies: pnpm install Start the development server, then add at least one AI provider API key in .env.local: pnpm turbo dev
- Where can I get giselle?
- The source code and installation instructions are on GitHub: https://github.com/giselles-ai/giselle
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
FastGPT is an open-source AI Agent building platform with data processing, RAG knowledge bases, and visual workflow orchestration for LLM apps.
A zero-code platform that generates production-style AI agents from natural-language descriptions, with built-in tools, memory and orchestration.
LobeHub is a platform for organizing AI agents into always-on teams that can be hired, scheduled, and reviewed from one place.
Agent-native memory infrastructure that turns LLM agent conversations and execution into persistent, structured memory for Python and TypeScript apps.
Memory operating system for LLMs and AI agents that stores, retrieves, and manages long-term memory as an editable graph.