ianarawjo/ChainForge
An open-source visual programming environment for battle-testing prompts to LLMs.
ChainForge helps you quickly test and compare different prompts for large language models (LLMs) to see which ones work best. You feed it various prompts, LLM settings, and optionally a dataset, and it shows you how different LLMs respond, allowing you to easily evaluate and visualize the quality. This is for anyone creating or refining applications that use LLMs, such as content generators, chatbots, or data analysis tools.
2,958 stars.
Use this if you need to systematically evaluate how variations of prompts and different LLMs perform for a specific task, going beyond simple one-off chats.
Not ideal if you are looking for a simple API wrapper or a basic chat interface for individual LLM interactions without extensive comparison and evaluation needs.
Stars
2,958
Forks
252
Language
TypeScript
License
MIT
Category
Last pushed
Jan 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/ianarawjo/ChainForge"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
microsoft/promptflow
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
pezzolabs/pezzo
🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version...
promptdesk/promptdesk
Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and...
cremich/promptz
Resource Library for AI-assisted software development with kiro
scafoldr/scafoldr
Building an open-source alternative to v0 and Lovable.