ianarawjo/ChainForge

An open-source visual programming environment for battle-testing prompts to LLMs.

51
/ 100
Established

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.

prompt-engineering LLM-evaluation AI-application-development natural-language-processing chatbot-development
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

2,958

Forks

252

Language

TypeScript

License

MIT

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.