Show HN: Knit – A Better LLM Playground

Posted by xjconlyme on Tuesday August 08, 2023 @07:33AM
from the show-hn dept.

https://promptknit.com

Knit was created to solve pains of other LLM playgrounds.

Some of the highlights:

- Smart prompt builder, create prompt with simple requirement and few shot learning, fast and effortlessly.

- Function call simulation, visualize the function callings and you can also setup a mocked value to return.

- Support OpenAI/Anthropic/Azure models.

- Manage prompts with projects and members.

- And so much more!

I have been developing Knit by myself for over 4 months now, and am looking for ways to improve it. Any feedback is appreciated.

( 4 comments | on HN )

Re:Show HN: Knit – A Better LLM Playground by tikkun on Tuesday August 08, 2023 @08:45AM (#37048200)

Looks nice, and it's nice that it also supports function call simulation.

I've been collecting a list of tools for prompt engineering, I've added Knit now.

Newly added: https://promptknit.com/

Newly added: https://github.com/promptfoo/promptfoo

Newly added: https://promptlayer.com

https://promptable.ai/

https://github.com/ianarawjo/ChainForge

https://trywale.com/

https://promptknit.com/

https://promptrefine.com/

https://www.vellum.ai/

https://promptclub.ai/

https://www.everyprompt.com/

https://scale.com/spellbook

[ Parent | on HN ]

Re:Show HN: Knit – A Better LLM Playground by tikkun on Tuesday August 08, 2023 @09:02AM (#37048371)

I re-read my list and realized I'd already added promptknit about 2 months ago :)

[ Parent | on HN ]

Re:Show HN: Knit – A Better LLM Playground by xjconlyme on Tuesday August 08, 2023 @08:56AM (#37048313)

thx! Prompting is still hard, people need better tools.

[ Parent | on HN ]

Re:Show HN: Knit – A Better LLM Playground by resiros on Thursday August 10, 2023 @08:11AM (#37075169)

Can you add https://github.com/Agenta-AI/agenta (Agenta.ai) We're an open-source platform that includes prompt engineering, end-to-end evaluation (even for larger workflows with multiple-prompts and retrieval augmented generation), and deployment.

[ Parent | on HN ]