Show HN: Superflows – open-source AI Copilot for SaaS products

Show HN: Superflows – open-source AI Copilot for SaaS products

Henry, Matt and James here – we’re building an open source toolkit that makes it easy to integrate an LLM-powered copilot that talks to your API into software products.

It works by calling API endpoints which you choose to expose to it. This lets the chatbot complete tasks within your software in response to natural language queries.

It’s also open source, so you don’t have to send user data to another 3rd party. We support Llama 2, but we haven’t fine-tuned Llama 2 yet (coming soon) so highest accuracy is seen with GPT-4 or fine-tuned GPT-3.5 (much faster).

We started working together 2 years ago and have pivoted a few times. One problem we came across running a startup was we had to learn to use a lot of business software.

We also heard from software companies that one of their biggest problems was helping users get the most out of their software. We’re building Superflows to address these problems.

You can upload your OpenAPI spec to get up and running. Endpoints can be enabled/disabled and you can evaluate performance in the playground. There’s a React component library for easy integration.

You can self-host for free. We're charging for the cloud version. This has faster & easier setup, user permissions (in future), analytics & support.

Give it a spin and let us know what you think!




First one of these I've seen that actually supports an open source models

Can you self-host the models too?


Not right now, but we're working on it! :)

Base Llama 2's reliability on our prompt isn't good enough right now so working on fine-tuning it to make sure it outputs the right format - we'll release this at the same time as we make it easier to self-host


This looks so really cool, we tried to build something similar in-house for our SaaS product but it took too long and wasn't reliable enough. Would love to retry with superflows sometime!


Totally get the reliability issues you've seen - getting LLMs to output the right response 80% of the time on these kinds of tasks is not that hard, the last 20% is the real challenge.

On trying us out - ping me an email at


Looks great! I really like the developer dashboard - so many other OSS tools (eg langchain w/ loaders) trade off ease of debugging for setup speed.