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…
In plain words
Superflows is an open-source toolkit for integrating AI-powered chatbots into SaaS products. It enables the chatbot to complete tasks within software by calling selected API endpoints in response to natural language queries. The open-source approach keeps user data private without relying on third-party services. It works with Llama 2, GPT-4, and fine-tuned GPT-3.5, with the latter offering faster performance. The tool is designed for software companies looking to help users better utilize their products.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
