Across the many experiments I've made this year (and which I've written about here) I've felt the need for better tools. Specifically, for the past few months I have been building copilots, and doing so from scratch takes a bunch of work every time.
So we decided to release OpenCopilot: an OSS framework which helps developers to build open-source AI Copilots that actually work and embed into their product with ease.
Why another LLM framework? Quoting from our Hacker News post:
Twitter is full of impressive LLM applications but once you peel off the curtains it’s clear that they are just demos. The reason being because building an AI Copilot that goes beyond a Twitter demo can be complex, time-consuming and unreliable.
Our team has been in the AI space since 2018 and built numerous LLM apps & copilots. While doing that, we got approached by many startups saying they’d also like to build a copilot for their product but they haven’t been able to get it reliable, fast or cost-effective enough for production use. Thus we built OpenCopilot framework, so devs can intuitively get AI Copilots running in less than 10 minutes and iterate towards a useful Copilot in a single day.
We believe every product, company and individual will have their Copilot in the future. Thus, we’d love your feedback, questions and constructive criticism.
If you've considered making a copilot - for work or for fun - please try it out. Tthis is a very early release and I would love to hear your feedback, so if you do, I'd love to hear from you! Just shoot me an email at
taivo [at] opencopilot.dev.
One surprising thing I've found is that it can be kind of addictive to make copilots. Once you get the first working version (which is very quick with the OpenCopilot framework), you can see bugs and improvements very clearly, and fix them very quickly. If - like for me - the copilot helps you with your actual daily work, it becomes a very powerful loop.