We've been exploring the space of AI agents and as part of our research we've made a list of both open source and closed source AI agents.
We've tried to include mostly just agents but the lines sometimes get blurry as it's hard to sometimes distinguish agents from SDK.
At the moment, a lot of these agents are still in the "toys" stage but we think the future looks very promising. Especially some of these agents are already pretty helpful.
Curious to hear what has been yours experience with agents?
I'm working on an AI agent that functions as a Project Manager. It will pull Jira task statuses, ask for updates, lead standup, and measure velocity - all with a bit of sass.
I've been working on this project for a while, it's an open source platform to help developers create and integrate AI agents into their web applications without hustling and wasting time on technical stuff.
AI agents are multimodal: can accept text, images, and audio as input, and return text, audio, or JSON as a response with real-time streaming.
You can also extends agents knowledge, connect them with APIs and custom functions, and easily manage their long-term memory and context.
The platform will give you full data validation, type safety, easy server-client integration for modern web applications, and works with the edge out of the box.
you can start by checking the website at scoopika.com.
For people wanting to play with that: this is very close to langchain's agents system (their documentation has a very impressive demo using both a calculator and Google searches as tools available to a language model).
It's pretty interesting how well it works, but there is a lot more to improve as you can refine the agents for more than their generalized domain, into their perspective and real publish knowledge for increased improvement.
Our startup has been building agents inside of a workspace for the past few months. We had our first version about nine months ago, and the UI looks almost identical to OpenAI's.
That said, it's going to be very interesting to see if one AI Agent platform becomes the standard, or if people end up having different AIs for different platforms.
On our end at least, we are planning to keep our agent builder, even if we end up using OpenAI on the backend. At the very least we will at least maintain the agency to utilize another platform if we want.
Yes, this will be an interesting next experiment - adding agents with additional tools (also for example access to internal APIs) will be quite powerful.
It's great to see this kind of infrastructure work to integrate a variety of agents into whatever system you're building. Keep up the good work! I may crib some notes from this for use in non-Python projects.
reply