This is where we'll be providing the most up to date news for the platform
Most of this week was spent working on our backend behind the scenes to set up the Infrastructure needed to improve our product moving forward.
With this comes the start of our Python migration🐍, allowing us to connect with the existing LLM ecosystem and access more tools!
We have a suite of new features in the Python backend, but they're unfortunately not operational yet.
In the meantime, we have reintroduced our basic web search capabilities 🌐 and have added a daily run limit to ensure we don't have to take it down in the future.
With our new infrastructure in place, this week will involve:
- Fully migrating to the Python backend
- Subscriptions so users can avoid usage limits
- Improved Agent handling via the ReAct framework
- Additional tool support
And again, thanks for joining us in this journey!
• • •
Missing some Tweet in this thread? You can try to
force a refresh
Introducing #AgentGPT, an attempt at #AutoGPT directly in the browser 🤖
Give your own AI agent a goal and watch as it thinks, comes up with an execution plan and takes actions. Try for free now at https://t.co/julzWBNk6Xagentgpt.reworkd.ai
Built using @nextjs with the @t3dotgg stack, @LangChainAI, #GPT3 and
Established from ideas by #BabyAGI from @yoheinakajima and #AutoGPT from @SigGravitas
It works through using models to generate a task list and then iteratively executes tasks, evaluating whether or not tasks are completed or require further sub-actions.
In the future, we'll have long term memory via @pinecone and give models the ability to query the web