Search code, repositories, users, issues, pull requests...
HybridAGI is the first Programmable LLM-based Autonomous Agent that lets you program its behavior using a graph-based prompt programming approach. This state-of-the-art feature allows the AGI to efficiently use any tool while controlling the long-term behavior of the agent.
Automatic prompt optimization & finetuning: Thanks to the integration of DSPy, HybridAGI can self-refine its own prompt automatically. This new feature helps the system optimize itself based on the examples you provide. You can use the LLM as a judge and train your AI with ease or even finetuning it. See the examples for more information.
For AI makers: This framework is intended for data scientists, prompt engineers, researchers, and AI enthusiasts who love to experiment with AI. This product requires some programming and prompt engineering knowledge to get the best out of it. It's a Build Yourself product where the focus is on human creativity rather than AI autonomy. If you are new to prompt engineering, start by looking at this guide.
Memory-Centric AGI: Thanks to a hybrid vector and graph database powered by FalkorDB enabling efficient storage of data, you can inspect its long-term memory and know what's going on at a glance! The AGI remembers its programs, can execute, or modify them dynamically.
