FalkorDB’s Post

FalkorDB reposted this

View organization page for The Year of the Graph, graphic

3,400 followers

HybridAGI: A Programmable Graph-based Open Source Framework for Neuro-Symbolic AI HybridAGI is an AgentOS framework designed for creating explainable and deterministic agent systems suitable for real-world applications. It is a programmable LM-based Agent that enables defining behavior using a graph-based prompt programming approach. The metaphor its creators use to describe it that if DSPy is the PyTorch of LMs Applications, HybridAGI is the equivalent of Keras for LMs Agents systems.  It's a memory-centric system which centralizes knowledge, documents, programs and traces into a hybrid vector/graph database. HybridAGI is designed for data scientists, prompt engineers, researchers, and AI enthusiasts who love to experiment with AI.  It is a "Build Yourself" product that focuses on human creativity rather than AI autonomy. It's open source, GitHub link available in the comments. Has anyone used it? Let us know what you think. #KnowledgeGraph #AI #LLM #DataScience #Python #OpenSource #GenAI #EmergingTech 

  • No alternative text description for this image
Liam McGee

Making data fit for human use. Keeping it real (ontologically). Building tools for the future of infrastructure.

2mo

While I _am_ very excited about this, the sentence “The metaphor its creators use to describe it that if DSPy is the PyTorch of LMs Applications, HybridAGI is the equivalent of Keras for LMs Agents systems.” was funny I think we may need to work on our metaphor accessibility to non specialists…

Yoan Sallami, PhD

PhD in Human-Robot Interactions, expert in neuro-symbolic cognitive architectures, co-founder and CEO of SynaLinks | Building the LLM based Agent systems of tomorrow using Graphs and Symbolic AI.

2mo

Thanks for sharing! Many new features are coming in the next weeks, this is just the starting point of the journey! :D join our discord if you don't want to miss anything! :) https://discord.gg/82nt97uXcM and leave a star if you find it appealing

Daniel Svonava

Vector Compute @ Superlinked | xYouTube

2mo

How exactly does this graph-based approach work under the hood? Like, are we talking about some kind of knowledge graph that the agent navigates, or is it more abstract?

Peter Emmenegger

Test Systems Consultant at ee.works

2mo

Marco Schmid, thanks for sharing. This is really powerful. A graph-based approach - now we're talking. It could be the entry point to closing the loop between requirements and state diagrams or the high-level diagrams. P.S. Copilot did a good job explaining the framework.

David Stevens

Founder, scrappy servant leader, love 0-1 especially inside scale up 10-100, intersection of product-engineering-business, exponential thinker, autodidact, challenger of the status quo, a crazy one, beach taker.

2mo

Very interesting.

Oliver Cronk

Technology Director & Sustainable Tech Leader at Scott Logic | #ArchitectTomorrow Podcast | R&D | Innovation | Speaker & Facilitator

2mo

Thanks for this! Phil Baxter Hélène Sauvé one to take a look at.

Jon Seals

Artist | Educator | Curator

2mo

Joshua Rio-Ross, Joshua, this reminds me of how I’m organizing my circle compositions. Interesting!

Mark Bain

Multifaceted polymath, serial entrepreneur, tech geek, problem solver, builder

2mo
See more comments

To view or add a comment, sign in

Explore topics