Hello everyone, I've been part of this community for quite some time, mostly as a reader, but now I'd like to ask a question that is closely related to AI agent development. I'd especially appreciate insights from people with hands-on experience designing AI agents and multi-agent systems. When building AI agents, it has become common practice to represent agent architectures as graph-based workflows using frameworks such as LangChain and related tools. This applies both to the internal architecture of a single agent and to orchestration in multi-agent systems handling more complex tasks. My question is: how much time and effort does it typically take you to design a high-quality agent (or multi-agent) architecture without LLM assistance? We all know that modern LLMs are extremely capable when it comes to coding. However, I'm curious about your experience with using them for architecture design itself. How good are they at proposing agent or multi-agent architectures, and how much do you trust their recommendations in this part of the development process? Do you mainly: - Design the architecture yourself and use LLMs only as assistants? - Or do you largely rely on LLMs to generate the architecture and then refine it afterward? I'm currently working on a system aimed at optimizing the design of AI agent architectures (graph-based workflows), so any experiences, opinions, or lessons learned would be extremely valuable. Looking forward to hearing your thoughts.

Hi, I am going over Brandon's langchain masterclass, inorder to save the chat history of messages Google FireStore is been used. I am curious to know if the same can be accomplished with Supabase or other production grade popular alternatives, thanks..

Hi While importing "from langchain.chains import create_history_aware_retriever" It's throwing errors. Please suggest any other to use Chat history.

For both Python and TypeScript Some highlights: - New Docs - LangChain Agent: revamped and more flexible with middleware - LangGraph 1.0 - Standard content blocks: swap seamlessly between models LangChain and LangGraph Agent Frameworks Reach v1.0 Milestones

Hey AI Developer Accelerator community! I've been building an open-source alternative to LangGraph Platform that addresses the major pain points we face when deploying AI agents. THE PROBLEM: - LangGraph Platform pricing is 10x what's reasonable for scale - Self-hosted "Lite" option has no custom auth (what's the point?) - Vendor lock-in with no way to bring your own database - Forced tracing with no privacy controls MY SOLUTION: - Self-hosted deployment (no per-node pricing) - Custom authentication (Supabase Auth, JWT, OAuth, etc.) - PostgreSQL persistence (no vendor lock-in) - Backward compatible with LangGraph Client SDK - Agent Protocol compliance Agent Protocol Server: https://github.com/ibbybuilds/agent-protocol-server WHY THIS MATTERS FOR AI DEVELOPERS: - Reduce your infrastructure costs by 90% - Full control over your data and privacy - No vendor lock-in for your AI applications - Custom auth integration with your existing systems CURRENT STATUS: MVP ready, already got our first contributor reaching out! LOOKING FOR: - Early adopters to test and provide feedback - Contributors to help shape the roadmap - Community input on what features are most needed Anyone interested in testing this or contributing to the project? This could be a game-changer for AI app deployment costs!