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!

I am very new to Lang chain. Watched yoututbe video (https://www.youtube.com/watch?v=yF9kGESAi3M&t=7261s) and am mimicking the codes. While practicing RAG, first error came from TextLoader( "./..//odyssey.txt") - Even when odyssey.txt was present in the directory, it showed "file not found". Solved it by using TextLoader("./..//odyssey.txt", encoding='utf-8'). But when I am using the same query as used in the video- "Who is Odysseus' wife?" Retriever finds very odd results, no relevancy I can find in the answer. The image shows the retrieved answer by the retriever. Furthermore, in the case of RAG for conversation, the LLM always generates "answer cannot be found". I am using Google's embedding - GoogleGenerativeAIEmbeddings(model="models/embedding-001"). I feel something is wrong with vector generation. However, I have also tried with Huggingface embedding model, the issue remains. Your advice will be helpful. Thanks for your time.

Hi all -- I am new to this. I am following the instructions in the video and got stuck at the very beginning, when setting up the environment. I am running a 2025 Mac Sequoia 15.5. When downloading Python it does so using the latest version 3.13.xx and all the poetry references in the *.toml file are restricted to python versions between 3.10.xx and 3.12.xx. I tried changing the configuration in the file but the trick did not work. Some of the issues included not finding dotenv and other imports as well. Any advice? Is there any way in which I can follow the tutorial without poetry? Is there an updated version for more recent version of Python, Poetry, etc.? Thanks in advance, Macos.

I am currently working on OAP , agentic Ai, langchain, langgraph and MCPs I would like to connect with you. 🔗 www.linkedin.com/in/amanjain1644

heyy there guys, can someone tell me what langchain is used for ?