Introducing ☄️MolCraftDiffusion☄️: A 3D molecular generative framework for data-driven chemistry We have created a unified generative‑AI framework that makes 3D molecular diffusion models accessible for real-world chemistry applications. 📖 Read more: chemrxiv.org/engage/chemrxi…

Accelerating Enterprise AI with Supermicro and NVIDIA: RAG-ready Infrastructure.

いったいどんな人生を歩んできたらこれを非合理だと思わずにいられるのかまったくわからない

Graph-based RAG with dual-level retrieval! LightRAG is an open-source RAG framework that builds knowledge graphs from documents and uses dual-level retrieval to answer both specific and conceptual queries. Traditional RAG relies on vector similarity and flat chunks. This works

Chunking is the original sin of RAG. You take a beautifully structured document. Slice it into arbitrary 512-token pieces. Destroy all context. Then wonder why retrieval is bad. PageIndex doesn't chunk. Documents stay organized in natural sections. Hierarchy preserved. Context

🚨 Someone just built a self-hosted AI companion that plays Minecraft, chats with you in real-time, and runs completely on your own hardware. It's called Airi and it's not a demo. It's a real AI companion with memory, voice, personality, and a Live2D body that moves when it

Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing

🚨 BREAKING: Someone built an anime AI friend that can literally hop into your games. Airi is a self-hosted companion that doesn’t just talk it plays. → Real-time voice conversations with custom AI characters → Can play Minecraft, Factorio, and more alongside you → Works on

AI assistant for academic writing with Overleaf integration github.com/PaperDebugger/…

AI Engineering are going to love this! ART (Agent Reinforcement Trainer) is an open-source framework for training agents with GRPO + RULER (an automatic reward system). No need to hand-craft reward functions. GitHub: github.com/OpenPipe/ART

Automate web research via local LLMs github.com/langchain-ai/l…

Google just dropped another banger 🤯 They open-sourced the Agent Development Kit, and it perfectly pairs with Gemini 3.1 Flash-Lite. Means you can now build always-on AI Agents that run 24/7 at a negligible cost. 100% Open Source.

MolCraftDiffusion Molecular Discovery (catalyst, material drug design) with 3D molecular generation github.com/pregHosh/MolCr… chemrxiv.org/doi/full/10.26…

Converts static images into editable diagrams and slides github.com/BIT-DataLab/Ed…

MCP server for AI agents to control diagrams github.com/lgazo/drawio-m…

Automates job applications by scraping boards and tailoring resumes github.com/DaKheera47/job…

Building RAG systems usually means stitching together 10 different tools. OpenRAG bundles everything into one stack. • document ingestion • semantic search • agentic workflows • chat over your data Powered by Langflow, Docling, and OpenSearch.

Collection of skills for AI agents github.com/LeoYeAI/opencl…

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in