Github
66 articles and counting — stay ahead of the curve.
66 articles published
Memory for 24/7 proactive agents like openclaw (moltbot, clawdbot).
MemU Builds Persistent Memory for Always-On AI Agents AI agents often struggle with short-term memory, forcing users to repeat context and costing businesses significant compute resources. NevaMind-AI’s new open-source framework, memU, changes this by providing a persistent, always-on memory system
![[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"](https://res.cloudinary.com/deilllfm5/image/upload/v1774511326/trendingsociety/og-images/2026-03/hkuds-lightrag-boosts-rag-speed-simplicity-emnlp20.png)
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
LightRAG Accelerates RAG System Development with Knowledge Graphs Building sophisticated Retrieval-Augmented Generation (RAG) systems just became simpler and faster with LightRAG, an open-source framework that integrates advanced knowledge graph capabilities and multimodal processing to enhance Lar
"🐈 nanobot: The Ultra-Lightweight OpenClaw"
Nanobot: Tiny AI Assistant Shrinks OpenClaw to 99% Smaller Codebase An ultra-lightweight AI assistant called nanobot emerges as a streamlined alternative to the popular, but complex, OpenClaw framework, delivering core agent functionality with 99% fewer lines of code. This open-source project direc
Production-ready platform for agentic workflow development.
Dify, an open-source platform, streamlines the development of large language model (LLM) applications, enabling developers to build powerful AI workflows from prototype to production rapidly. It combines intuitive visual workflow design, comprehensive model support, and advanced agent capabilities,
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
PageIndex Revolutionizes RAG with Reasoning, Ditching Vectors PageIndex, a new open-source project by VectifyAI, dramatically improves document analysis for large language models (LLMs) by achieving 98.7% accuracy on the FinanceBench benchmark. This reasoning-based retrieval augmented generation (R
"RAG-Anything: All-in-One RAG Framework"
RAG-Anything, a new "All-in-One RAG Framework," recently garnered over 14,600 stars on GitHub, signaling a significant shift in how developers process and query complex documents. This open-source tool is designed to move beyond text-only retrieval-augmented generation (RAG) by seamlessly integratin
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Hands-On LLMs: Master AI with O'Reilly's Code Repo The official code repository for O'Reilly's "Hands-On Large Language Models" book, by authors Jay Alammar and Maarten Grootendorst, is rapidly becoming a vital resource for developers navigating the complex world of AI. With over 24,500 GitHub star
OpenClaw-RL: Train any agent simply by talking
OpenClaw-RL transforms how developers train AI agents by allowing continuous optimization directly from natural conversations. This innovative framework decouples agent operations into independent asynchronous loops, enabling real-time learning without interrupting user interaction. It offers a self
This repository contains a curated collection of 300+ case studies from over 80 companies, detailing practical applications and insights into machine learning (ML) system design. The contents are organized to help you easily find relevant case studies based on industry or specific ML use cases.
ML System Design: 300+ Case Studies Curated A new GitHub repository, "A-Curated-List-of-ML-System-Design-Case-Studies," offers an invaluable resource for machine learning engineers, compiling over 300 real-world case studies from more than 80 leading companies. This collection provides practical in
Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig
NullClaw emerges as a groundbreaking, fully autonomous AI assistant infrastructure, designed for unparalleled efficiency. Built in Zig, its static binary is a mere 678 KB, booting in under 2 milliseconds and consuming only ~1 MB of RAM. This allows sophisticated AI agents to run on virtually any har
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀
ZeroClaw Unleashes Ultra-Efficient AI Assistant for Any Device A new open-source project, ZeroClaw, is disrupting the personal AI assistant landscape by offering a fast, autonomous solution designed to run on minimal hardware. This Rust-powered infrastructure enables a fully customizable AI assista
MCP Toolbox for Databases is an open source MCP server for databases.
Generative AI agents can now seamlessly interact with complex databases, transforming how developers manage and query data. The MCP Toolbox for Databases, an open-source server developed by Google, simplifies this integration by handling intricate tasks such as connection pooling and authentication.