Top Finds

🦀 The transformer is a brilliant hack scaled past its limits. DREX is what comes next — tiered memory 🧠, sparse execution ⚡, and a learned controller that knows what to remember 💾✨

🕵️♂️ Analyze and reverse engineer keyword filtering in large language models to enhance compliance and operational insights.

AI Agent Memory System with Soul, Bonding, and Semantic Search

A production-grade Deep Reinforcement Learning project solving the 3D Bin Packing Problem. It features DQN and PPO agents, a custom Gym environment, MLOps integration with MLflow and DVC, and a FastAPI service for inference.

Thoth - Personal AI Sovereignty

Google Maps–Inspired AI Traffic Route Guidance | Deep Learning + Heuristic Search | Real-World SCATS Data (Boroondara 2006)

多平台模型接入，可扩展，多种输出格式，提供大语言模型聊天服务的插件 | A bot plugin for LLM chat with multi-model integration, extensibility, and various output formats

:package: Boilerplate CLI app

AI assisted programming in Emacs with Aider

Automatically generates interactive API documentation for Rails by mapping routes, controllers, and models. Zero configuration—just install and go.

Skills to help AI Agents master the vvvv gamma ecosystem

Ontology-based MCP server that analyzes database schemas (PostgreSQL, Snowflake, ClickHouse, Dremio) and generates RDF/OWL ontologies with SQL mappings for fan-trap-free Text-to-SQL.

Share your Claude Code setup. Try anyone's in one command.

MarkdownFlow extends standard Markdown with AI to create personalized, interactive documents. Tagline: "Write Once, Deliver Personally"

Product feeds for 3rd partys like Google Merchant

A Terminal Application for Linux, Windows, and Mac

VRM Metal

A minimal, composable Go library for building AI agent applications.

Personal AI assistant chatbot and RAG built with FastAPI, SQLAlchemy, and Hugging Face LLMs. Clean architecture, rate limiting, and vector database support.

The AI Safety Gauge for Legal Contracts. ⚖️ Scans PDFs, detects predatory clauses, and scores risk using Llama-3 & Cosine Similarity.

Back up, restore, and manage custom Steam library artwork on SteamOS. Scan game collections, create Steam shortcuts, and download artwork from multiple providers.

:zap: Experimental prototypes

AgentHER: Hindsight Experience Replay for LLM Agents

🏎️ Train autonomous racing cars with DQN and PPO in a realistic simulator featuring custom physics, interactive track building, and side-by-side performance comparison.

Take a break while AI thinks If a reply takes too long, the extension opens your chosen break-site tab and brings you back when the answer is ready.