nmicic/int-llm-viz Visual anatomy of a Q16.48 integer GPT — four self-contained offline HTML pages: weight atlas, bit-exact inference trace, 32-D embedding space, 3-D weight explorer. Every displayed number is exact (BigInt in-browser, verified against the C oracle). Fourth in the int-llm series. GitHub · 47分钟前
matthews-wong/rag-eval-toolkit Offline evaluation toolkit for RAG pipelines: retrieval hit-rate, MRR, and answer-faithfulness checks. GitHub · 1小时前
matthews-wong/ai-gateway A lightweight LLM API gateway: multi-provider routing, response caching, retries, and token/cost accounting. GitHub · 1小时前
ahmedvnabil/deskswarm Self-hosted fleet of AI-controlled desktops — dispatch natural-language tasks to a swarm of real Linux desktops (not just a browser tab) and track results from one dashboard. Built on cua. GitHub · 1小时前
TGPSKI/run-watcher Build a live-render TUI that is the control center, debugging surface, and anomaly detector for a long-running job — or for a system that never stops. Seventeen design laws, each stated with the incident that produced it. GitHub · 1小时前
collinear-ai/reading-list The Collinear AI reading list: synthetic data, verifiers, agent environments, evaluation science, user simulation, and self-improving systems GitHub · 1小时前
ghayda-njaafreh/tetris-ai-lab AI-powered Tetris agent trained with video imitation learning, recovery training, verified augmentation, lookahead, and safety filtering. GitHub · 1小时前
saran-io/ugraph Turn a YouTube channel into a knowledge base an AI agent can navigate and cite. Plain markdown, no database, and every quote checked against its transcript. GitHub · 1小时前
zhouyu033/medical_AI_security_experimentcode_v2 [Version 2] OPEN AI Team Paper: A Unified Multimodal Privacy-Enhancing Framework for Secure Medical Data Processing in Large Language Models GitHub · 2小时前
ishandutta2007/Awesome-Masked-Language-Modeling a machine learning training method that hides random words in a text and teaches an AI model to guess the missing words GitHub · 2小时前
orlyjamie/internetcondom Protection against npm supply-chain attacks. One command: Socket Firewall on every package manager, minimum release age, ignore-scripts. GitHub · 2小时前
Sparkfetch/sparkfetch 🔥 Turn any URL into clean, structured, LLM-ready content. The open-source web fetching & extraction API. GitHub · 2小时前
creativoma/auto-claude A small, auditable bash loop that runs Claude Code unattended against a queue of tasks, gated by a verification command GitHub · 2小时前
