All AI Tools

blackwhite084/playwright-plus-python-mcp

使用 Playwright 的 Python MCP 服务器，更适合 LLM。

30 Seconds of Interviews

Short interview questions for developers

Medical Reasoning with Large Language Models: A Systematic Review and Evaluation (April 2026)

Comprehensive review of medical reasoning methods + MR-Bench (real-world hospital data); reveals large gap between exam-level performance and authentic clinical decision-making

Box

Box 官方集成，通过 Box AI 与智能内容管理平台交互。

furey/mongodb-lens

功能齐全的 MongoDB 数据库 MCP 服务器。

CreateAny.ai

No-Code / Low-Code

Instant Digital Product Creation with AI: CreateAny.ai

A Real-Time Operating System on the Raspberry Pi

A practical guide to RTOS on the Raspberry Pi

MSA: Memory Sparse Attention to 100M Tokens (2026)

End-to-end trainable sparse attention with linear complexity — scales to 100M tokens on 2×A800 GPUs with <9% degradation vs 16K baseline; Memory Interleaving enables multi-hop reasoning across scattered segments

grafana/mcp-grafana

Grafana 官方 MCP 服务器，让 AI 查询仪表盘、数据源、Prometheus / Loki 指标与告警，辅助可观测性分析。

Bare Metal Programming in C

Bare metal C programming for Raspberry Pi

Self-Propagating Attacks Across LLM Agent Ecosystems (March 2026)

Demonstrates how attacks can autonomously propagate across interconnected LLM agents — worm-like self-spreading malware targeting agent ecosystems via MCP, tool chains, and shared memory

In site learn

Free Interactive PHP Tutorial

Med-CAM: Minimal Evidence for Explaining Medical Decision Making (April 2026)

Minimal evidence extraction for medical AI explanations — identifies the smallest subset of input features sufficient for model decisions, improving interpretability without performance loss

PSEUDO.AI

Coding Assistants

Bridging Code Complexities with AI-Driven Simplicity.

DeepSeek Space Invaders

Games

Classic Space Invaders game built entirely with DeepSeek R1 AI assistance, demonstrating AI-powered game development.

Resilient

AI Chatbots

AI-powered mock interview coach

LPS-Bench: Long-Horizon Safety Benchmarking for Computer-Use Agents (2026)

Safety benchmark for browser/computer-use agents focused on long-horizon tasks where risk accumulates across many UI actions — useful for testing confirmation discipline, phishing resistance, and context drift

Survia

Forms & Surveys

Smart Survey Platform for Saudi Market

Can Large Language Models Self-Correct in Medical Question Answering? (April 2026)

Exploratory study of LLM self-correction in medical QA — finds reflection can both correct and introduce errors; analyzes error correction dynamics across multiple reflection steps on MedQA, HeadQA, PubMedQA

Digitap AI

Business Tools

Analyze creditworthiness smarter with Digitap AI. Use advanced APIs for credit scoring, risk assessment, and alternate data insights today.

Digiotouch AI

AI Chatbots

AI meeting assistant that sees every slide, hears every word, and translates in 130+ languages.

Waveform.ai

Forms & Surveys

Smarter surveys with AI voice forms