详解 MCP 传输机制
MCP传输机制详解
Look Twice: Training-Free Evidence Highlighting in MLLMs (April 2026)
Inference-time framework exploiting MLLM attention patterns to identify relevant visual regions and text, then re-conditions generation on highlighted evidence — consistent VQA improvements, no training required
TapTap
I suggest games you'll love! by [Dash Huang](https://x.com/DashHuang/)
AI Content Generator | emaildojo.io
Writing AssistantsTransform Your Text into Structured, Readable Content
MyThinkingCap
EducationMyThinkingCap is an AI-powered study tool that helps students learn faster with instant explanations, summaries, and personalized tutoring.
RAG Web Browser
Apify 开源工具，执行网页搜索、抓取 URL 并以 Markdown 格式返回内容。
Agent-Memory-Paper-List
Curated papers on memory architectures for LLM agents — long-term, short-term, attention mechanisms (2026) 
Muvon/octocode
Rust 编写的语义代码索引器，构建代码库 GraphRAG 知识图谱并通过 MCP 暴露给 AI 代理。支持 13+ 语言，提供 tree-sitter 解析、ast-grep 结构化搜索和代码签名视图。
Dating with Raiden Shogun
Go on a date with Raiden Shogun and please be nice.
EpiBench: Multi-turn Research Workflows for Multimodal Agents (April 2026)
Benchmarks multimodal agents on episodic scientific research workflows — literature search, figure extraction, cross-paper synthesis; built on smolagents with persistent memory and tool use
jae-jae/fetcher-mcp
使用 Playwright 无头浏览器获取网页内容，支持 JS 渲染和智能提取 (Markdown/HTML)。
isnow890/naver-search-mcp
Naver 搜索 API 集成 MCP 服务器，支持博客、新闻、购物搜索和 DataLab 分析功能。
yzfly/mcp-python-interpreter
安全、标准化的 Python 环境，支持代码执行、环境和包管理。
Zlatanwic/wechat-article-read-mcp
支持微信公众号内容提取，绕过微信反爬机制
Rubrics to Tokens: Token-Level Rewards for Instruction Following (April 2026)
Rubric-based RL with Token-Level Relevance Discriminator — solves credit assignment for instruction following by predicting which tokens satisfy specific constraints; fine-grained optimization
The Infinite Conversation
Conversational AIExplore Endless AI-Generated Dialogue Between Herzog and Žižek
VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models (April 2026)
First unlearning method for VLA models — removes target behaviors while preserving general capabilities; introduces forget/retain/boundary splits and real-robot OXE benchmarks
Schema Key Wording as an Instruction Channel in Structured Generation (April 2026)
Discovers that schema key wording itself acts as an implicit instruction signal under constrained decoding — changing JSON key names alters model behavior even when semantic content is identical
LongCLI-Bench: A Benchmark for Long-Horizon Agentic Programming in the CLI (2026)
Benchmarks terminal-based coding agents on long-horizon programming tasks that require sustained planning, repo navigation, debugging, and recovery over many steps instead of single-fix patches
EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development (April 2026)
Conversational framework for embodied AI development — batch simulation environment synthesis, automatic scene creation, controllable scene editing, and workflow execution via natural language
CalmrioAI
Mental Wellness AssistantsYour trusted emotional support companion, right at your fingertips.
TotemoTech
New AI ToolsTotemoTech: Your Daily Tech News from Japan in 2-Minute Bites
BlogBud AI
Blog WritingAI-powered SEO-optimized article generation at scale
Me.bot for Android
AI ChatbotsYour Second Me, Speaking for You