Research & Data

GoodMemory 是一个面向 AI 应用的**可插拔用户记忆层**。 它不替代： - LLM - agent framework - 向量数据库 - RAG 系统 它专注解决一个更具体的问题： > **如何让任何 chatbox / copilot / agent / workflow assistant 在不重训模型的前提下，真正“记住用户”。** GoodMemory 的核心不是“存更多”，而是： - 记什么 - 何时更新 - 如何检索 - 如何压缩 - 为什么引用 - 如何删除 - 如何控制跨 agent / 跨项目 / 跨租户边界 它的本质是一个： > **Personal Context Engine / Memory Layer for AI Apps**

Claude Code based job search agentic workflow

Classify shell commands with AST analysis and risk scoring for AI coding agents

MCP server exposing Stockholm SL transit as AI agent tools — every response tagged with realtime / cached / stale_fallback / scheduled_fallback so the agent always knows how fresh its data is.

MCP server wrapping the Japan Patent Office API: query Japanese patents from Claude Desktop / Code / iPhone via 12 official tools + an isolated keyword-search tool.

Slash commands, mental frameworks, and prompt engineering resources for Claude Code — grounded in LLM research

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

Learn CLI agent architecture with practical notes and research on Claude Code and coding agents

Connect AI agents to MATLAB with expert workflows, idiomatic code, testing, and error handling for faster engineering and science tasks

Master the AI Engineer Stack: A professional-grade roadmap for Agentic Generative AI. Features Python, LangGraph, Multi-Agent workflows, Scalable RAG, Semantic Memory, and MCP integrations using LLMs from Hugging Face and OpenAI.

科研工作流 Claude 技能：覆盖选题、文献、方法、实验、写作、自审、Rebuttal、投稿九大阶段，支持 mentor / reviewer / mixed 三种模式（触发词含 reviewer mode、审查模式、mixed mode、混合模式），充当贴身导师与挑刺审稿人。

Enterprise Agentic RAG Security Copilot with guardrails, context engineering, memory, multi-agent workflow, MCP-style tools, evaluation, and observability.

Streamline CDK contributions with agent workflows, AWS tooling, and SOPs for faster issue analysis, PR authoring, and human review

Index Claude Code conversations into SQLite via hooks, with local LLM summaries and a search skill that lets Claude recall past sessions

Versioned AI development workflow standard for BDA teams: neutral commands, verification, feedback loop, Codex and Claude support

Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites.

Agentic Data Engineering framework with MCP server — local LLM orchestrates DE tools via ReAct loop

Stock research skill for AI agents — A-share, HK, US. Plan → fetch → validate → report.

Multi-agent orchestration system — Claude Code orchestrates Codex + Gemini as workers. Custom MCP servers, routing rules, safety guards, and research pipeline.

Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase and Serper, multi-engine search aggregation, structured JSON output, provider fallback, deduplication, and SearXNG alternative architecture for agent workflows.

Search Japanese laws & regulations via the official e-Gov Law API V2 — an Agent Skill for Claude Code / Cursor / Copilot. 日本の法令調査スキル。

A collection of advanced agent skills.

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: AI assistant, emerging agent runtimes, and production AI workflow patterns.

Run an open-source AI hedge fund on Claude Code with 45 trading agents, 147 MCP tools, and paper trading by default