Research & Data

Explore a full source snapshot of Claude Code for TypeScript analysis, file mapping, and MCP-based code research

A production-style ChatGPT-like enterprise assistant using Azure, Databricks, and OpenAI for grounded document Q&A, agent workflows, memory, and MLflow-based evaluation.

Out-of-the-box enterprise context brain for AI agents — Graph RAG, WebGL 3D console, one-click Docker deploy

Analyze Claude Code source leaks, map the architecture, and document its TypeScript, Bun, agent, and security systems.

Go/Golang multi-agent LLM framework — ReAct loops, parallel tools, streaming, sub-agent

8-phase literature-review pipeline. 7 federated sources, dedup, ranked retrieval, citation chasing, self-critique, 5 report archetypes.

Straightforward LLM dependency orchestration for multi-agent workflows. Compose chat, code, and data into declarative pipelines in YAML. Export AI workflows as a single binary, ISO, Docker or Kubernetes pods. Use ollama, llmfile, or any cloud AI providers.

Manage project.md files using a single CLI tool to track tasks and coordinate work between humans and AI agents without databases or external services.

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.

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.