Skip to content
View Agwave's full-sized avatar

Block or report Agwave

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Agwave/README.md

👋 Hi, I'm Agwave(chenyinbo) | AI Agent & Knowledge Graph Architect

🤖 架构 AI 与图智能的未来 | Architecting the Future of Agentic AI

我是一名深耕 AI Agent 与 GraphRAG 系统构建的资深工程师。我专注于智能数据的全生命周期管理:从支撑海量异构数据的 高性能 ETL,到 图数据库 中的复杂关系建模,再到利用 LangGraph 编排多体协同工作流,从而交付具备行动力的洞察。

I specialize in the entire lifecycle of intelligent data: from high-performance ETL ingesting massive data, to Graph Modeling, and orchestrating multi-agent workflows to deliver actionable insights.

  • 🔭 核心聚焦 / Focus: 基于 LangGraph & MCP 构建自主 Agent,并由语义增强的 GraphRAG 驱动。
  • ⚡ 性能与规模 / Scale: 精通数据库 I/O 优化与分布式系统 (Kubernetes, Kafka)。
  • 🧠 工程落地 / Engineering: 致力于将 机器学习理论 (ML Theory) 转化为可扩展的工程实践。

🧰 技术版图 / Technical Ecosystem

根据数据问题的维度选择最合适的工具。Selection of tools based on data dimensions.

领域 / Dimension 技术栈 / Technologies
AI & Agent 编排 LangChain/LangGraph, MCP, Vector DBs, ML Theory
图与 NoSQL (核心) ArangoDB, Nebula Graph, Cassandra, Redis
关系型数据库 PostgreSQL, MySQL, Oracle
大数据与 ETL Kafka, HDFS, Hive, Impala
开发语言 / Lang Python (AI/DS), Go (High-perf Services)
前端与 UI Next.js, Tailwind CSS, shadcn/ui
基础设施 / Infra Docker, Kubernetes (K8s), CI/CD

🧠 AI 原生开发流 / AI-Native Development Workflow

我利用前沿的 AI 编程智能来加速开发并确保代码质量。 I leverage AI intelligence to accelerate development and ensure code quality.

Cursor Claude GitHub


📈 数据统计 / GitHub Stats

Your GitHub stats Top Langs


📍 Based in Shenzhen, China | 欢迎关于 Graph-AI、智能 ETL 和 Agentic RAG 的技术交流与合作。

Pinned Loading

  1. PDF-Resume-Information-Extraction PDF-Resume-Information-Extraction Public

    天池比赛作品整理。实现从pdf中提取出姓名、出生年月、性别、电话、最高学历、籍贯、落户市县、政治面貌、毕业院校、工作单位、工作内容、职务、项目名称、项目责任、学位、毕业时间、工作时间、项目时间共18个字段。

    Python 113 26

  2. bilibili-publish bilibili-publish Public

    跨 WSL2/Win11 的 B站投稿自动化:WSL2 里跑 Playwright,经 CDP 接管 Win11 浏览器,自动填标题/简介/分区/标签/封面并提交

    JavaScript

  3. smart-flow-v2 smart-flow-v2 Public

    基于 Agents 和 RAG 的智能售后客服

    TypeScript

  4. llm-wind llm-wind Public

    日 Token 用量观察:拉取榜单、日环比分析、Markdown 报告、企业微信推送

    Go 1

  5. domain-wind domain-wind Public

    Daily domain-invest hot-word watcher: RSS → surge analysis → WeCom report + candidate .com check

    Go