Skip to content
View xianyu-sheng's full-sized avatar
🎯
Focusing
🎯
Focusing
6 followers · 2 following
  • CQUPT
  • Chong Qing
  • 09:02 (UTC -12:00)

Achievements

Achievement: Pull SharkAchievement: Pair ExtraordinaireAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: Pair ExtraordinaireAchievement: YOLO

Highlights

  • Pro

Block or report xianyu-sheng

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.

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
xianyu-sheng/README.md

Hi, I'm Xianyu Sheng 👋

M.S. student at CQUPT, building practical AI agents and developer tools.

重庆邮电大学硕士研究生，关注 AI Agent、代码智能与开发者工具工程化。

Featured work

Xenon

A terminal AI coding agent with DeepSeek V4 support, native tool calling, multiple execution engines, MCP integration, permission-gated tools, and a focused TUI. The project includes an automated test suite and documented end-to-end verification.

SmartBench

An evidence-grounded code-diagnosis workbench that combines static analysis, repository context, and multi-agent review. The current focus is making findings reproducible and evaluating diagnostic quality against labeled cases.

Agent-hub

A multi-agent orchestration project exploring intent routing, DAG scheduling, and collaboration strategies.

resume-sync

A developer workflow that turns repository activity into reviewed LaTeX résumé updates and PDF builds.

Open-source contribution

Technologies

Python · C++ · Go · TypeScript · LLM Agents · MCP · DeepSeek

Pinned Loading

  1. Xenon Xenon Public

    Local multi-model AI Coding Agent CLI with ReAct, Plan-Execute, MCP tools, memory & TUI. 本地多模型 AI 编程助手命令行工具。支持 DeepSeek/OpenAI/Claude/Gemini 等模型。

    Python 3 1

  2. SmartBench SmartBench Public

    Evidence-grounded code diagnosis with structural parsing, retrieval, and multi-agent review

    Python 1 1

  3. resume-sync resume-sync Public

    Auto-detect Git commits → LLM generate resume bullets → update LaTeX → compile PDF. Git 提交自动同步到 LaTeX 简历，求职不再手动改简历。

    Python

  4. Agent-hub Agent-hub Public

    Multi-Agent orchestration system with LLM intent routing, DAG scheduling & 7 collaboration strategies. 多 Agent 中央调度系统 — 自然语言输入，自动路由到专业 Agent 协同工作。

    Python