Skip to content
View rayhpeng's full-sized avatar
  • China

Block or report rayhpeng

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
rayhpeng/README.md

Hi, I'm Ray Peng

Agent / LLM application engineer. 6 years of backend & AI engineering, now focused on enterprise agent systems.

What I work on

  • 🤖 Agent systems — agent gateway, multi-agent orchestration, declarative workflow engines, skill systems, MCP tool ecosystems
  • 📚 Vertical RAG — policy & academic-literature retrieval: hybrid search, reranking, structured knowledge modeling (LLM Wiki)
  • 🧪 Agent evaluation — golden datasets, Recall@K / AUC / NDCG, LLM-as-judge, trace replay, regression gating
  • 🏗️ AI-coding governance — hexagonal architecture with AST-enforced dependency rules, spec-first workflow, AGENTS.md conventions

Open source

DeerFlow (ByteDance's open-source multi-agent framework) — contributor:

  • Implemented the LangGraph Platform API in Gateway, replacing langgraph-cli single-process mode (#1403)
  • Unified persistence layer: event store, per-call token tracking, feedback, per-user isolation (#1930, #2134, #2153)
  • Runtime reliability: atomic run-creation persistence (#3152)

llm-space — sister project of DeerFlow: desktop tool for building, tracing, debugging and evaluating agents.

📫 penghui8411@gmail.com

@rayhpeng's activity is private