Skip to content
View wzltmp's full-sized avatar

Block or report wzltmp

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

Popular repositories Loading

  1. rag-eval-harness rag-eval-harness Public

    End-to-end RAG over Paul Graham essays with a hand-curated eval harness — pgvector, cross-encoder rerank, LLM-as-judge scoring. Includes A/B/C eval results and discussion of why rerank didn't help …

    Python

  2. langgraph-research-agent langgraph-research-agent Public

    Stateful research agent: LangGraph + Tavily + Claude. Plans, searches, reads, drafts, self-critiques. Eval harness vs Sonnet+web_search baseline.

    Python

  3. mcp-automations mcp-automations Public

    Production-grade MCP server (FastMCP, Pydantic-typed tools, Resources, Prompts) with Claude Desktop + Streamlit playground integration. Deployable to Fly.io.

    Python