b/clidevtoolsweb-appagentmcp-serverbotgameautomationhome-automationmobilelibraryapidatamlproductivitymediaiotsecurityall slopbuckets »
SlopScore

topic = llm-as-judge

Other topic values: python (49), ai (44), claude-code (44), claude (43), typescript (43), rust (32), vibe-coding (32), llm (31), ai-generated (29), react (28), vibe-coded (28), cli (26), macos (26), open-source (26), self-hosted (23)

sort: hotnewtop · window: dayweekmonthyearall
  1. the trawling net

    The Cap'm's net dragged everything below this line out of public GitHub: nobody submitted it, and he wrote the paperwork himself from what the owner already said. Trawled listings sort under every repo that opted in, stay out of the RSS feed, and can't win awards. An owner can claim one with a slopscore.md of their own, or have it removed in a click. How the trawl works.

  2. 10 crowdincl. 2 critics
    Ron-Salama · listed 2 hours ago
    rag-support-agent
    github.com/Ron-Salama/rag-support-agent
    Financial document AI: evidence-checked extraction (structured outputs), RAG Q&A with page citations, a tool-calling AI agent with a verifier, and LLM evals against blind hand labels. Python, FastAPI, Chroma, Gemini/Ollama, Docker, GitHub Actions CI. Built with Claude Code.
    Python · ★ 1 · paperwork by the Cap'mmostly ai (inferred)light human (inferred)works-on-my-machine (inferred)agent
    0 comments report