Skip to content
View My-Denia's full-sized avatar

Highlights

  • Pro

Block or report My-Denia

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

Pinned Loading

  1. CloseScreen CloseScreen Public

    Maintained community fork of OpenScreen: a free, MIT-licensed screen recorder and editor. Windows capture runs on a Rust WGC/WASAPI/Media Foundation backend by default, with a packaged legacy C++ r…

    TypeScript 1

  2. uegame uegame Public

    WARDENFALL — a seeded action-roguelite vertical slice on Unreal Engine 5.8, built agent-first under evidence gates. Three procedural floors, Executioner/Tempo/Bulwark builds, risk/reward room contr…

    C++

  3. wasm-zero wasm-zero Public

    Zero-dependency Wasm 2.0 interpreter in Rust. Full official test/core at wg-2.0: 54,006 commands, 52,915 PASS / 0 FAIL / 1,091 UNSUPPORTED (text-format method boundary). Fail-closed CI accounting; …

    Rust

  4. wuwa-translate-bot wuwa-translate-bot Public

    Self-hosted Wuthering Waves terminology translator: dictionary-first official CN<->EN term lookup and term-locked sentence translation, served by a Telegram bot and a versioned HTTP API with revoca…

    Python

  5. agent-choice-bench agent-choice-bench Public

    Offline, interview-oriented Agent technical-choice benchmark: 15 frozen A/B cells (A1–F2) over 36 arms — memory, LTM routing, tools, LangGraph orchestration, similarity, observability. External-onl…

    Python

  6. rag-production-hardening rag-production-hardening Public

    Offline-first RAG evaluation bench on a synthetic corpus: frozen datasets, sealed confirm-only holdout, 10 pre-registered arms, external-judge metrics (no LLM-as-judge), multi-stage process-kill re…

    Python