Skip to content
View HeiSir2014's full-sized avatar
🍋
🍋

Block or report HeiSir2014

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
HeiSir2014/README.md

HeiSir

Shanghai-based engineer — audio/video, realtime communication, and LLM infrastructure.

What I do

  • Building media stacks: streaming pipelines, players, WebRTC.
  • LLM application engineering: agents, tooling, on-device inference (Rust + Candle).
  • Currently exploring WebRTC × AI for next-gen RTC.

Stack

Languages   C++ · TypeScript · Rust · Python · Go

Media   WebRTC · FFmpeg · GStreamer · HLS · RTMP

AI   LangChain · LLM agents · Candle · MCP

GitHub

stats languages

Contact

heisir2012@gmail.com · heisir21@163.com

Pinned Loading

  1. M3U8-Downloader M3U8-Downloader Public

    M3U8-Downloader 支持多线程、断点续传、加密视频下载缓存。

    JavaScript 4.2k 562

  2. owt-client-rtc owt-client-rtc Public

    OWT-Client is a video conferencing client developed based on Electron and OWT JavaScript SDK.

    JavaScript 20 5

  3. git-aiflow git-aiflow Public

    🚀 An AI-powered workflow automation tool for effortless Git-based development, combining smart GitLab/GitHub merge & pull request creation with Conan package management.

    TypeScript 5

  4. hello-langchain hello-langchain Public

    langchain, langgraph, deepagent examples

    TypeScript

  5. sherpa-onnx sherpa-onnx Public

    Forked from k2-fsa/sherpa-onnx

    Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…

    C++ 1

  6. qwen3-tts-candle qwen3-tts-candle Public

    A Rust implementation of Qwen3-TTS inference powered by Hugging Face Candle, enabling fast and lightweight text-to-speech synthesis without Python dependencies.

    Rust 1