Skip to content
@lyshark

LYSHARK

LYSHARK ® It is an information security industry portal website headquartered in Beijing, with a brand trademark international classification of Class 41
image

Brand Introduction

Founded with a core focus on cutting-edge technical fields including security operation & maintenance, secure development, cybersecurity, reverse engineering and underlying system technologies, the brand is a professional Chinese technical team specializing in low-level security and open-source technology.

The team has long been committed to cybersecurity research, open-source tool development, technical knowledge accumulation and industry talent cultivation. Adhering to the development philosophy of independent technology development, open-source sharing and in-depth research on underlying technologies, it consistently delivers high-quality technical articles, open-source projects, hands-on tutorials and industry-specific solutions.

Rather than chasing fleeting industry fads, we concentrate on in-depth fundamental technology research. Rooted in solid technical capabilities and an open-source mindset, we deliver dependable technical support and a learning & communication platform for individual developers, cybersecurity practitioners, university research teams and enterprise clients.

Business Scope

  • Penetration testing and offensive & defensive cybersecurity research
  • Binary reverse engineering analysis
  • Kernel development, underlying system principle exploration and vulnerability research
  • R&D of open-source security tools, as well as maintenance of script libraries and technical frameworks
  • Compilation of technical documents, structured tutorials and systematic knowledge architecture
  • Customized technical consultation and solution services for enterprise cybersecurity

Team Philosophy

Centered around the core values of concentration, in-depth research, open source and knowledge sharing, we uphold technical authenticity and the spirit of free open sourcing. We strive to lower the entry barrier for cybersecurity learning and build a sound industrial technical ecosystem.

Official Portal

Official Website: https://www.lyshark.com
Contact Email: admin@lyshark.com

Open Cooperation

We welcome technical exchanges, project partnerships and joint open-source development, as well as learning interactions. Fellow industry experts and tech enthusiasts are invited to communicate and grow alongside us to jointly advance the development of the cybersecurity technology ecosystem.

Copyright Introduction

Copyright registration for all brand-related works is solely intended to guard against unfair infringing practices such as third parties maliciously registering copyrights to file counter-complaints and abusive rights claims, so as to ensure the stable operation and normal dissemination of the project. Upholding the core spirit of openness, sharing and open source inherent to the internet, this project warmly welcomes technical practitioners from all over the world to co-build and iteratively improve it. We look forward to refining technical solutions together with industry peers to jointly advance technological innovation and upgrade the industrial ecosystem.

In addition, we sincerely welcome suggestions, feedback and optimization ideas from all parties. All reasonable comments will be carefully reviewed, promptly followed up and addressed, driving continuous iteration and improvement of the project.

Pinned Loading

  1. LyScript LyScript Public

    An AI driven debugging assistant specially designed for x32/x64dbg, it helps to double the efficiency of reverse engineering, vulnerability mining, and malware analysis, making it your intelligent …

    C 79 13

  2. IDA-Moles IDA-Moles Public

    A static reverse analysis interface specifically developed for IDA Pro, supporting users to independently develop MCP servers and interface with large models, as well as Cherry Studio client usage,…

    C 8

  3. BinSentry BinSentry Public

    A binary debugger interface designed specifically for AI agents, with a total of 436 functional implementations, covering the entire dynamic debugging process.

Repositories

Showing 10 of 218 repositories
  • LyScript Public

    An AI driven debugging assistant specially designed for x32/x64dbg, it helps to double the efficiency of reverse engineering, vulnerability mining, and malware analysis, making it your intelligent copilot.

    lyshark/LyScript's past year of commit activity
    C 79 GPL-3.0 13 5 0 Updated Oct 2, 2026
  • BinSentry Public

    A binary debugger interface designed specifically for AI agents, with a total of 436 functional implementations, covering the entire dynamic debugging process.

    lyshark/BinSentry's past year of commit activity
    0 GPL-3.0 0 0 0 Updated Oct 2, 2026
  • MysticMirror-LLM Public

    玄鉴(Mystic Mirror LLM)大语言模型,一款自主知识产权的大模型源码

    lyshark/MysticMirror-LLM's past year of commit activity
    Python 0 GPL-3.0 0 0 0 Updated Sep 23, 2026
  • dify Public Forked from langgenius/dify

    Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

    lyshark/dify's past year of commit activity
    TypeScript 0 25,405 0 0 Updated Sep 21, 2026
  • Linux-mcp Public

    专为 Linux 开发的 AI 运维连接器,基于 MCP 协议打通 AI 与底层运维工具的交互,整合 SSH 远程执行、主机管理能力,无缝承接自主运维模式。

    lyshark/Linux-mcp's past year of commit activity
    Python 1 GPL-3.0 0 0 0 Updated Sep 21, 2026
  • colibri Public Forked from JustVugg/colibri

    Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

    lyshark/colibri's past year of commit activity
    C 0 Apache-2.0 4,287 0 0 Updated Sep 16, 2026
  • llama_index Public Forked from run-llama/llama_index

    LlamaIndex is the document processing platform for AI

    lyshark/llama_index's past year of commit activity
    Python 0 MIT 8,460 0 0 Updated Sep 12, 2026
  • ms-swift Public Forked from modelscope/ms-swift

    Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

    lyshark/ms-swift's past year of commit activity
    Python 0 Apache-2.0 1,731 0 0 Updated Sep 10, 2026
  • unsloth Public Forked from unslothai/unsloth

    Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

    lyshark/unsloth's past year of commit activity
    Python 0 Apache-2.0 7,254 0 0 Updated Sep 10, 2026
  • vllm Public Forked from vllm-project/vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    lyshark/vllm's past year of commit activity
    Python 0 Apache-2.0 23,186 0 0 Updated Sep 10, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.