2026 年 10 月 23 日

Reverse engineer anything with agents, from app behavior down to native binaries.

在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap.

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

PhotoCraft: An open-source, photo editor written by scratch in pure Rust

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

An agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D effects.

Write HTML. Render video. Built for agents.

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

A growing collection of viral videos made with Claude Opus 5.5 and the prompts behind them. Watch each original next to a live remake on Skillry. Updated regularly.

Ghidra is a software reverse engineering (SRE) framework

Official, Anthropic-managed directory of high quality Claude Code Plugins.

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

DroidDeck brings the SteamOS experience to Android

The open-source app everyone uses to manage agents at work

A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

OpenShell is the safe, private runtime for autonomous AI agents.

紫微斗数开源排盘引擎 — 基于倪海厦《天纪》体系，含完整排盘算法、四化系统、格局知识库、古籍原文数据

claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.

Official, Anthropic-managed directory of high quality Claude Code Plugins.

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

The open source coding agent.

Open-source Grok Bot alternative. Choose your own model and sandbox.

Ghidra is a software reverse engineering (SRE) framework

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

The PHP Interpreter

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Node.js JavaScript runtime ✨🐢🚀✨

Reverse engineer anything with agents, from app behavior down to native binaries.

Cursor plugin specification and official plugins

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

Write HTML. Render video. Built for agents.

Debloat any Android or Google TV over Wi-Fi and get an Apple TV-style home.

A fast, ad-free home screen for Google TV, LG webOS and Samsung Tizen. One button to undo.

One 8 KB skill that replaces REA (Reverse Engineer Anything): plain CLI tools, no MCP. Benchmarked: 38% faster, 35% cheaper.

让你的agent一键直出商业级产品宣传片：会作曲，能指着画面改。Commercial-grade launch films by your coding agent — point at the frame to change it.

Make an old Android TV fast again with Claude Code or Codex: a tiny ad-free home screen plus the prompt to clean it up

CVE-2026-109618/109619 — 5 RCE chains + detection rules (Suricata, Sigma, ModSecurity). PHP session.upload_progress pre-auth exploit research.

A php2shell exploit that requires no modifications to the official version, and does not require display_errors or limit_memory.

Proof-of-Concept (PoC) exploit for php2shell (CVE-2026-109618 / CVE-2026-109619), demonstrating remote code execution in vulnerable PHP environments. For security research and educational purposes only.

The 100% Pure x86-64 Assembly Systems Language

A tool to generate normal maps from any sprite and animated sprite sheet.

数学（小学到高中）、英语（三年级到高中）、初中物理的知识图谱：1644 个知识点、2403 条先修边、6723 道题，对齐课标，附自适应前置诊断。

Take the ads, tracking and clutter out of your Fire TV over ADB, no root. Every step can be undone. Comes with its own open-source home screen.

Official repository for MemT-1.0

⚡ The fastest open-source AI gateway — one Rust binary with a built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more.

Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux

🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac и сервере — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, агенты, fine-tuning, лучшие фишки

AI Roadmap 2026: a beginner's path through Foundations, LLM Engineering, Agents, Evaluation, and Production, with verified free resources and a mini-project per layer

A self-hosted AI gateway for enterprises. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

DeepSeek-V4.1-Flash-1017 EXL3 2.9bpw on 2x NVIDIA DGX Spark (GB10) with TensorFold: 2.1-2.3x the vLLM kit's decode speed.

AI chat app with unified access to 500+ LLMs via OpenRouter, Clerk auth and a terminal-style interface.

High-performance Roblox aimbot with adaptive smooth tracking and precise auto aim. Fully configurable, works with most executors, clean modular structure. Easy setup for current Roblox version.

Build a video template once, reuse it across coding agents. Editable Remotion templates and an Agent Skill for Claude Code, Codex and 25+ agents.

Native Quiet Home launcher, reversible cleanup tools, and an agent-readable guide for the Samsung U8000F running Tizen 9.

Operational information regarding the 2026 php2shell vulnerabilities

OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.

Transplant all the games to the web platform

AI 实时直播间：Vidu S2 实时数字人 + 弹幕过滤调度 + 衣柜换装 + OBS 叠层（角色资产不含）

Keeps AI coding agents such as Claude Code, Codex, GitHub Copilot, Gemini CLI and Cursor to the least code that does the job and still works.

Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.

AGENTS.md contract for AI coding agents + zero-dependency linter + SessionStart hook. Works with Claude Code, Codex, Cursor, Copilot.

Published: 2026-10-18

Self-hosted decision model (selfjev-4b) with a Jev-compatible API: Python SDK, server, fine-tuning and RLCD.

Game development plugin for Hermes Agent: sound effects, music, NPC voices, pixel art, 3D models, Godot/Unity/Blender/Unreal, a playtester that actually plays the build, and one-click export.

Fast, local, read-only MCP Server for WeChat (4.x/3.x) & DingTalk (7.x V2/V3) chat history with FTS5 search

llama.cpp fork that abliterates at inference

轻量的 Electron + Vite + Vue 3 + TypeScript 桌面应用模板，不依赖第三方集成插件 | A lean Electron + Vite + Vue 3 + TS desktop app template

Open-source template for "one photo → AI video that follows a viral template" SaaS sites, one site per trending keyword. Cloudflare Workers + D1/R2/KV/Queues, TanStack Start + Hono, Google sign-in, credit packs (Waffo/Dodo), fal.ai video generation, admin console.

Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md / CLAUDE.md.

A lightweight, fast, and minimal code syntax highlighter.

The source code of the https://speed.skk.moe

Terraria 1.4.5.8 Web Rewrite, using GLM-5.3-Flash and GLM-5.3

随手记，本地日记小工具

Open source software to control laser cutters and engravers. No install needed

A coding agent you run on your own machine, with the models you choose: desktop (Linux, Windows), headless server and Android, with signed self-updates.

Headlamp plugins for Kubernetes: Cilium, Gateway API, Envoy Gateway, Agent Router, Inference Hub (KServe, llm-d, vLLM), Prometheus Operator and Open Cluster Management.

Qwen3.8-Flash-Next (W4A16) on 2x NVIDIA CMP 170HX with vLLM pipeline parallel: 226 tok/s single-user, 840 tok/s at 8 users, 262K context, HumanEval 157/164

Deterministic bytecode VM for agent execution - verified images, snapshots and a hash-chained replay journal

Incremental rust builds up to 92x faster than cargo/rustc

The harness of Open Math OS, infrastructure for Math 2.0. Built for everyday math research.

Spotify on Linux in ~60 MB: Spotify's official Soloist player as an MPRIS player, so bars, media keys and playerctl just work.

Learn to sing the songs you love. A free, open-source singing trainer for Mac that listens to the music you play.

Local security intelligence for CVE triage - 39 data sources and 36 tools, risk scores and an MCP server for AI agents, all in native Rust. Private by default.

A native launcher for rooted LG webOS TVs, inspired by Apple TV.

Fast, native SSH client for macOS, Windows and Linux (Rust, GPUI, libghostty-vt)

MixMusic: Spotify and YouTube Music in one player. Open-source desktop music player for macOS, Windows & Linux: one search, one queue, mixed playlists, synced lyrics, and equalizer with community themes and plugins.

Evidence-based PHP security assessment: patch verification, intrusion tracing, and offline reports.

Scanner for PHP2Shell (CVE-2026-109618/109619): URL blackbox, local device and SSH.

免選字的注音輸入法：在本機用 Transformer 看前文選字。支援 Linux（Fcitx5／IBus）、macOS、Windows。

Self-hosted private websites for your team. Upload a folder of HTML and get a link only your coworkers can open, with a database, live updates, uploads and AI built in. An open-source take on Shopify Quick.

VC - AI-orchestrated coding agent colony

沿着好奇心继续发现 —— 本地优先的多平台内容聚合、阅读与笔记工具

Lossless speculative decoding for Apple Silicon (MLX): 2× faster Qwen3 generation on a Mac with a trained hidden-state drafter. MIT.

Run stock llama.cpp with the stock Unsloth Qwen3.6-35B-A3B 4-bit on a 16 GB Mac.

Deterministic local LLM engine and debugger — run GGUF models on your own GPU, get bit-identical output, and record, replay and compare runs. Written in 글(geul).

AI Engine RunTime, lite: language models and image generation on the NPU of AMD Ryzen AI processors

A readable NumPy inference loop: prefill, prefix recovery, verification budgets and speculative KV rollback

An offline, zero-dependency multi-node pipeline-parallel LLM inference broker. Pools heterogeneous consumer hardware (Apple Metal + NVIDIA CUDA) over ad-hoc local hotspot LANs with an integrated OpenAI-compatible API gateway.

DeepSeek-V4.1-Flash-1017 on two NVIDIA DGX Sparks (GB10) with TensorFold TP2: scripts, chat-template fix, speed and quality results

How many watts does your local LLM really burn? Live power, temperature and energy-per-token dashboard for Windows: llama.cpp, Ollama, LM Studio. No admin, no drivers, 0 dependencies.

Runs Hugging Face ONNX models on any Nx backend, with no per-architecture code

Fast qwen3-tts inference using RSI

DeepInfer: High-performance, large-scale inference framework for DeepSeek models