2026 年 10 月 25 日

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

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

Orca is the place for working with a fleet of agents (e.g. Grok Bot, Claude Code). Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

Free, open-source file converter. Convert 255 formats offline by drag & drop — images, PDF, Word, Excel, PowerPoint, HWP/HWPX, video, audio, e-books and archives. No upload, no Office needed.

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.

Write HTML. Render video. Built for agents.

SolidCraft: an open-source parametric 3D CAD application built in pure Rust. Desktop, web, and automation through MCP.

The open source coding agent.

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.

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.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

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.

A toolbox of film styles made in code for Claude Code: 59 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. · 一套用代码做片的风格工具箱：59 种现成风格，也能做出你自己的

Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。

Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

The design language that makes your AI harness better at design.

TradingAgents: Multi-Agents LLM Financial Trading Framework

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

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

Universal SEO skill for Claude Code. 26 sub-skills + 19 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, agent readiness (Lighthouse Agentic Browsing, WebMCP, llms.txt), backlinks, local SEO, e-commerce, international SEO, Google APIs, and PDF/Excel reporting. 9 optional extensions for live SEO data.

🌊 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

Vibe code with pi in a lightweight, real IDE that customises itself around the way you work — The Vibe You Need

Ghidra is a software reverse engineering (SRE) framework

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

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

A Tiny biped duck robot 🦆

An open-source, self-hostable PaaS alternative to Vercel, Heroku & Netlify that lets you easily deploy static sites, databases, full-stack applications and 360+ one-click services on your own servers.

Write HTML. Render video. Built for agents.

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

Cursor plugin specification and official plugins

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

11 Claude skills for day trading: scan thousands of charts, track breaking news, time every entry and exit, and replay every outcome before you risk a dollar.

Import .sql files into TypeScript with full type inference and zero codegen.

Official Inference Code of EAGLE-4

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.

HatchZip is a free, open-source archive extractor for Windows, macOS and Linux that extracts ZIP, 7z, RAR, tar and split archives in place, so it needs free space for the extracted files only. Desktop app and CLI.

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

Stream any torrent, video or audio, and skip to any moment in about a second. Free, open-source desktop app for Windows, macOS and Linux. No servers, no accounts, no telemetry.

给国产电视的一块干净桌面：参照 tvOS 设计的开源 Android TV 桌面，没有广告，开机自动接管。A tvOS-style launcher for Xiaomi, TCL and other China-market TVs.

REAP - Prompts for you to use REA (Reverse Engineer Anything), get the most out of it, and clone or break down any program

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

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]

A custom LLM inference engine for low-cost NVIDIA GPUs: Quadro K420 and K1200, two K1200s joined into one 8 GB card, GTX 1080 and RTX 3080. Runs Bonsai 2B, 4B, 9B and 27B models with an OpenAI-compatible server.

You type. It already knows. Local LLMs that read and think while you type.

AST-Aware, Personalized-PageRank-Ranked, Token-Budgeted Codebase Compressor for LLMs

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

DSV4.1-Flash-1017 SAGE EXL3 (1.62 bpw) on one DGX Spark with vLLM: DSpark MTP, cold-expert ATS alias, tile-K 16 MoE, memory guard, measured 31-34 tok/s

GLM 5.3 abliterated or uncensored API access with RouterHub. Browse 35 jailbreak prompt links, compare GLM models, and find SDK examples, coding-tool setup, pricing, and evaluation guides.

麦当劳自助管家 McButler — 基于麦当劳 MCP 的点单参谋：每日推荐 / 套餐健康体检 / 门店全成本比价 / 团餐智能配餐 / 麦险分信用评级 / 麦门小剧场。麦当劳 1024 程序员节参赛作品。

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.

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.

为 AI Agent 设计的哔哩哔哩命令行工具：扫码登录、看视频、评论、私信、发动态、投稿，全部 JSON 输出

Learn a codebase by re-deriving its design decisions yourself. A Claude Code skill.

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

基于麦当劳MCP的智能省钱助手

Static recompiler that turns Nintendo Switch executables into native PC programs, written in Rust.

Clean-room Nintendo Switch 2 (Tegra T239 / Horizon OS FW 23.0.1) Emulator Engine in Pure Rust

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

A native launcher for rooted LG webOS TVs

Rust web content engine: clean Markdown, incremental collections, isolated HTTP sessions and verified media archives. Firecrawl-compatible API.

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.

Rune: Native UI framework

Open-source, cross-platform AI quota monitor (Codex, Claude, Cursor and 47 more). Windows, macOS, Linux, Android and iOS. Built with Flutter.

DeepSeek 蓝色大肥鱼消除计划：识别并清理 B 站（Bilibili）评论区中由 DeepSeek 大模型、AI Agent 驱动的机器人账号（大肥鱼）的 Chrome / Edge / Firefox 浏览器插件。离线规则 + DeepSeek API 精判，AI 评论检测、空间主页鉴定、鲸鱼娘一键清场。DeepSeek AI bot detector for Bilibili comments.

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.

Arkdraw is an open-source diagramming app for creating flowcharts, UML, ER diagrams, network maps, wireframes, and mind maps with a built-in AI assistant that generates and edits diagrams from natural-language prompts.

AnythingLLM Desktop — The enhanced all-in-one AI desktop app.

Anything to API (万物皆可2API): put an AI agent, a script, or even yourself behind an OpenAI-compatible API

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

Agentic coding, in your control

反代本地：把 Converge/enter.pro 反代成本地 OpenAI / Anthropic 兼容服务，多账号池自动切号 · prompt cache · 工具调用 · 单页控制台。 | Local OpenAI/Anthropic-compatible proxy for Converge/enter.pro with multi-account pooling, prompt caching, tool calling and a web console.

麦当劳 × Rokid Glasses 眼镜点餐助手：一句话点餐、MCP直连、购物车管理与实时算价

M餐搭子：基于麦当劳 MCP 实时菜单与营养数据的智能搭餐 Skill｜在线演示已上线

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.

The ESP32-S3 bench guide as a React app: live pinout, lessons with interactive simulators, a code reader for the esp-labs firmware, and the bench log. In 8 languages, including Arabic (RTL).

Animated, steppable code explainers. Zero-dependency TypeScript, SVG output, browser and Cloudflare Workers.

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

The IDE you know, rebuilt in Rust. IntelliJ IDEA–style keymap, tool windows and search-everywhere in a fast native app: editor, code insight, debugger, Git, terminal, database and HTTP clients for 60+ languages.

Run a web page like a program

Self-hosted inbox for WeCom bots and WeChat customer service: durable files, searchable records, and independent Agent integrations.

Open-source AI alternative to Buffer and Opus Clip: Claude Code makes on-brand videos, posts them to 9 platforms and drafts replies. Self-hosted, your own keys.

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。

A native git diff viewer for macOS, with Codex-written commits and code reviews, built in Go with MyGo

A Go-based social Feed system featuring push/pull feed delivery and trending content discovery.

A local Go learning app with lessons, quizzes, and runnable practice.

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

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.

Minimal, educational continuous-batching LLM inference engine with Paged KV-cache, prefix caching, and speculative decoding for Qwen2.5 in pure PyTorch.

Qwen3.8-Flash-Next W4A16 on 2x CMP 170HX with Morrowmake's vllm-cmp170hx: full CUDA graphs and the n-gram table in RAM, made for old CPUs

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

Learn DeepInfer through a small, runnable inference engine. Follow the code on CPU, then run real Qwen3.5 models on Ascend 910C.

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

PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-correct), OpenAI-compatible local server, report and logs.

An O(N) CPU-first linear recurrence inference runtime — hand-written AVX2/AVX-512 kernels, multi-architecture support (SunnyNet / RWKV-7 / Mamba-2 / GLA / DeltaNet / HGRN2).

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.

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

Native OpenCL inference engine for Intel N100-class SoCs: EmbeddingGemma-2, LiquidAI d1-omni and LFM2.5 chat in one C++ binary, on the iGPU. Measured ~2x llama.cpp's own Vulkan backend on the same N100 (2.1-2.3x); OpenAI-compatible server, CPU fallback, bit-exact batch invariance.

Unlock FP/BF16 instruction issue rate on Nvidia 3000's cards to their professional equivalents

A team of long-lived bots for DeepSeek Harness, with main bots, bot-to-bot messages and group chats.

AI API 中转站评测排行与切换工具：实测可用率、延迟与价格 · Open-source AI API relay benchmark, rankings & switcher for Claude Code / Codex