2026 年 10 月 21 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.

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

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

Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.

Write HTML. Render video. Built for agents.

Ghidra is a software reverse engineering (SRE) framework

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.

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

DroidDeck brings the SteamOS experience to Android

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.

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub:https://clianything.cc/

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

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

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

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

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.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

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

The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

Ghidra is a software reverse engineering (SRE) framework

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Kronos: A Foundation Model for the Language of Financial Markets

freehire — the open-source search engine for job seekers

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

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.

Cursor plugin specification and official plugins

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

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

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. Open source, built with Claude Code. One button to undo.

Ears for coding agents: let AI hear, review and make sound. CPU-only, open source.

Turn your regular JavaScript code into a neural net.

Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.

CVE-2026-63030 + CVE-2026-60137 exploit RCE chain.

中小学知识图谱 + 前置诊断：数学（一–九年级、高中必修与选择性必修）+ 英语（小学、初中、高中），课标对齐、人教版，1503 知识点、6159 题、自适应诊断

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.

Uncharted: The Nathan Drake Collection running natively on Windows - by SuperMedo

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

There is no official XScreenSaver GitHub repository.

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.

🐋 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

一个通过:多llm并发/实时线性算法/ai自动优化进行记忆体整理的多模态ai聊天助手

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.

Agent 式的 SillyTavern 角色卡酒馆：高缓存命中，兼容酒馆角色卡与世界书，自带配图和一键朗读，角色形象固定，引导式创作角色卡。An agent-style SillyTavern card player for your own LLM API.

Снайпер вакансий hh.ru: LLM-скоринг под ваш профиль, автопилот откликов в первые 10 минут после публикации (обгоняем ботов), статические письма с гвардом от галлюцинаций. Всё локально на вашем ПК, официальный API, Python.

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）

Convert and edit files with a liquid-glass radial menu: start dragging a file, press Shift, drop it on a slice. Windows, Mac and Linux.

一个微信机器人框架，目前稳定可用

Local video editing through conversation. Created by Matheus Gomes.

Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V example.

FL2/FL3 porting and custom LUT/DCP import tools for Sony A7C II (ILCE-7CM2) firmware 2.01, with backup, installation, readback verification, and restoration workflows. Includes single-camera test results and known limitations.

A faster, leaner fork of the superpowers workflow for Claude Code: one approval gate, parallel waves, routed models. 3.9x faster in benchmark at equal quality.

Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, llama.cpp, LoRA weight analysis with charts

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

AI 编程福利导航：汇总 Claude Code、Codex、Cursor 中转站与公益站，整理免费额度、注册福利、签到活动和评测记录，提供可视化看板与 Python 数据采集工具。

Zero-dependency Node toolkit: bulk-create n33.ai accounts, harvest session cookies and serve the 10 free models through 9Router as an OpenAI-compatible provider.

A local AI agent built from scratch in Python with Ollama: conversation memory, system prompts, and multi-step tool calling.

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

全网最全的 AI 破甲合集：一个仓库破甲所有模型。收录 1733 个上游破甲项目，9 条可一键安装的破甲卡覆盖 GPT/Claude/Gemini/DeepSeek/GLM/Kimi/Grok/Qwen 与本地模型，内置 llms.txt 让 Claude Code/Codex/Cursor 自己装 有用的话可以点个收藏星星，会持续收录

一个会主动发现任务的智能体

Rust compiler daemon on rust-analyzer: fast incremental cargo builds and live edits to running programs. Try: nix run github:indexable-inc/ra-jit

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

A fast, multi-threaded Redis® and Valkey alternative written in Rust: drop-in compatible, with full-text and vector search built in

The chat app that doesn't eat your PC. A lightweight, native Discord client in Rust.

Local security intelligence for CVE triage - 38 data sources and 36 tools, risk scores and an MCP server for AI agents, all in native Rust. Private by default.

A terminal on GPUI and Ely components

Analyze the Indonesian stock market (IDX/IHSG) from web terminal, CLI, or any AI agents via MCP server. IHSG Prices, Fundamentals, and Screening. Free and No API keys required. Changelog: https://github.com/fzn0x/idx/blob/main/CHANGELOG.md

PandaCode: a calm desktop workspace for coding agents

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.

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

Turn requirements into UML diagrams, test cases and editable Word specs—with traceability. Self-hosted, bring your own AI model. Built for capstone and course projects.

随手记，本地日记小工具

研迹 Trail｜本地优先的 AI 投资研究工作台。连接行情、K 线与深度研究，让判断可追溯、风险可复核。Local-first AI investment research desktop with an evidence-grounded copilot.

A lightweight design agent built with libfx. Describe a page and an agent writes it as one HTML file.

Slidev-style presentations written in markdown, compiled with Angular. The core app and the slide-ng command line.

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. No Spotify Premium needed.

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。

Open-source, auditable network gateway for homelabs, NAS and servers: DDNS, STUN traversal, port forwarding with SNI routing, reverse proxy and web server, ACME certificates, WAF, Tailscale, frp, Cloudflare Tunnel, Docker and web terminal in one binary. Runs on Docker, fnOS, OpenWrt, Linux, macOS, Windows; imports Lucky configs.

Private Keys

Recommend AI coding harness changes from repository context and coding signals, then distribute approved rules, skills, hooks and agents to selected people or teams. Pair with Agent Desk through your ingestion adapter; use audience targeting for manual test/control rollouts.

The open TMS built for AI

qwen2API çok dilli (i18n) fork'u • Multi-language (i18n) fork of qwen2API — WebUI artık Çince, İngilizce ve Türkçe / UI now in Chinese, English & Turkish. Orijinal / Original: YuJunZhiXue/qwen2API

Browserless Chrome uTLS + HTTP/2 OpenAI-compatible API daemon for Google Gemini Web (/v1/chat/completions & /v1/responses)

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.

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

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.

Fast qwen3-tts inference using RSI

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

GPU scheduler for Linux

One-command recipe to serve nvidia/Qwen3.8-Flash-Next-FP4-Local on a single NVIDIA DGX Spark with vLLM (OpenAI-compatible API).

Qwen3.8-Flash-Next on 2× NVIDIA CMP 170HX with vLLM: up to 152.8 tok/s single-user, up to 674.7 tok/s at 8 users, 262K context, one-command container install

Learning repo and future reference, following Build a Large Language Model (From Scratch) by Sebastian Raschka.

The curation of most useful ChatGPT Plugins - Free and Open Source

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.