Havuz

Self-hosted AI buddy with visible memory: personal AI agent + Pi coding-agent workspace for any browser, phone or WeChat. 自托管私人 AI 助理：记得你，能办

Windows AI 桌面应用网络出口门禁：仅在约定代理出口放行 Claude、ChatGPT 等应用，出口异常即刻熔断并断网隔离。

An open-source UX research companion that runs inside Claude, ChatGPT or Gemini, from the first question to the final report.

PenEcho, el yazısı ve diyagramlarla çalışılan bir canvas üzerinde AI agent’larla görsel düşünme ve ortak üretim sağlayan bir uygulamadır.

Neden yükseliyor · 75 günde 2410 yıldız erken dönemde belirgin ilgiye işaret ediyor; görsel canvas fikrini MCP üzerinden Codex ve Claude Code gibi mevcut agent’larla birleştirmesi dikkat çekici. Ancak son 28 günde 5 commit ve 1 farklı yazar var; yıldızlar ilgi göstergesi olsa da aktif topluluk veya ürün olgunluğunu tek başına kanıtlamıyor. İlginin kesin nedenini bu verilerden belirlemek mümkün değil.

AIKON, Nokia Series 40 ve Symbian S60 telefonlarda Claude, OpenAI, Gemini ve Grok ile sohbet etmeyi sağlayan Java ME uygulaması ve Go sunucusudur.

Neden yükseliyor · 2007 model bir Nokia'da güncel AI modellerini çalıştırma fikri dikkat çekici ve gösterilebilir; repo 7 günde 314 yıldız almış. Son 28 güne ait commit ve farklı yazar verisi ölçülmediğinden geliştirme temposu ve katkı çeşitliliği hakkında kanıt yok.

Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs

vibe coding 的驾驶舱：左边文件，右边/下边终端，中间看清每一次改动。 / The cockpit for vibe coding: browse files on the left, command agents on the right, watch every c

One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's

霓虹天頂 — a rain-soaked vertical cyberpunk city you can fly through in the browser. three.js WebGPU + TSL, a Blender-baked Hong Kong night mark

Claude Code mods: 21 styles and a full set of features you turn on when you need them, for the terminal and the desktop app. · 一键为 Claude 换上

A GUI workbench for Claude Code and other CLI agents · Claude Code 的可视化工作台（网页 + 桌面），也能驱动 Codex / Gemini CLI / Qwen / OpenCode 等 CLI agent

A self-hosted workspace where people and AI agents work together

Always-on durable pi agent on your server that you talk to in Telegram. Survives crashes and restarts, keeps history in SQLite. pi-durable T

Reclaim disk space with an AI agent: measure top-down, group findings by risk, and delete only what you approve. Prompts in 7 languages. mac

Drive a real Telegram account from an MCP client: chats, messages, media, secret chats, communities, folders, admin rights, invite links and

Open-source AI interfaces built with Claude (Fable 5) including hero sections, GLSL shaders, design systems, animations, 3D components and

Record the talking head, Claude Code does the rest: the cut, the visuals, the voice, the sound effects, the thumbnail, and the YouTube uploa

Production-grade Claude Code and Codex skills for Spring Boot developers

Find out where your coding agent starts degrading. Personal context-rot analytics from your own sessions - 100% local, zero-config: uvx cont

绕过网络限制，一键安装 Claude Desktop 并修复 Host Claude Code binary not available 问题。

A Claude Code workflow for long projects: short context, decisions remembered, lessons that stick across sessions

Use DeepSeek, GLM, Kimi, OpenRouter and more in Codex CLI and Claude Code: one local endpoint, API translation, failover. Single Rust binary

Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.

Self-hosted news feed that learns what you care about. Groups stories across outlets, ranks and summarises them with Claude.

Quicksilver, toplu sınıflandırma ve arama işlerini Jev modeline devrederek Claude Code'un daha az token kullanmasını amaçlayan bir skill ve plugin'dir.

Neden yükseliyor · README, 12 görevlik benchmark'ta token kullanımında medyan %82 azalma ve bazı görevlerde hız artışı iddia ediyor; ölçülebilir tasarruf vaadi dikkat çekici. Ancak bu sonuçlar repo'nun kendi benchmark'ına dayanıyor ve bağımsız olarak doğrulanmış değil. Proje yalnızca 2 günlük olduğundan 66 yıldız erken ilgi göstergesi; 2 commit ve 1 farklı yazar ise henüz sınırlı geliştirme kanıtı sunuyor.

Shortcuts Playground: A Claude Code and Codex plugin for building, validating, signing, and remixing macOS/iOS Shortcuts with natural langua

A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance

Full job-hunt Claude skill bundle — Job Description decoder + Resume builder (11 templates) + Behavioral Interview / story bank. Three self-

Run coding agents like infrastructure, not terminal sessions. Warren manages isolation, lifecycle, spend, recovery, and Git delivery on comp

MCP plugin for Unreal Engine 5.7 & 5.8 — gives AI assistants full read/write access to Blueprints, Materials, Niagara, Animation, Mesh, AI,

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

AI(Claude·클로드 · Codex·코덱스)로 한글 문서(.hwp/.hwpx)를 한컴 없이 읽고·만들고·편집하는 오픈소스 스킬 · Read, create & edit Korean HWP in Claude/Codex

Study guides for all Anthropic Claude certifications: CCA-F, CCDV-F, CCAO-F, and CCAR-P. Exam domains, comparison, study paths, free practic

Specialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.

I gave Claude Code 120 pages of my handwritten college notes. It gave me back my handwriting as a real font, in 66 minutes for $13.68.

DSH 桌面端 Claude 风格主题插件

Reverse engineering skill for Claude Code and other AI coding agents.

Security-testing methodology as portable, tool-agnostic agent skills for Claude Code and any agent runtime: white-box bug hunting, AI-agent

Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus

quackd, farklı robotları tek bir CLI üzerinden LLM tabanlı görevlerle yönetmeyi ve birlikte çalıştırmayı amaçlayan Python aracıdır.

Neden yükseliyor · 30 günlük bir repoda 505 commit ve 241 yıldız dikkat çekiyor; ancak son 28 günde yalnızca 2 farklı yazar görünmesi, hareketliliğin sınırlı sayıda katkıcıda toplandığını düşündürüyor. README yedi robot gövdesi desteği bildiriyor, fakat bunlardan yalnızca birinin gerçek donanımda çalıştığını; diğerlerinin simülasyon veya mock olduğunu belirtiyor.

Mission control for your AI agents

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, er

Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, les

365 free AI marketing skills (zh-TW/en) for ChatGPT, Claude, Gemini, Claude Code & Cursor — copywriting, ads budget, margin, CRM, email. 365

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

One local board for Claude Code, Codex, Cursor and 5 more coding agents. See which session needs you, share your fleet card, start free on $

The execution control plane for AI agents. Govern every model request, MCP tool call, A2A delegation, and downstream action—while keeping yo

Open-source, multi-model agent for coding, research, and everyday workflows. Independently built engine with our own Alysis Sandbox, strict

Claude SEO Skills — production Claude Agent Skills for the SE Ranking MCP server. Content briefs, AI Search share of voice, audits, backlink

Open-source fantasy village for monitoring Claude Code and Codex across terminals, apps and IDEs. Live activity, context gauges, skills, plu