Havuz

DeepSeek Harness 长篇角色扮演agent（DSH酒馆插件）：SillyTavern 角色卡导入、行动选项卡、分支对话管理、长篇记忆、关键词与语义混合检索、交互式角色卡创作、世界书、多角色 Agent 集群、文风预设、小说与角色卡导出、一键安装。 / Rolepla

🌹安装即自带mattpocock/skills v1.3.2的27个工程与效率技能，无需手动装技能。520亿token打造本插件，在原始技能之上提供10倍的开发效率，也能帮助新手更快上手该技能套件。支持 GitHub 与 GitLab 的 issue；本地 Markdown 为预

Project memory and workflows for Claude Code and Codex. Keep stories, plans, handovers, and review evidence in your repo. Resume across sess

omg.dev — Remote control for claude, codex, cursor, opencode, pi, grok, jcode with mobile client

Static analysis for the debt AI agents leave in PHP: 34 rules, Claude Code hooks, git-diff review, a Rector and Pint fix pass, Pest expectat

Browse, create, and edit AI agent files across Claude Code, Cursor, Codex, and 12 coding tools — from Obsidian.

基于麦当劳 MCP 的权益精算 Skill——按档口与账户权益实时核价，算清这顿值不值、这张卡值不值，一次确认完成点单

CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.

Put the world's best AI agents to work. One workspace for all of them -- Claude Code, Codex, Gemini, Grok and more, running side by side on

qiaomu-codex-imagegen, Codex’in yerleşik image generation özelliğini MCP, CLI ve Agent Skill üzerinden farklı agent’ların kullanmasına yarayan bir araçtır.

Neden yükseliyor · Herhangi bir agent’tan görsel ürettirme vaadi ve çok sayıda hazır tasarım yönü projeyi kolayca denenebilir kılıyor; ancak 1 günlük geçmiş, 3 commit ve tek farklı yazar nedeniyle ilginin kalıcı benimsemeye dönüştüğüne dair kanıt henüz yok.

Turn your Claude Code session history into a searchable local knowledge base — 13 MCP tools, pure stdlib, nothing leaves your machine

The open source Unity Dev Agent

Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

Autonomous GitHub Project build → QA → review loop for Claude Code. One-line install.

帮你的 Claude Science 一键接入你自己的 API：DeepSeek / 通义千问 / 智谱 GLM / Kimi / MiniMax / 小米 MiMo / 硅基流动 / OpenRouter / 任意 OpenAI·Anthropic 兼容端点

A custom Agent OS built to be hackable, heavily inspired by OpenClaw.

OnCo: total information dominance on cancer. A public, cited knowledge graph of oncology with a website, JSON API, MCP server and CLI: one p

Kanwas — Shared context board for teams and agents

120 patterns that make writing read like AI slop, with an agent skill for Claude Code and Codex.

AI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sour

Tarayıcıda çalışan Türkçe konuşma tanıma ve altyazı aracı. Otomatik noktalama, canlı transkript ve altyazılı video dışa aktarma. Tamamen yer

MobileCode, AI coding agent deneyimine iOS ve Android projelerini derleme, çalıştırma ve canlı cihaz önizlemesi özellikleri ekleyen bir opencode fork'udur.

Neden yükseliyor · Henüz 23 günlük bir repo için son 28 günde 214 commit ve 17 farklı yazar kayda değer geliştirme hareketliliğine işaret ediyor. Yıldız sayısı 239; ilginin büyüklüğünü tek başına kanıtlamasa da hareketlilikle birlikte projenin erken dönemde dikkat çektiğini gösteriyor.

Matching decompilation of the Gran Turismo 4 (PS2) engine, AI-assisted. No game data included.

DeepSeek Harness (DSH) backup & restore plugin — export, import, migrate and sync your complete DSH configuration, plugins, MCP servers, ski

Open-source, channel-native agent gateway for Slack. Route team threads to Claude Code, Codex, OpenCode, Docker, HTTP agents, and custom CLI

Inference-native Tokenmaxxing Agent Harness for Loop Engineering

A local-first desktop app for running a team of AI agents on Claude Code, Codex, Cursor, Cline and more, on your own computer.

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /rend

🪸 Powerlevel10k-inspired statusline for Claude Code — paste one prompt and your AI interviews you, then installs it

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-awa

A vLLM-inspired inference engine for looped transformers, with loop-level scheduling and execution across composable stages

为 A股投资者打造的全球产业链资讯看板 · 12 大赛道一一对应 A股板块(半导体/AI/机器人/新能源车…)，覆盖 100+ 权威源，用你自己的大模型每日提炼中文「今日要点」+ 翻译 · 本地运行、零 API key · Local AI news dashboard trac

Sentio, AI agent’lara ayrı email inbox’ları sağlayan ve gelen postaları webhook, gönderimleri REST API üzerinden yöneten çok kiracılı bir mail sunucusudur.

Neden yükseliyor · AI agent’lara gerçek email adresi verme fikri güncel ve anlaşılır bir kullanım alanı sunuyor; proje 35 günde 249 yıldız ve son 28 günde 27 commit almış. Ancak 2 farklı yazar, geliştirme ve bakım kapasitesine dair sınırlı kanıt sağlıyor; yıldızlar üretim olgunluğunu veya gerçek kullanım düzeyini göstermiyor.

VelaTerm = Codex + iTerm2, The Best ADE for AI Coding

Hermuse (Hermes + Muse) — personal AI agent stack built for Muse: Hermes + 9Router + Telegram gateway, automated install, Cloudflare tunnel,

A free, open-source desktop app for getting work done with AI. It shows you what it would remember before it saves anything.

麦门全能管家：基于麦当劳中国官方 MCP 的一站式助手——自动领券、权威比价、点餐推荐、每日巡检、巨无霸指数。2026 麦当劳程序员节创意开发大赛参赛作品。

DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Ten

AI-native, local-first video editor by Ribbi — runs entirely in the browser. Rust/WASM engine, WebGPU compositing, WebCodecs export; humans

RikkaHub fork，Android AI 客户端。支持 IM（类 Grok-Bot）模式，ChatGPT 订阅登录使用、跨应用划词悬浮翻译、高性能低延迟远程云电脑控制。

日语、英语视频与直播实时同传悬浮字幕（Android / macOS / Windows）｜本地离线语音识别 · 自备 LLM 翻译（BYOK）

安卓AI聊天端:开箱即聊，无损导入酒馆卡，缓存强省用量，手机操控，专属RP模式，防空回，主动信息，前端卡支持，高定制主题，QQbot，AI群聊，插件系统，强兼容中转站。手机移动端原生支持，求 Star 收藏⭐Android AI Chatbox: lossless SillyTa

Metis is a coding agent that boosts AI/LLM coding performance by 50% QQ群: 801193315

Open-source directory of agent-bot prompts for Grok Bot, Rakazo, and any agent — botdirectory.ai

21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a

The agent flow system for token maxxing.

AI red-team platform. Autonomous LLM agents run a penetration test end to end inside a Kali container and write the report. LangGraph plan/a

The ultimate collection of APIs for building autonomous AI agents — 2,036 production-ready APIs across Agents, AI Models, and MCP Servers. S