Havuz

briefme / brief-me: Turn complex AI analysis into a consultant-style, visual, interactive decision briefing.

Self-hosted game den where AI players pull up a chair — 大富翁/大富豪/斗地主/炸金花/UNO with Claude at the table. 一套 AI 牌友同桌打牌的自托管家庭牌窝。

Modawen Agent for WordPress is a completely autonomous, AI-powered multi-agent SaaS that researches live trends, writes deep-dive SEO-optimi

DeepSeek Harness (DSH) plugin: a read-only ledger for the plugins you already have installed — a capability inventory with file:line evidenc

Make destructive AI-agent actions reversible by default — quarantine + audit + human escalation for rm/git destructive operations. Reliabili

Autonomous AI inventors that daydream, invent, and make new toys and games around the clock.

Agent Skill that turns your coding agent into a keyboard firmware expert. Audits ZMK/QMK keymaps, tunes home row mods, makes trackballs laye

AI-authored 2D rigging and animation, verified before it is written. rigc compiles a rig spec into skeleton data in the Spine 4.3 format, ga

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation,

Live monitor and workspace orchestrator for AI coding agents (Herdr, OMP, Hermes, remote Hermes peers, Claude, Codex, Grok) in the Omarchy b

Native terminal workspace for parallel AI coding agents. Git worktree isolation, persistent sessions, embedded browser tabs, and mobile remo

Focused Agent Skills for complete Flutter and Dart app delivery, based on real-world projects.

Your machines, from anywhere — for you and your agents. The shanframe agent + CLI.

Guard rails for Claude Code: workspace boundaries, protected branches, production targets, lost exit status, and foreground time.

⚡ High-frequency (~60Hz) in-browser behavior tree execution engine for autonomous AI agents. Reactive priority interrupts, safety guardrails

Foremerge, coding agents'ın Git worktree'lerinde paralel çalışırken niyet ve kapsam çakışmalarını kod değişikliklerinden önce fark etmelerini sağlayan yerel bir koordinasyon aracıdır.

Neden yükseliyor · 37 günde 511 yıldız, coding-agent koordinasyonuna yönelik görünür bir ilgi olduğunu düşündürüyor; yükselişin özel nedeni verilerden doğrulanamıyor. Son 28 gündeki 39 commit geliştirme hareketliliğine işaret etse de katkı 2 farklı yazarla sınırlı.

agenttrail, AI coding agents’ın yerel etkinliklerini proje değişiklikleri ve görev katkıları olarak görselleştiren bir observability aracıdır.

Neden yükseliyor · 37 günde 710 yıldız, kısa sürede dikkat çektiğini gösteriyor. Son 28 günde 23 commit olması geliştirme etkinliğine işaret etse de farklı yazar sayısının 1 olması ve ürünün experimental preview olarak tanımlanması, bu ilginin olgun benimseme kanıtı sayılmasını engelliyor.

Tiny Engineer, AI coding agent’ların çalışma durumlarını Wi-Fi üzerinden aldığı olaylarla hareket, ekran ve ses tepkilerine dönüştüren, ESP32 tabanlı masaüstü robottur.

Neden yükseliyor · AI coding agent’ların yaygınlaşmasıyla görünür çalışma durumu fikri ilgi çekiyor; 37 günde 395 yıldız ve son 28 günde 44 commit ile 5 farklı yazar, hem erken ilgi hem de kayda değer geliştirme faaliyeti gösteriyor.

Reusable Agent Skills for Amazon product research, listings, advertising, inventory, and operations.

DeepSeek Harness plugin for Android — build, run, and interact with a live emulator or USB device stream inside a conversation, driven entir

🖼️ AI agent skill for Claude Code & Codex — turns raw app screenshots into store-ready App Store & Google Play marketing images: device fram

Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential imp

DeepSeek Harness 三端兼容桌面启动器：多实例完全隔离、并行协作，协作画布编排 Agent 工作流；便携版 Exe 一键启动、仅约 20M；双隔离机制让兼容性极强

Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.

Lightweight, zero-broker hybrid retrieval engine for RAG. Combines vector search, local Personalized PageRank (PPR) over Atomic Entity Graph

Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KV

Interactive data exploration that is extremely fast and agent-native

WebView automation for Kotlin Multiplatform. Run page workflows in an embedded WebView on Android, iOS and desktop, from your app, a test, o

Scroll Video Website is a portable AI-agent skill that turns videos into smooth, scroll-controlled canvas experiences with optimized WebP fr

A lightweight, Git-backed permanent memory for AI agents.

Source-backed, production-first FDE interview fieldbook with cases, scorecards, and current role research.

Visualize AI context & traces.

Turn scattered, duplicated AI-agent Skills into per-Agent Rosters—with evidence, receipts, and exact undo.

A collection of public writeups on attacks against AI agents: prompt injection, tool abuse, memory poisoning, and data exfiltration.

Your AI remembers what you decided — and what you changed your mind about. Plain-Markdown memory for Claude Code, Codex, Cursor and any MCP

A /human-review skill for Claude Code: assembles one page that lets a human review a change set fast — diagram deltas, Code City, a feature

DeepSeek Harness plugin: DietrichGebert/ponytail lazy senior mode & 7-rung ladder port, 6 skills with bilingual descriptions & per-skill tog

Pilly - AI trading copilot for Solana memecoins. Live trending, crew verdicts, charts, price alerts, PnL tracking and a desktop pet that rea

Free, open-source SSH client, SFTP, tunnels, database GUI and a secure AI-agent (MCP) bridge in one app a MobaXterm, PuTTY and Termius al

把工作组织成目标看板的 DeepSeek Harness (dsh) 插件：目标 / 判据 / 上下文卡片 / 执行 attempt 的二维泳道看板，数据以文件+事件流落在 .dsh-graph · Goal-kanban plugin for DeepSeek Harness

Desktop personal AI agent for local projects, coding and learning. Persistent conversations, editable memory, scoped helpers and a living Vi

Five layers of an agent harness, each with the failure it prevents. Runnable with no API key.

Consensus REST API. Semantic search over 400M+ peer-reviewed research papers, including all of PubMed, for RAG, AI agents and research tools

Open-source delivery system for building commercial software with AI agents: governed project board, independent review, security by default

Scores 10,100+ open-source AI repos on Impact / Velocity / Health - refreshed 6x daily.

Let Claude Code or Codex draw real Excalidraw diagrams — flowcharts, wireframes, slide decks, SWOT, Lean Canvas & 17 official use cases. Ins

dsh-dock · DeepSeek Harness 功能坞插件：一张面板统一注册/开关所有小功能——用量记账（自定义单价·分时价）、模型设置与余额、19 种任务动画、任务通知（钉钉/飞书）、运行状态、图片理解代理、账号密码远程访问、10 款小游戏。每个功能独立模块，可开关、错

Delegate Grok Bot coding work to your own local Claude Code / Codex CLIs via a custom MCP connector

Independent evidence-gated second brain for understanding and porting DeepSeek Harness architecture.

Kiro as a Software Factory: graph engineering with agent loops that run turn after turn as kiro-cli sessions, wired together through folders