Havuz

FailproofAI, farklı AI agent harness’lerindeki çalıştırmaları izleyen ve tehlikeli tool çağrılarını yürütülmeden önce policy ile engelleyebilen bir araçtır.

Neden yükseliyor · 175 günlük bir repo için 5.166 yıldız ve son 28 günde 84 commit ile 8 farklı yazar, hem belirgin ilgiye hem de yakın dönem geliştirme faaliyetine işaret ediyor. Çok sayıda harness için ortak observability ve enforcement sunma iddiası, agent araçlarının çeşitlendiği dönemde dikkat çekici; yıldızlar tek başına benimseme veya kalite kanıtı değil.

A free Agent Skill for writing short-form hooks, scripts, and carousels for TikTok, Reels, and YouTube Shorts.

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injectio

Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already

Antigravity 破甲工程：二进制提示词补丁 / 规则技能 / 生命周期钩子 / IDE 等长补丁 / 模型后端改道

Approve Claude Code from your Mac's notch. A native SwiftUI menu-bar app that surfaces Claude Code permission prompts, questions, cost and c

Track the carbon footprint of your Claude Code sessions, in the terminal and the Claude desktop app

The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

Auto AI improver. Cost and token burn reducer, turn saver, and focus keeper for Claude Code, Codex, Copilot, Gemini, and more: surgical read

One-stop skills, subagent, MCP and LSP manager for DeepSeek Harness (DSH) — compatible with Claude Code, Codex, Cursor, Kimi and other agent

Show local time on every Claude Code message, and let Claude know when each prompt was sent. Zero-config plugin, cross-OS, graceful degradat

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any sc

Claude Code skill: one topic in, one ranked YouTube research workbook out. Searches YouTube Data API v3, ranks by views, engagement, momentu

Контроль качества 1С-разработки для Claude Code: стандарты, принципы ООП и паттерны, XML метаданных, блокирующие гейты и проверяемый след пр

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

An open protocol and client for what your coding agents are doing: hooks for every harness, four privacy tiers, any sink.

Stop Claude Code from burning through your quota in 20 minutes. Auto-rotates oversized sessions and preserves context.

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code:

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

Deja de usar Claude Code como venía en la caja. Semáforo de contexto, modo conciso, 4 hooks que bloquean comandos destructivos y secretos, e

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory

Desktop & phone notifications for AI coding agents (Claude Code, Codex, Gemini CLI, Cursor). Native VS Code support. Toast + ntfy push. Zero

A research lab's Claude Code setup: 67 skills, hooks and rules, plus a knowledge base in plain git — GitHub for ideas. A question goes in, k

A tested harness for durable work across coding agents: CLAUDE.md/CHECKPOINT.md state and 17 skills, a Claude Code plugin with enforcing hoo

Discord Rich Presence (RPC) for Claude Code — live model, project, tokens, and lifetime stats in your Discord profile. Driven by Claude Code

The Claude Code harness I run every day, published under this name since day one and now the same repository as ucsandman/Agnostic-AI: guard

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

Your AI coding assistant can finally see what you're doing. Local-first screen context for Claude Code, Codex, Gemini CLI and Muse Code.

Let TypeSafe Jev decide whether a message you send mid-turn should steer, queue, or interrupt your coding agent. Claude Code plugin; Codex C

An engineering team in a box for Claude Code — 12 specialized agents, 15 automation hooks, and the P7/P9/P10 methodology.

A comprehensive statusline dashboard for Claude Code — session info, quota bars, agent tracker, MCP health, message history, and more.

Full-lifecycle wiring between Claude Code and the Clawd on Desk pet — all 15 hook events, with permission prompts answered straight from the

A Lean quality system for AI-assisted work — every defect becomes a permanent countermeasure. Built by a manufacturing operator.

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via

⌚ 在 Apple Watch 上批准 Claude Code / Codex 的危险操作,任务完成自动提醒 | Approve your AI coding agent's risky actions from your Apple Watch, get buzzed when

Run multiple Claude Code accounts as one. Auto-switches on rate limits and resumes your session no lost context, no logout dance.

Claude Code plugin that plays a Mr. Meeseeks voice line whenever Claude is waiting for you.

Driver-based, zero-dependency, fetch-first TypeScript HTTP client. Hooks, retry, redirect security, RFC 9111 cache, RFC 6265 cookies, Idempo

A battle-tested, framework-agnostic reference architecture for Claude Code. Beginner-friendly with graduated adoption (minimal / standard /

Local-first, evidence-aware memory and project continuity for AI coding agents. Checkpoints, context packs and auditable receipts without te

Hook-driven multi-agent CLI — one prompt to specs, code, tests, and a shipped release.

A macOS desktop AI pet that mirrors your Claude Code & Codex CLI session state in real time. 支持Claude Code和Codex CLI 的像素风AI桌面宠物，会话状态实时映射，支持导

AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemin

React Lab is an interactive sandbox designed for modern learners to master React through hands-on experimentation. It bridges the gap betwee

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

"Linux? Nah. WinUX!" Windows auto-patcher for vibe coders.

A self-evolving Claude Code plugin. Context routing, memory bootup, smart delegation, self-correction — out of the box.

Audits the .claude/ ecosystem — skills, commands, hooks, agents, settings, plugins, memory — for dead references, weak triggers, token bloat

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deter