#productivity

AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.

Personal AI Agent Hub 2026 — Build Your 24/7 Autonomous Assistant

35 portable Agent Skills for Codex, Hermes, and Claude, maintained by Rylai with Vietnamese documentation and upstream attribution.

A SKILL that turns a code diff into an evidence-backed ledger of hidden assumptions, failure modes, and falsification tests.

Turn your Cursor AI agent's work and your own typing into live, generative music 🎼

A terse-output skill for AI agents. Shorter replies without stripping technical details.

🚀 Modern, high-performance Terminal AI Coding Assistant built in Rust. Supports OpenAI, Gemini, Anthropic, Groq, OpenRouter, and Ollama with a premium Orange TUI.

Search your Claude Code conversation history by content (not just titles), then resume any session. grep + fzf, no index.

Hear a short spoken summary after your coding agent answers. Free to install - no API keys, no subscription, no cloud TTS.

Claude Code memory system — auto context injection, drift detection, compounding, FTS5/vector search, Obsidian vault export. Zero core deps.

Terminal cockpit for running a fleet of Claude Code sessions across all your repos — dispatch work, watch what ships, and act on what's blocked, from one screen.

Universal collaboration protocol + CLI for multi-agent LLM teams — Claude Code, Reasonix, Codex, WorkBuddy, Cursor

The best Pi coding agent setup — 10 packages, 59 skills, 10-step autonomous workflow. Zero bloat, pure Pi ideology.

Mission control for Claude Code: see and steer every session, subagent, /loop and todo list from one local dashboard. Zero dependencies.

Curated, hand-verified catalog of working Claude Code skills — marketing, SEO, dev, MCP — plus a built-in 19-sub-skill SEO/GEO agent. No dead links.

GPL-3.0 browser extension for Claude.ai: timeline navigation, text pins, folders, favorites, prompt vault, and one-click conversation export.

🚦 Always-visible macOS traffic light for AI coding agents. One glanceable dot per Claude Code / Codex session — red working, yellow waiting, green done — floating across every Space. Click a dot to jump to its terminal tab.

Give every Claude Code session a real name, automatically.

A crew of specialist AI agents and command workflows that drive a GitHub issue to a reviewed, CI-green pull request autonomously. Multi-harness.

Local-first AI coding usage dashboard for Codex, Claude Code, and Cursor — tokens, credits, USD estimates, native GUI, and WakaTime sync.

Local orchestration for Claude Code — session recovery, scheduling, worktrees, Token Saver, and dashboards via official CLI transport. Independent third-party software.

🎙️ Free, local, offline voice-to-text for Mac. Hold Ctrl → speak → text pastes anywhere. Powered by OpenAI Whisper. No API key, no internet, no limits.

A lightweight, instant-access scratchpad — from quick snippets to AI prompts, every piece of scattered text finds its place

Cross-agent prompt pocket: remember your most-used prompts and pick one to run. Works on Claude Code, Codex, OpenCode, Cursor, Copilot & Gemini; auto-scans Claude/Codex/OpenCode sessions for prompts you repeat 7+ times. Forged by agent-plugin-kit.

Shared AI agents for teams: one agent per channel, with memory, connected apps and approvals. Open source and self-hostable. Hosted at teamski.in

A desktop agent you can trust with files: preview every write, sandbox MCP tools, and keep Markdown local.

macOS menu-bar app + CLI for juggling multiple Claude Code and Codex accounts on one machine — isolated logins, parallel sessions, live usage tracking, and scheduled usage-window warm-ups.

三个实战验证的Claude Code Skill：会话交接、CLAUDE.md 生成、事前否决审计

Menu-bar status HUD for Claude Code — monitor multiple running Claude Code sessions (running · needs input · done · error) across terminals on macOS. Installs as a Claude Code plugin. No Xcode needed.

Repeating sound alert for Claude Code — only when it's genuinely blocked waiting on you, configurable interval and sound.

Claude Code plugin that stamps every message with the local time and turn duration, names the tool behind a slow turn, and reports where a session's time went.

slopstop is a system for preventing a coding agent, in this case Claude Code, from introducing slop and bugs into your code base. Slopstart is quite large when you using all of its features. It also is slow. A single ticket may take multiple hours... that's because its doing the checks that a senior engineer would do.

Ops toolkit for Claude Code power users: auto-merge session worktrees on SessionEnd + auto-resume sessions after usage-limit resets.

Free, open-source inbox cleaner that runs 100% on your machine. Bulk-delete promotions and one-click unsubscribe in Gmail. No cloud, no account, no cost.

Free disk space on macOS without breaking anything. A Claude Code skill with a native GUI picker that finds leftovers Homebrew and npm can't see — .pkg installers, curl installers, bundle-ID orphans, Xcode caches and project build output. Trash by default, so every removal is recoverable.

A quiet AI workflow coach. It spots where your time goes, hands you a 5-minute drill, and saves you a reusable playbook you can run by name. Works with Claude, Codex, and Gemini. MIT.

A notification sound plugin for AI coding agent CLIs — Claude Code and Codex.

The easiest way to start a second brain — an Obsidian vault Claude Code sets up in minutes and maintains for you

One file. One conversation. An AI memory that lasts - single-file second brain setup for Claude Code, Codex CLI, and any AI agent.

8 款生产级 AI Agent Skill：持久记忆、代码安全评审、自然语言数据分析、调试复现、测试生成、IaC 安全扫描、性能诊断、文档生成 | 8 production-ready agent skills (memory, code-review security, NL data analysis, agentic debugger, testforge, iac-guard, perf-doctor, docsmith). Pure Python stdlib, zero dependencies.