Independent directorynot affiliated with xAI
Catalog refreshed Nobody pays to be listed or ranked
9,075 templates from 4,179 creators, each showing what it connects to, whether it asks first and how often it runs. “Checked” means the link was reachable — not a safety rating.
A workbench for building bots rather than using them. Describe what you want and it drafts a focused persona, wires up an interface that talks through webhooks, and re-checks an exis…
Rather than briefing several assistants yourself, you brief exactly one. It forms a view, converts that view into instructions, and pushes the actual work down to the bots underneath…
Independent verification for AI-generated diffs. Coordinates the sealed verify.sh | proof-agent-verify-copilot pipe and reports Copilot’s PASS, FAIL, or PARTIAL. Does not judge the c…
It behaves like a long-running engineering and product lead: it keeps the shape of the whole system in view, calls when something is ready to ship, and cuts the work into tight, well…
An assembly seat inside Figma for product designers. It builds new frames and tidies existing ones with the library components already in the file, and it reads autolayout and spacin…
Give it a half-formed question and what comes back is a tight brief that has already been checked, not a pile of links to work through yourself. It hunts across the open web, the fil…
Screens websites, repos, packages, and extensions you are considering, and recommends whether they are reasonable to use, with evidence. Built for people who want a careful look befo…
Reads one public website the way an AI crawler would and hands over what to fix: an llms.txt draft, additions for robots.txt, notes on schema, and a patch list of five items. Everyth…
Interview coach for DevOps and Cloud roles on Azure: it assesses your real experience, builds a prep plan, runs hands-on Kubernetes, Terraform and CI/CD labs, and gives mock intervie…
Checks what your AI bots and prompts produce against a contract with AISchemaGate, repairs what it can, and explains failures in plain words. For anyone shipping LLM output into real…
Builds Firefox or Chrome extensions that change how X (Twitter) looks, such as hiding names, avatars, metrics, ads, or sidebars. For anyone who wants X their own way.
A cost overseer for anyone running more than a couple of bots against Cursor. It keeps a running picture of where the budget is going, identifies the individual bots responsible for…
A small, focused Linux desktop utility. It installs the Hyprland droplet pointer theme on an Omarchy setup at whatever size you pick between 24 and 48 pixels, pulling the artwork fro…
Audits your AI agents' tools, secrets, and permissions, writes a deny-by-default policy, and helps you install free open-source guardrails with an audit log and kill switch. For foun…
Writes coding prompts you paste into several AI models to compare how well each one builds something visual in code (Three.js, canvas, SVG, HTML/CSS). Keeps a numbered idea log, with…
Sets up and audits paid plans for mobile apps and websites: App Store and Play subscriptions through RevenueCat, plus Stripe or Paddle on the web, kept in sync so both grant the same…
새 AI 도구·스킬·플러그인·MCP 서버 링크를 주면 보안 점검표로 정적 검사해서 도입·보류·일부 차용 중 하나로 판정하고, 깔 거라면 연결된 컴퓨터·서버·에이전트 중 어디에 깔지도 추천해요. GitHub 별표와 X 북마크에서 쓸 만한 도구를 알아서 찾아 평가하고, 쓰는 도구 목록 관리, 주간 점검, 이미 깔린 도구와의 중복…
A coding collaborator that errs on the side of asking. It proposes changes and can open a pull request when you request one, but merging, publishing and deploying all wait for an exp…
Handles the parts of a codebase that run close to the metal: background daemons, installed applications, graphics pipelines and the scripts that push them out. Its comfort zone is C+…
It looks at how an AI-assisted task is set up and finds the parts of the bill you do not need: context that adds nothing, a heavyweight tool where a lighter one would do the job, and…
A plain-spoken home-tech helper that runs app rotations across phones, tablets and a Chromebook, tunes small Bitcoin miners for electricity cost, and watches your email for security…
Hand it a problem you have already reproduced and it writes the incident up accurately, keeping the details straight, then sends that report on to whoever owns the surface it belongs…
Scans a repository for questions worth investigating and holds them in a queue. When your coding assistant hits its usage ceiling for the day, that queue is handed to a browser sessi…
Produces small games that genuinely run and open with no connection needed. There is a real way to win and a real way to lose, optional scorekeeping, and placeholder data throughout…
A knowledge bot scoped to one engineer's public work. Ask it something and it answers from what Kun Chen has published, demonstrated on video, or open-sourced, rather than from gener…
Pulls figures for what Grok Bot and Cursor are costing you straight from their interfaces, holds the total against a ceiling you set for the day, and lists whatever is eating most of…
Get your own iBot, an iPod-style player for your Apple Music, deployed on your own Vercel in about 15 minutes. It walks the MusicKit key, the deploy and the iPhone test one step at a…
A security lock-down operator. It finds weak spots in your own accounts, devices, and networks, puts the fixes you approve in place one step at a time, and reports what risk is still…
Keeps your Grok Bot memory in sync with GBrain, hosted or self-hosted, and helps you run the server: jobs queue, consolidation, calibration, upgrades and backups. Made by @massimodel…
Reads back through what your bots have been saying and where their recurring jobs overlap, then names the waste: a conversation circling the same ground, two timers firing for one ta…
Describe the feature you want and, in plain language, the condition that proves it is finished. The bot then drives a coding tool already installed on your machine, such as Cursor, C…
Long-press your Android assistant button on any reel, video or page, ask a question out loud, and get a short silent answer as a notification. Works with the free open-source Android…
Checks whether a bot or template already exists before you create a new one. Describe the bot you want and get a quick verdict: already exists, partly covered, or nothing similar found.
Runs a research question through five specialist stages instead of a single pass: a deep-dive brief, a claim-and-source fact check, a competitor sweep, trend monitoring, and a final…
When one of your specialists stops making progress, this is the one you call. It works out what is actually blocking it and hands you a specific next move rather than a vague status…
When the machine your bots share starts running hot on memory or storage, this one steps in and takes the pressure off before work grinds to a halt. It also guards the slim update ro…