Most Popular

Teslascope MCP assistant for Tesla owners. Answers questions about drives, Superchargers, charging, and your vehicles.

Private desk workspace runner from Prism for focused bot work.

Drives a real Android phone through MyPhonely: taps, types, reports the screen. Never posts until you approve both the text and the action.

Sends documents for human signature via SumoSign with the client's own API key: upload, place fields, preview, send.

Midkernel GitHub repo scan from chat: sandbox run, report plus full log, credits meter each run.

Wraps an API into a Cursor and Grok Bot plugin (MCP plus skills). Smallest scaffold that works, prove locally, then ask once before publishing.

You say what to build and how you know it is done. Keeps a coding agent working on your computer until that check passes.

Picks 1–3 Korean public/government APIs that fit a service idea, with why, auth, official links, and alternatives — short planning brief.

A daily GitHub trending scout that picks a handful of hot repositories and explains, in Chinese, why each is worth a look.

Bridge to a Hermes Agent so you can talk, collaborate, and delegate — including coaching Hermes install and API setup when needed.

Builds and maintains a TRMNL private plugin that surfaces UniFi Protect UP-AirQuality sensor data on a desk display.

Coding coordinator where cloud agents write code, each job gets a fresh agent, and work is not done until verified.

Walks a Bot org through Telnyx signup, API keys, numbers, SMS/voice, webhooks, and a first live test.

Stops PRs from merging on hope. Reviews the diff against the claim, waits for real tests, and only ships when the evidence is there.

QR-links WhatsApp Web once, then list / read / search / send via headless Chrome CDP. Capture-first. No mass messaging.

Governance-driven systems closeout bot. Single-tree workflow, source-of-truth first, short progress updates, fail-closed dual-store mobile release gates.

Operates your Tesla through Teslr. Charge, climate, closures, navigation, security, and schedules. Blunt, short, a little theatrical.

Runs the real Grok Build CLI for apps, code, and deep research at maximum effort on the agent computer.

Owns PR quality gates: waits on CI and Bugbot, posts a verdict, and auto-merges only low-risk changes.

Daily issue and PR triage with labels and replies queued for your OK.

Designs high-quality Grok Bots. Asks a few preference questions, then creates them with CreateAgent. Coding bots get the pstack bar (poteto-mode: one job, unslopped, verified). On first run after import, run setup-pstack so pstack models are configured. Non-coding bots get the same tightness: one job, one voice, explicit anti-jobs. Casual, mad-scientist, lowercase. Bias to act. Does not default to shareable templates.

Reviews PRs for bugs, security, and missing tests.

Feature editor. ONLY job: suggest actually good product features — few, sharp, named, with the cut. Voice is Steve Jobs: short, opinionated, taste over metrics, "no" is a feature. Never write code, never ship, never dump a brainstorm list, never write a PRD. Given a product or problem, return 1–3 features, one line why each, and what to cut. On-demand only. Stay quiet when there's nothing to suggest.

Nightly engineering auditor that researches a whole codebase, then ships one cleanup per area.