kheish
Persistent runtime for long-lived, tool-using workflows
All Skills in This Repository (75)
Pure Emerald Level Indicatorsdogfood
Automate exploratory QA testing for web applications with structured bug reports.
kheish-daemon-live-validation
Output the deterministic readiness marker for Kheish daemon live validation tests.
apple-reminders
Manage Apple Reminders tasks via the remindctl CLI.
imessage
Send and receive iMessage and SMS messages via the imsg CLI on macOS.
findmy
Track Apple device and AirTag locations via FindMy.app UI automation.
apple-notes
Manage Apple Notes via the memo CLI from the macOS terminal.
blogwatcher
Automate tracking of new content updates across blogs and RSS/Atom feeds.
polymarket
Query Polymarket REST API for prices, orderbooks, and market data.
llm-wiki
Create and maintain interlinked markdown knowledge bases with linting and Obsidian integration.
arxiv
Search arXiv metadata and full content without authentication.
Research Paper Writing Pipeline
Automate ML/AI research paper writing from experiment design to conference submission.
minecraft-modpack-server
Deploy modded Minecraft servers from CurseForge or Modrinth server pack zips.
Frequently Asked Questions
FAQPage SchemaHow to install Kheish?▼
Run `npx skills add graniet/kheish --all -g -y` in your terminal to install all skills in this suite globally.
What problem does Kheish solve?▼
It keeps long-running workflows alive when the caller crashes, the machine reboots, or a human is unavailable. Sessions, approvals, and state are journaled by the daemon and resume automatically.
Which model providers does Kheish support?▼
It supports Anthropic, OpenAI, Google, xAI, and OpenRouter, with per-run provider and model overrides. You can mix providers across sessions on the same daemon.
What kinds of skills are included?▼
The suite covers software development workflows, GitHub automation, research and paper writing, ML training and inference, creative media generation, email, smart home control, and macOS integrations.
Do I need coding experience to use Kheish?▼
Basic terminal use is required to build and start the daemon with Cargo. After that, you submit plain-English requests and the runtime handles execution, tools, and approvals.
Related Repositories in Software Engineering
View All in Software Engineering→openclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core