0012 views
Shareable instruction files for Cursor, Claude Code, Copilot, Windsurf, and more — installed alongside your existing agent rules.
Pure TypeScript grid engine. Zero DOM dependencies. Provides the pipeline, sorting, filtering, grouping, pagination, cell editing, validation, export/import, infinite scroll, selection, tree-view, and i18n systems.
This document provides guidelines and useful commands for AI agents contributing to the Cluster API Provider OpenStack (CAPO) repository. > **⚠️ IMPORTANT**: When making changes to Makefile targets, PR requirements, code generation workflows, verification steps, or any other information referenced in this document, **AGENTS.md must be updated accordingly** to keep it synchronized with the actual project state.
Guidance for AI coding agents working **on** this repository. If you are here to *use* the library in someone else's project, read `skills/` instead — those files are written for that, and are far more specific than this one.
Mei leads AI platform at a 25-person company building AI agents for enterprise customers. Agents forget everything between sessions — a support agent asks the same questions it asked yesterday. Stuffing entire conversation history into the prompt burns tokens ($500/day on GPT-4) and hits context limits. Agents can't share knowledge: the sales agent learns a customer's preferences but the support agent doesn't know. They need a context database: store agent memories, retrieve relevant context via
Applies on top of the root `AGENTS.md`: settle the **Footprint Ladder** before adding anything here. Most capabilities should NOT be core tools. Long-form: `website/docs/developer-guide/adding-tools.md`,
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in `node_modules/next/dist/docs/` (resolved from this file's directory; in monorepos the `next` package may not be visible from the repo root) before writing any code. Heed deprecation notices.
`Auto-Subtitle-Generator` is a local-first, GPU-accelerated video/audio subtitle generation and translation pipeline. It leverages `faster-whisper` (CTranslate2) for speech recognition, Hugging Face `transformers`
> **Read this file first.** It is the primary instruction file for all AI coding agents > (Claude Code, Codex, GitHub Copilot, or any other). After reading this, consult the > relevant files under `skills/` for deeper context.
**Cloudflare is a provider, not the architecture.** Every capability that wraps an external service ships as a neutral core plus provider modules, so a project swaps the vendor without touching the core, a consumer, or any other module. `email` + `email-cloudflare` / `email-plunk` / `email-console` is the reference shape; `logger` and `sms` follow it. `queue` + `queue-cloudflare` / `queue-memory` / a later `queue-upstash`, and `kv` + `kv-cloudflare` / `kv-upstash`, are the same shape applied to
This document provides essential information for agentic coding agents (Cursor, Claude, Copilot, Windsurf, etc.) working on **Promptr**. Promptr is a prompt testing & evaluation sandbox for AI agent builders. The platform is designed primarily to load custom scenarios, define constraints, and systematically stress-test prompts against adversarial workflows. It also features a curated curriculum of 25 missions across 5 progressive levels (Agent Basics → Tool Use → Workflow Control → Guardrails →