How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
joaogqueirozllms.txtjoaogqueiroz/joaogqueiroz.github.io/llms.txt
month. - Designed a real-time notification platform with SignalR and REST APIs that replaced frontend polling across three microservices, and later cut its database writes by about 90%, which resolved
kairav7220Reads credentialsllms.txtkairav7220/travel-booking-agent/llms.txt
versatile as the LLM - PostgreSQL + PostgresSaver for conversation checkpointing - Streamlit for the frontend - AviationStack API for flight data - Tavily API for hotel/hotel search ## Environment Variables GROQ_API_KEY, TAVILY
kivanov82llms.txtkivanov82/ShipWith.AI/site/llms.txt
regulated fintech. - A regulatory feature shipped to production across one backend and two frontends in 1 day. - 100% of Critical, High and Medium audit findings adversarially re-verified before they
koinaraReads credentialsllms.txtkoinara/koinara-site/dist/llms-full.txt
# Koinara full public archive This file concatenates all public-safe reviewed Koinara records for
koinarallms.txtkoinara/koinara-site/dist/llms.txt
form-submit-lost-on-unmount, aigora-path:records/traps/frontend/dropdown-form-submit-lost-on-unmount.json - tags: common-ai-mistake, external-systems, frontend, workflow - [Hot count polling can become the data import incident](https://koinara.org/records/hot-count-polling-can-become-the-incident/) - raw Markdown
lj22503Reads credentialsllms.txtlj22503/mangoview/llms.txt
bias 6. **Decide** with audit trail ## Tech Stack | Layer | Tech | |---|---| | Backend | FastAPI + Python 3.11+ | | Frontend | Next.js 14 + Tailwind + Recharts/ECharts | | Data | AKShare / 东方财富 / 天天基金 / 新浪 / tushare | | Knowledge | investment-framework-skill (submodule
lroollellms.txtlroolle/skills/llms.txt
fonts, icons, and references by function - [kiln](https://raw.githubusercontent.com/lroolle/skills/main/skills/kiln/SKILL.md): design or restyle a frontend surface; audit an interface; rescue generic AI-looking output - [taste](https://raw.githubusercontent.com/lroolle/skills/main/skills/taste/SKILL.md): judge whether
MachengShenllms.txtMachengShen/MachengShen.github.io/llms-full.txt
wheels for multi-agent AI coding — drift checks, adversarial review, a reuse compiler, a frontend smoke gate. Built for the failure mode where every agent reports "done" and nobody actually
MachengShenllms.txtMachengShen/MachengShen.github.io/llms.txt
wheels for multi-agent AI coding — drift checks, adversarial review, a reuse compiler, a frontend smoke gate. Built for the failure mode where every agent reports "done" and nobody actually
martin1847llms.txtmartin1847/krpc-starter/llms.txt
walks > the full loop end to end, paired with a universal React Native + Web frontend in one > monorepo. Read this if you are building a contract-first agent backend
mppyxxllms.txtmppyxx/claude-power-pack/llms.txt
listed in THIRD_PARTY_NOTICES.md. - 94 skills: 35 web research and browsers, 23 design and frontend, 13 Cloudflare and web platform, 6 animation, 5 working smarter, 4 AI image and video
naman10parikhllms.txtnaman10parikh/pixel/llms.txt
pixel > Frontend taste you can put in CI: an agent employee that scaffolds Next.js 16 apps and blocks UI that looks AI-made. pixel is the Energy fleet's frontend
naman10parikhllms.txtnaman10parikh/turbo/llms.txt
wire. turbo never holds cross-request state in process (the law). Other verticals: frontend → pixel · mobile → pebble · DB → acorn · auth → badge · billing → penny · deploy/CI → rocket. ## ID index (the queryable vocabulary
nauelGomezllms.txtnauelGomez/nahuelgomez-pro/portfolio/llms.txt
Express), PHP (Laravel, Symfony), APIs REST, WebSockets/Socket.io, arquitectura multi-tenant, PostgreSQL (Prisma), MongoDB, MySQL - **Frontend:** React, Angular, Astro, TypeScript - **Infraestructura e integraciones:** Docker, AWS (EC2, S3), Railway, Fly.io, GitHub Actions
nexorahai-svgPipes a download into a shellllms.txtnexorahai-svg/claude-knowledge-library/llms-full.txt
claude-code-tooling, MIT): مستندات بهروز کتابخانهها برای عامل؛ پلاگین رسمی بیرونی Claude Code - [Frontend Design (افزونهی رسمی Anthropic)](catalog/frontend-design.md) (claude-code-tooling, Apache-2.0): مهارت رسمی Anthropic برای رابط
nothingtosurpriseReads credentialsllms.txtnothingtosurprise/env-doctor/llms.txt
env.dev, .env.prod ## Server Located at server/server.py. Built with FastMCP (Python). Run with: python server/server.py ## Frontend Located at frontend/index.html. Pure HTML/CSS/JS — no build step, no dependencies. Open directly in browser. ## License
nycsavllms.txtnycsav/notion-geo-audit/docs/llms.txt
question FAQ assistant - [Architecture](https://geo.ensolabs.ai/architecture.html): How the backend, connectors, and frontends fit together - [Source code](https://github.com/nycsav/notion-geo-audit): MIT-licensed repository — CLI, Claude MCP connector, Notion sync
OctopusGaragellms.txtOctopusGarage/octopusgarage.github.io/llms-full.txt
generate a bracket, and export a shareable poster. It is implemented as a pure frontend app with React, TypeScript, Vite, internationalization, and GitHub Pages hosting. mbti-lab is a bilingual
ohnoshivmllms.txtohnoshivm/creative-engineering-os/llms.txt
against imitation, and produces a CONCEPT.md that requires owner approval before large implementation. - [ceos-frontend-architecture](skills/ceos-frontend-architecture/SKILL.md): Chooses and structures the frontend for creative websites — Astro vs Vite vs Next.js
opendaniilllms.txtopendaniil/collabora-online-sdk-llms/llms.txt
Hidden-form override mechanism for selected CheckFileInfo behavior at iframe setup time. ## iframe and Frontend Integration - [Website that presents the editing capabilities](articles/148_L1_How_to_integrate__Website_that_presents_the_editing_capabilities.md): Main iframe embedding entrypoint for document editing
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
