AGENTS.md examples from real projects

linkwardenReads credentialsAGENTS.md

linkwarden

linkwarden/linkwarden/AGENTS.md

spreads work across users), drives a headless Chromium through `lib/preservationScheme/*` to produce a screenshot, PDF, readability text, preview image and single-file HTML (Rust `monolith` binary), and optionally pushes

No other project uses it yet

storytoldAGENTS.md

pdfcraft

storytold/pdfcraft/AGENTS.md

material allowed is **non-visual technical data** that is openly licensed and required for PDF compatibility. Each item needs its own entry in `ATTRIBUTION.toml` with `adobe_data = true

firecrawlAGENTS.md

pdf-inspector

firecrawl/pdf-inspector/AGENTS.md

pdf-inspector Fast PDF text extraction to structured Markdown. CLI binary: `pdf2md`. Detection binary: `detect-pdf`. ## Build & Test ```bash cargo fmt # format cargo clippy -- -D warnings # lint (enforced, zero warnings

No other project uses it yet

sumatrapdfreaderDeletes or force-pushesAGENTS.md

sumatrapdf

sumatrapdfreader/sumatrapdf/agents.md

repo, with `sumatra-website:` prepended to the commit message (`sumatra-website: document CAJ files`). PDF example scripts live only in `sumatra-website/www/docs/scripts`. Edit and commit them in the website

Google CloudReads credentialsAGENTS.md

generative-ai / ge-demo-generator

GoogleCloudPlatform/generative-ai/search/gemini-enterprise/ge-demo-generator/AGENTS.md

# AGENTS.md — AI Agent Development Guide for Gemini Enterprise Demo Generator > **Purpose**: Project-specific knowledge

No other project uses it yet

tradecatlabsReads credentialsAGENTS.md

vibe-coding-cn

tradecatlabs/vibe-coding-cn/AGENTS.md

不进入GitHub当前文件树。 当前1个自有Skill和现有Extensions清单分别在其README，不另建工具注册层；16个官方引用入口已按用户要求移除。 用户点名的chat-vault、my-nvim、codex-config、MCPlayerTransfer、XHS-image-to-PDF-conversion、两个xhs图文HTML、html-tools-main说明及三份独立HTML工具均已从当前树移除；活动入口与位置绑定清理，原始快照/初审/排除保留，历史链接不是安装授权。 Lambda演算已按用户要求加入功法，品级天级上品（现行`tian-advanced

storytoldAGENTS.md

wordcraft

storytold/wordcraft/AGENTS.md

docx`, `formats` | line breaking, pagination, tables, headers/footers, hit testing; OOXML I/O; TXT/MD/HTML/RTF/ODT | | L3 | `render`, `pdf` | vello_cpu rasteriser; krilla PDF | | L4 | `engine` | Session, undo, **command registry**, Word feature catalog, samples

No other project uses it yet

suitenumeriqueReads credentialsAGENTS.md

docs

suitenumerique/docs/AGENTS.md

gouvfr-lasuite/ui-components` + Cunningham design system, Mantine for BlockNote - **Export**: BlockNote XL packages (PDF, DOCX, ODT) - **i18n**: i18next with Crowdin for community translations ### Collaboration Flow Clients connect via WebSocket

yusufkaraaslanReads credentialsAGENTS.md

Skill_Seekers

yusufkaraaslan/Skill_Seekers/AGENTS.md

unified_scraper.py` dispatches to per-type `_scrape_ ()` methods. `unified_skill_builder.py` uses pairwise synthesis for docs+github+pdf combos and `_generic_merge()` for all other combinations. **MCP tools** — grouped in `mcp/tools/` by category

ConardLiAGENTS.md

easy-dataset

ConardLi/easy-dataset/AGENTS.md

项目路由**: `app/projects/[projectId]/` - **API路由**: `app/api/` - **LLM核心**: `lib/llm/core/index.js` - **任务处理**: `lib/services/tasks/` ## 功能模块详解 ### 1. 文档处理模块 (`lib/file/`) - **支持的格式**: PDF, Markdown, DOCX, EPUB, TXT - **核心功能**: - 智能文本分割 - 目录结构提取 - 自定义分隔符分块 - 多语言支持 ### 2. AI模型集成 (`lib/llm/`) - **支持的提供商**: - OpenAI (GPT系列

kekingcnAGENTS.md

kkFileView

kekingcn/kkFileView/AGENTS.md

these areas: 1. preview routing and file-type dispatch 2. conversion pipelines for Office / PDF / CAD / archives / images 3. Freemarker preview templates under `server/src/main/resources/web` 4. CI, E2E fixtures, and production

MicrosoftAGENTS.md

agent-framework / azure-contentunderstanding

microsoft/agent-framework/python/packages/azure-contentunderstanding/AGENTS.md

store resources are cleaned up in `close()` / `__aexit__`. ## Samples | Sample | Description | |--------|-------------| | `samples/02-agents/context_providers/azure_content_understanding/01_document_qa.py` | Upload a PDF via URL, ask questions about it | | `samples/02-agents/context_providers/azure_content_understanding/02_multi_turn_session.py` | AgentSession persistence across turns | | `samples/02-agents/context_providers/azure_content_understanding/03_multimodal_chat.py` | PDF + audio + video

No other project uses it yet

nanobrowserReads credentialsAGENTS.md

nanobrowser

nanobrowser/nanobrowser/AGENTS.md

example skills the model loads, site notes, saved memory, the in-page Stop pill, PDF and Office parsing, the text tool-call parser, scheduled tasks

chromedpAGENTS.md

chromedp

chromedp/chromedp/AGENTS.md

transport, and the package `remote` in `remote/` | | `test/` | `github.com/chromedp/chromedp/test` | the tests that need `pdf` or `pixelmatch` | The package `remote` is not a module. It is a package

No other project uses it yet

vnotexDeletes or force-pushesAGENTS.md

vnote

vnotex/vnote/AGENTS.md

Utilities | [src/utils/AGENTS.md](src/utils/AGENTS.md) | PathUtils, HtmlUtils, FileUtils2 reference | | pdf.js assets | [src/data/extra/web/pdf.js/AGENTS.md](src/data/extra/web/pdf.js/AGENTS.md) | Touching the vendored PDF viewer or its Qt 6.9+ WebEngine requirement | | Testing | [tests/AGENTS.md](tests/AGENTS.md) | Agent GUI smoke testing with

vnotexReads credentialsAGENTS.md

vnote

vnotex/vnote/.github/AGENTS.md

attribution VNote requires the pinned Rust 1.99.0/Typst 0.15.1 shared library and Qt PDF. Embedding forces `VTEXTEDIT_ENABLE_TYPST=ON` and `VTEXTEDIT_BUILD_DEMOS=OFF`; do not ship upstream demos

vnotexAGENTS.md

vnote / src

vnotex/vnote/src/AGENTS.md

file viewer windows │ ├── markdownviewwindow2.h/.cpp # Markdown editor/preview window │ ├── textviewwindow2.h/.cpp # Plain text editor window │ ├── pdfviewwindow2.h/.cpp # PDF viewer window │ ├── mindmapviewwindow2.h/.cpp # Mind map viewer window │ ├── widgetviewwindow2.h/.cpp # Generic widget-hosting window │ ├── viewsplit2.h/.cpp # QTabWidget-based split

run-llamaAGENTS.md

liteparse

run-llama/liteparse/AGENTS.md

coding agents working on this codebase. ## Project Overview **LiteParse** is an open-source PDF parsing library written in **Rust**, focused on fast, lightweight document processing with spatial text extraction

No other project uses it yet

nearaiAGENTS.md

ironclaw / tests

nearai/ironclaw/tests/AGENTS.md

produce new downloadable files without changing the originals; and HTML renders to a persisted PDF | `document_edit.rs` | | Skill activation injects skill context into a real turn | `skill_activate.rs` | | Creating a project through

tw93AGENTS.md

Kami

tw93/Kami/AGENTS.md

document-generation skill and template system: self-contained editorial HTML templates rendered to PDF / PPTX / PNG, plus reference specs, demo assets, and a packaged skill archive. `SKILL.md` is the runtime

No other project uses it yet