anymd
SylphxAI/anymd/AGENTS.md
anymd — agent notes anymd (formerly Citra and pdf-reader-mcp) turns any file into Markdown for AI agents. It is one Rust binary (`crates/anymd`) that is both the MCP server
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
SylphxAI/anymd/AGENTS.md
anymd — agent notes anymd (formerly Citra and pdf-reader-mcp) turns any file into Markdown for AI agents. It is one Rust binary (`crates/anymd`) that is both the MCP server
borghei/Claude-Skills/AGENTS.md
sales-success/ # 5 skills — account exec, sales ops, solutions architect ├── documents/ # 4 skills — docx, pdf, pptx, xlsx (stdlib OOXML) ├── hr-operations/ # 4 skills — talent, people analytics, HRBP ├── research/ # 4 skills
magicyuan876/mineru-tianshu/AGENTS.md
项目概述 MinerU Tianshu(天枢)是一个**企业级 AI 数据预处理平台**,将非结构化数据转换为 AI 可用的结构化格式(Markdown + JSON): - 📄 文档:PDF、Word、Excel、PPT(MinerU 原生解析 DOCX/PPTX;旧版 .doc/.ppt 经 LibreOffice 转换)、Excel .xlsx/.xls 与 HTML/TXT/CSV/EPUB
joelhooks/swarm-tools/AGENTS.md
Make it scannable (headers, bullets, bold for key points) **MANDATORY: Pull a quote from pdf-brain.** This is NOT optional: ```bash pdf-brain_search(query=" ", limit=5) ``` Add the quote
usemoss/moss/AGENTS.md
Vercel moss-bun/ — Production Bun semantic search application moss-llamaindex/ — LlamaIndex + Liteparse full-stack PDF search demo next-js/ — Next.js 16 browser-based semantic search UI (@moss-dev/moss-web) pipecat
typedef-ai/fenic/AGENTS.md
Semantic templates use Jinja2 `{{ var }}` + matching column kwargs:** `fc.semantic.predicate("... {{ x }} ...", x=fc.col("x"))`. `parse_pdf` is **`fc.semantic.parse_pdf`** (under `semantic`, not `markdown`). - **Local extras for heavier operators:** `fc.semantic.parse_pdf
typedef-ai/fenic/docs/agents.md
Authoritative guidance for AI assistants using, describing, or generating code with fenic.
ggozad/haiku.rag/AGENTS.md
# haiku.rag Project Guide Agentic RAG system built on LanceDB with hybrid search, multiple embedding
7onez/cti-expert/AGENTS.md
held back ▼ evidence_report.render_cluster_report ──► assessment.md / assessment.json (+ whois/ .json sidecar) ▼ tools/house_report.py ──► cases/ /report/CTI-REPORT-*.{md,pdf,docx} (IntelReport/IntelGraph) scripts/build_report_data.py ──► REPORT.json ──► generate-cti-{html,iocs,docx-hybrid}.py ``` - **Two `intel.py` files.** `scripts/backend/intel.py
nodetool-ai/nodetool/docs/AGENTS.md
Architecture of the NodeTool agent system — planning, execution, tools, skills, and workflow integration.
dbt-labs/dbt-charts/AGENTS.md
default: `charts/` | | `dct render ` | Compile + execute + write static exports (svg, html, png, pdf, json) | | `dct serve` | Start local server; use its URL for browser previews | | `dct describe ` | Summarize a board
VILA-Lab/FigMirror/.codex/AGENTS.md
reference paper figure onto the user's own data, producing a camera-ready PDF and a self-contained matplotlib script. ## What lives here | Path | What it is | |------|------------| | `.codex/skills/figmirror/SKILL.md` | Codex runtime
microsoft-foundry/foundry-samples/samples/python/hosted-agents/bring-your-own/activity/github-copilot/AGENTS.md
JSON file under `$HOME` so they survive sandbox idle/recycle - `files.py` — attachment text extraction (PDF / DOCX / PPTX), inlined into the prompt by `main.py` - `Dockerfile` — container definition ## Development workflow The **Azure Developer
openai/GABRIEL/AGENTS.md
response, product listing, archival page, technology, job title, legal case, image, audio clip, or PDF. Keep an explicit stable source ID and preserve useful provenance or grouping columns beside
LimHyungTae/awesome-claudecode-paper-proofreading/AGENTS.md
missing assets when doing the workspace audit. 6. If the user provides a compiled PDF, use it during paper proofreading for figure placement, caption polish, and PDF-visible leftovers that
Community-Access/accessibility-agents/AGENTS.md
multilingual accessibility ### Document Accessibility Team Led by `document-accessibility-wizard`, handles Office and PDF audits: - `word-accessibility` - Microsoft Word (.docx) - `excel-accessibility` - Microsoft Excel (.xlsx) - `powerpoint-accessibility` - Microsoft PowerPoint (.pptx
Community-Access/accessibility-agents/.claude/AGENTS.md
XLSX scanning and remediation (XLSX-* rules) - `powerpoint-accessibility` - PPTX scanning and remediation (PPTX-* rules) - `pdf-accessibility` - PDF scanning and remediation (PDFUA.*, PDFBP.*, PDFQ.* rules) - `office-scan-config` - Office scan configuration
Community-Access/accessibility-agents/claude-code-plugin/AGENTS.md
XLSX scanning and remediation (XLSX-* rules) - `powerpoint-accessibility` - PPTX scanning and remediation (PPTX-* rules) - `pdf-accessibility` - PDF scanning and remediation (PDFUA.*, PDFBP.*, PDFQ.* rules) - `office-scan-config` - Office scan configuration
langchain-ai/langchain-google/AGENTS.md
Part.from_bytes` type to pass a variety of data types (images, audio, video, pdf). ```python from google.genai import types with open('path/to/small-sample.jpg', 'rb') as f: image_bytes = f.read() response = client.models.generate
NVIDIA/cuda-q-academic/AGENTS.md
need a GPU?", recommend Brev first. The launchable URL and step-by-step PDF are linked from [README.md](README.md). - **qBraid** — hosted Jupyter with CUDA-Q support; a good second option
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.