How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
LangChainAGENTS.mdlangchain-ai/deepagents/examples/deploy-mcp-docs-agent/AGENTS.md
Deep Agents. Your job is to answer developer questions by using the available MCP documentation tools before relying on general knowledge. ## Core behavior - Prefer the docs MCP tools for factual
LangChainAGENTS.mdlangchain-ai/deepagents/examples/nvidia_deep_agent/src/AGENTS.md
topic at a time. 2. **data-processor-agent**: Handles data analysis, machine learning, and document processing using GPU-accelerated NVIDIA tools. This agent has specialized skills (cuDF analytics, cuML machine
LangChainAGENTS.mdlangchain-ai/deepagents/libs/code/AGENTS.md
intentionally replace concrete app methods with `MagicMock` or `AsyncMock`, prefer `monkeypatch.setattr(...)` or one small documented dynamic helper over repeated `cast("Any", app)` expressions. Assert on local mock variables instead
LangChainAGENTS.mdlangchain-ai/deepagents/libs/talon/deepagents_talon/defaults/agents/external-research/AGENTS.md
Find concise cited evidence on the web or in largely public sources without private context.
LangChainAGENTS.mdlangchain-ai/deepagents/libs/talon/deepagents_talon/defaults/agents/internal-research/AGENTS.md
Find concise cited evidence in internal or semi-trusted sources using available read tools.
labringAGENTS.mdlabring/FastGPT/AGENTS.md
应用(前端 + API 路由) - `projects/code-sandbox/` - Bun + Hono 代码执行沙箱服务 - `projects/mcp_server/` - Model Context Protocol 服务器实现 ### 关键目录 - `document/` - 文档站点(NextJS 应用及内容) - `plugins/` - 外部插件(模型、爬虫等) - `deploy/` - Docker 和 Helm 部署配置 - `test/` - 集中的测试文件和工具 ## 开发命令
OpenAIAGENTS.mdopenai/openai-agents-python/AGENTS.md
data, private prompts or responses, tool payloads, or recordings in code, tests, snapshots, logs, documentation, or shared artifacts. Use approved credential injection only for explicitly authorized live tests
OpenAIAGENTS.mdopenai/openai-agents-python/docs/agents.md
capabilities to the agent | [Tools](tools.md) | | Run an agent against a real repo, document bundle, or isolated workspace | [Sandbox agents quickstart](sandbox_agents.md) | | Decide between manager-style orchestration and handoffs | [Agent
kestra-ioAGENTS.mdkestra-io/kestra/AGENTS.md
Coding Agent Guidelines for Kestra Open Source Edition This document provides essential information for AI coding agents working on the Kestra codebase. **IMPORTANT — READ FIRST** - **Act as a Senior Software
BloopAIAGENTS.mdBloopAI/vibe-kanban/AGENTS.md
Files published to the npm CLI package. - `scripts/`: Dev helpers (ports, DB preparation). - `docs/`: Documentation files. ### Crate-specific guides - [`crates/remote/AGENTS.md`](crates/remote/AGENTS.md) — Remote server architecture, ElectricSQL integration, mutation patterns, environment variables
BloopAIAGENTS.mdBloopAI/vibe-kanban/docs/AGENTS.md
technical writing rule You are an AI writing assistant specialised in creating exceptional technical documentation using Mintlify components and following industry-leading technical writing practices. ## Working relationship - You can push
Hugging FaceAGENTS.mdhuggingface/lerobot/AGENTS.md
approval), `latest_deps_tests.yml` (daily lockfile upgrade), `security.yml` (TruffleHog), `release.yml` (PyPI publish on tags). - **`docs/source/`** — HF documentation (`.mdx` files). Per-policy READMEs, hardware guides, tutorials. Built separately via `docs-requirements.txt` and CI workflows
gastownhallAGENTS.mdgastownhall/beads/AGENTS.md
Claim your task atomically**: `bd update --claim` 3. **Work on it**: Implement, test, document 4. **Discover new work?** Create linked issue: - `bd create "Found bug" --description="Details about what
manaflow-aiAGENTS.mdmanaflow-ai/cmux/skills/cmux-browser/AGENTS.md
secrets. - Refresh the installed skill through the supported installer when the CLI and cached documentation disagree; never repair stale examples by weakening CLI surface validation
Kilo-OrgAGENTS.mdKilo-Org/kilocode/AGENTS.md
only after a Java-version or missing-Java failure. | | CI/local guards | Run affected guards documented above, such as `bun run knip`, `bun run check-kilocode-change`, `bun run script/check-opencode-annotations.ts --worktree
VercelAGENTS.mdvercel/ai/AGENTS.md
unified interface for multiple AI providers and framework integrations. - **Repository**: https://github.com/vercel/ai - **Documentation**: https://ai-sdk.dev/docs - **License**: Apache-2.0 ## Repository Structure This is a **monorepo** using pnpm workspaces
deepset-aiAGENTS.mddeepset-ai/haystack/AGENTS.md
header`, `parent_headers`, and split positions; add new keys only for existing downstream contracts ## Documentation - Keep inline comments and private-helper docs to what is non-obvious — remove restatements, keep
deepset-aiAGENTS.mddeepset-ai/haystack/docs-website/AGENTS.md
docs-website/ Guidelines ## Documentation - Keep `docs-website` API names, import paths, and links current with public exports — link data-class symbols to anchored API docs and verify every MDX link
MicrosoftAGENTS.mdmicrosoft/winget-cli/AGENTS.md
Keep each PR focused on one logical change. 3. Include or update tests and documentation when the change affects behavior, command output, user guidance, or public APIs. 4. Summarize validation
EveryIncAGENTS.mdEveryInc/compound-engineering-plugin/AGENTS.md
that is not readily recoverable from the final code, tests, types, comments, or existing documentation, and losing it would plausibly cause recurrence, material risk, or substantial rediscovery. Apply this counterfactual
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.
