buzz
block/buzz/AGENTS.md
Minimal ACP-compliant agent (non-streaming, tool-calls-as-output) buzz-dev-mcp # Developer MCP server — shell + file-edit tools buzz-persona # Agent persona packs buzz-workflow # YAML-as-code
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
block/buzz/AGENTS.md
Minimal ACP-compliant agent (non-streaming, tool-calls-as-output) buzz-dev-mcp # Developer MCP server — shell + file-edit tools buzz-persona # Agent persona packs buzz-workflow # YAML-as-code
block/buzz/desktop/src/features/agents/AGENTS.md
host requires an installed `buzz-backend-*` provider, and without one `WhereToRunSection` never renders, so "server" would name a concept the owner has never been shown; when it *is* remote they
can1357/oh-my-pi/AGENTS.md
promise | | Binary lookup | `$which("git")` from `@oh-my-pi/pi-utils` | `spawnSync(["which", "git"])` | | HTTP server | `Bun.serve()` | `http.createServer()` | | SQLite | `bun:sqlite` | `better-sqlite3` | | Hashing | `Bun.hash()`, `Bun.password.*`, WebCrypto | `node:crypto` | | Path resolution
alibaba/nacos/AGENTS.md
Remote Agent Discovery Protocol Spec](./specs/en/ai/rad-protocol-spec.md), [Agent API Spec](./specs/en/ai/agent-api-spec.md), [Agent Storage Spec](./specs/en/ai/agent-storage-spec.md), [MCP Server Spec](./specs/en/ai/mcp-server-spec.md), [A2A Agent Spec](./specs/en/ai/a2a-agent-spec.md), [Prompt Spec](./specs/en/ai/prompt-spec.md), [Skill Spec](./specs/en/ai/skill-spec.md), [AgentSpec Spec
vercel/turborepo/apps/docs/AGENTS.md
behavior, analytics, and the Remote Cache page action app-owned. - Do not advertise an MCP server unless Turborepo provides one. # This is NOT the Next.js you know This version
topoteretes/cognee/AGENTS.md
search "..." # low level uv run cognee-cli -ui # Launches UI, backend API, and MCP server together ``` - Start the FastAPI server directly: ```bash uv run python -m cognee.api.client ``` - Run tests
langchain-ai/deepagents/AGENTS.md
langchain-ai/docs` repo; a local checkout supports file search, and the docs MCP server is configured in `.mcp.json` ## OpenWiki This repository has a generated `openwiki/` evidence index
openai/openai-agents-python/AGENTS.md
MCPServerManager`, request serialization, tool caching or filtering, transport retries, cancellation, or cleanup, read [Local MCP server lifecycle](.agents/references/local-mcp-server-lifecycle.md). - For trace or span context, processors, export, flush, shutdown, sensitive data
openai/openai-agents-python/docs/agents.md
tool_choice`. | | `tools` | no | Tools the agent can call. See [Tools](tools.md). | | `mcp_servers` | no | MCP servers that provide MCP-backed tools to the agent. See the [MCP guide](mcp.md
openai/openai-agents-python/docs/ja/agents.md
settings` | いいえ | `temperature`、`top_p`、`tool_choice` などのモデル調整パラメーターです。 | | `tools` | いいえ | エージェントが呼び出せるツールです。[ツール](tools.md)を参照してください。 | | `mcp_servers` | いいえ | MCP ベースのツールをエージェントに提供する MCP サーバーです。[MCP ガイド](mcp.md)を参照してください。 | | `mcp_config` | いいえ | スキーマの strict
openai/openai-agents-python/docs/ko/agents.md
모델 조정 매개변수 | | `tools` | 아니요 | 에이전트가 호출할 수 있는 도구. [도구](tools.md)를 참조하세요. | | `mcp_servers` | 아니요 | 에이전트에 MCP 기반 도구를 제공하는 MCP 서버. [MCP 가이드](mcp.md)를 참조하세요. | | `mcp
openai/openai-agents-python/docs/zh/agents.md
模型调优参数,例如 `temperature`、`top_p` 和 `tool_choice`。 | | `tools` | 否 | 智能体可以调用的工具。请参阅[工具](tools.md)。 | | `mcp_servers` | 否 | 为智能体提供基于 MCP 的工具的 MCP 服务器。请参阅 [MCP 指南](mcp.md)。 | | `mcp_config` | 否 | 微调
anthropics/knowledge-work-plugins/partner-built/zoom-plugin/AGENTS.md
workflow for Claude ## Repo Shape - `.claude-plugin/plugin.json` — Claude plugin manifest - `.mcp.json` — bundled Zoom MCP server definition - `skills/` — all plugin skills and supporting references - `README.md` — user-facing overview - `CONNECTORS.md` — bundled
EveryInc/compound-engineering-plugin/AGENTS.md
canonical source for new releases. - Run `bun run release:validate` if agents, commands, skills, MCP servers, or release-owned descriptions/counts may have changed. - When removing a skill, agent, or command
activepieces/activepieces/AGENTS.md
Activepieces Open-source AI-first workflow automation platform. Self-hosted or cloud. 400+ pieces. MCP support. ## Architecture (Non-Obvious Rules) - **Multi-tenant**: Platform → Projects → Users. ALL queries MUST filter
modelcontextprotocol/python-sdk/AGENTS.md
root project's runtime dependencies are dynamic (the published `mcp` wheel exact-pins `mcp-types`), so `uv add` cannot edit them — add the requirement to `[tool.hatch.metadata.hooks.uv-dynamic-versioning].dependencies
pascalorg/editor/AGENTS.md
/viewer/capture` | | `packages/editor` | Editor UI components reused by the standalone app and embedders | | `packages/mcp` | MCP server and scene storage adapters | | `apps/editor` | Standalone editor app — composes `viewer` + `editor` + tools | ## Where to look
coleam00/Archon/AGENTS.md
parallel context switch. - Workflow AI nodes start without ambient skills, skill-like plugins, or MCP servers. A node receives only the skills, plugins, and MCP servers it explicitly names. Enforce
czlonkowski/n8n-mcp/AGENTS.md
configuration. ## Project Structure & Module Organization Core TypeScript lives in `src/`. Important subsystems include: - `src/mcp/` — MCP server, request handlers, tool definitions and documentation, and bundled skills - `src/database/` — SQLite adapters, repositories, FTS5
1Panel-dev/MaxKB/AGENTS.md
JSON-RPC endpoint (`initialize`, `tools/list`, `tools/call`) routed through `chat.mcp.tools.MCPToolHandler`. MaxKB also *consumes* external MCP servers via `mcp_node` in the workflow and `langchain-mcp-adapters`. ### Frontend (`ui/`) Two SPAs built
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.