kimi-cli
MoonshotAI/kimi-cli/AGENTS.md
software engineering workflows. It supports an interactive shell UI, ACP server mode for IDE integrations, and MCP tool loading. ## Tech stack - Python 3.12+ (tooling configured for 3.14) - CLI framework: Typer
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
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.
MoonshotAI/kimi-cli/AGENTS.md
software engineering workflows. It supports an interactive shell UI, ACP server mode for IDE integrations, and MCP tool loading. ## Tech stack - Python 3.12+ (tooling configured for 3.14) - CLI framework: Typer
MoonshotAI/kimi-cli/tests_e2e/AGENTS.md
runs the flow until `END`. - W-36 MCP: use a Python fastmcp test server, load via `--mcp-config-file`, verify tool works. **Resilience and Errors** - W-37 Invalid JSON: malformed
apereo/cas/AGENTS.md
local branch | | [`cas-interrupt-notifications`](.claude/skills/cas-interrupt-notifications/SKILL.md) | `support/cas-server-support-interrupt*` | | [`cas-ldap`](.claude/skills/cas-ldap/SKILL.md) | LDAP modules | | [`cas-mcp-server`](.claude/skills/cas-mcp-server/SKILL.md) | `support/cas-server-support-mcp` | | [`cas-oauth-oidc-authentication`](.claude/skills/cas-oauth-oidc-authentication/SKILL.md) | OAuth/OIDC/UMA client authentication, access-token-protected endpoints, `OAuth20UserProfile
modelcontextprotocol/inspector/AGENTS.md
Inspector V2 This is an application for inspecting MCP servers. It has four client surfaces — Web, TUI, one-shot CLI, and the experimental connection CLI (`mcpdo`) — over a shared `core
tambo-ai/tambo/docs/AGENTS.md
authentication/** (8 pages including index) - Auth.js, Auth0, Clerk, Supabase, Neon, WorkOS, Better Auth - connect-mcp-servers - Single page (not in subfolder) - **self-hosting/** (9 pages including index) - quickstart, environment-variables
No other project uses it yet
tambo-ai/tambo/react-sdk/AGENTS.md
return rich content including images, audio, or mixed media. This is particularly useful for MCP tools that already return content in the proper format. ### Key Hook System - **`useTambo()`** - Primary hook
No other project uses it yet
langchain-ai/open-swe/AGENTS.md
composing generic capabilities such as plugins, automations, skills, or external MCP servers. First check whether existing capabilities, with small generic additions if needed, can deliver the feature. - Before changing
Steady12 mentions in 2 weeks
No other project uses it yet
microsoft/fluentui-system-icons/AGENTS.md
affected`) instead of using the underlying tooling directly - You have access to the Nx MCP server and its tools, use them to help the user - When answering questions about
Steady13 mentions in 2 weeks
1 project uses a version of this
go-vgo/robotgo/AGENTS.md
build linux ├── pub/ # pure-Go shared config/helpers: KeySleep, MouseSleep, DisplayID, MilliSleep, Sleep, SetDelay ├── mcp/ # MCP server package (mcp.go, a bare `package mcp` stub) ├── cuse/ # computer/, browser/, gui/ — empty placeholder dirs
No other project uses it yet
google/adk-recipes/core/python/adk-voice-agent/AGENTS.md
docs/architecture.md#thread-lifecycle) | | 7 | **One MCP gateway with server-held tokens.** Harnesses see one MCP server. The gateway proxies [`.mcp.json`](.mcp.json) servers as ` __ `, attaching the user's token
google/adk-recipes/core/python/adk-voice-agent/sandbox/home/AGENTS.md
Talking to the user Progress, card, and Drive tools live on the `voice_agent` MCP server. - **Report findings, not activity.** Call `update_user` with one short spoken sentence when
Steady2 mentions in 2 weeks
1 project uses a version of this
google/adk-recipes/core/python/genmedia-for-commerce/AGENTS.md
only tools for the panel and background jobs the panel polls. - `infra/gemini_enterprise.py` registers an MCP server on Cloud Run (` /mcp`) in a Gemini Enterprise app; change `DISPLAY_NAME` and `STUDIO
Steady2 mentions in 2 weeks
1 project uses a version of this
google/adk-recipes/core/python/long-horizon-harness/AGENTS.md
gateways (Telegram/Discord/Slack/WhatsApp/Signal), sandbox backends other than the managed Sandboxes backend + local fallback, browser/computer-use/image-gen/video-gen/TTS/voice tools, MCP server, TUI, ACP. ## Project Layout ``` lha/ ├── horizon/ # importable Python package (`import horizon`); outer repo
Steady2 mentions in 2 weeks
1 project uses a version of this
polarsource/polar/server/AGENTS.md
PostgreSQL, Redis, and S3 storage. ## Quick Commands ```bash uv run task api # Start API server (http://127.0.0.1:8000) uv run task worker # Start background worker uv run task test
Steady2 mentions in 2 weeks
No other project uses it yet
electric-sql/electric/AGENTS.md
OPENAI_API_KEY`): ```sh ./scripts/dev.sh build # install + build typescript-client, agents-runtime, # agents-mcp, agents-server, agents ./scripts/dev.sh start # docker + 5 dev processes; Ctrl-C stops everything ./scripts/dev.sh start --with
alvinunreal/oh-my-opencode-slim/AGENTS.md
entry point │ ├── config/ # Constants, schemas, MCP defaults │ ├── hooks/ # OpenCode lifecycle hooks │ ├── mcp/ # MCP server definitions │ ├── multiplexer/ # Tmux/Zellij pane integration for child sessions │ ├── skills/ # Skill definitions (included in package publish) │ ├── tools
hyperdxio/hyperdx/AGENTS.md
packages/api` - Express backend (Node.js 22+, MongoDB for metadata, ClickHouse for telemetry). Also hosts the **MCP server**, **External API v2**, and **OpAMP server** as sub-applications. - `packages/common-utils` - Shared TypeScript utilities
No other project uses it yet
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.