gitdiagram
ahmedkhaleel2004/gitdiagram/CLAUDE.md
GitHub repository into an interactive Mermaid architecture diagram, plus narrated explainer videos, a public MCP server and sponsor ad slots. It is **one Next.js 16 App Router application** (React
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.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.
ahmedkhaleel2004/gitdiagram/CLAUDE.md
GitHub repository into an interactive Mermaid architecture diagram, plus narrated explainer videos, a public MCP server and sponsor ad slots. It is **one Next.js 16 App Router application** (React
transitive-bullshit/agentic/CLAUDE.md
agentic.config.{ts,js,json}` files to define: - Project name and metadata - Origin adapter (MCP server or OpenAPI spec) - Tool configurations and permissions - Pricing plans and rate limits - Authentication requirements
storytold/filmcraft/CLAUDE.md
crates/engine`): id, label, menu path, shortcut, params, enabled(), run(). UI, CLI, control channel and MCP all dispatch by id. - **Everything is agent-drivable:** every interactive widget registers an automation
ag-ui-protocol/ag-ui/CLAUDE.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
Steady10 mentions in 2 weeks
No other project uses it yet
storytold/wordcraft/CLAUDE.md
engine` | Session, undo, **command registry**, Word feature catalog, samples, I/O dispatch | | L5 | `mcp` | MCP server (headless or bridged to the app) | | L6 | `ui-egui` | Word-style egui front end (swappable
Arindam200/awesome-ai-apps/CLAUDE.md
args": ["-y", "@modelcontextprotocol/server-github"], "env": {"GITHUB_PERSONAL_ACCESS_TOKEN": os.environ["TOKEN"]} } ) as server: agent = Agent(mcp_servers=[server], ...) ``` Example: `mcp_ai_agents/github_mcp_agent/main.py`, `mcp_ai_agents/mcp_starter/main.py` ### Framework-Specific Patterns **Agno Framework** (most
GLips/Figma-Context-MCP/CLAUDE.md
Framelink MCP for Figma Framelink MCP for Figma is a Model Context Protocol (MCP) server that gives AI coding tools (Cursor, etc.) access to Figma design data. It fetches Figma
No other project uses it yet
organicmaps/organicmaps/CLAUDE.md
when a hash is available, and trusted as-is otherwise -- they come from our servers. On-disk corruption afterwards is out of OM scope: crashing on corrupted data is fine
CoplayDev/unity-mcp/CLAUDE.md
Plugin (MCPForUnity/) ↓ Unity Editor API Scene, Assets, Scripts ``` **Two codebases, one system:** - `Server/` - Python MCP server using FastMCP - `MCPForUnity/` - Unity C# Editor package ### Three Layers on the Python Side
No other project uses it yet
mauriceboe/NOMAD/CLAUDE.md
server/`** (`@trek/server`) — NestJS API (Express adapter), SQLite via `better-sqlite3`, WebSocket sync, built-in MCP server, sandboxed plugin runtime. - **`client/`** (`@trek/client`) — React 19 + Vite + Zustand + Tailwind PWA, offline-first
mauriceboe/NOMAD/server/CLAUDE.md
from `server/`) ```bash npm run dev # scripts/dev.mjs: tsc -w then node --watch dist/index.js (server on :3001) npm run build # scripts/build.mjs — emits even on type errors (see below) npm run typecheck
mauriceboe/NOMAD/shared/CLAUDE.md
keys and `evaluatePermission(level, { isAdmin, isOwner, isMember })` the one decision rule. The server's `PermissionsService` and `@RequirePermission(action: PermissionKey)` are built on them, so a new action starts here
storytold/lightcraft/CLAUDE.md
crates/engine`): id, label, menu path, shortcut, params, enabled(), run(). UI, CLI, control channel and MCP all dispatch by id. Every slider is a `develop` control spec. - **Long-running work shows
grokability/snipe-it/CLAUDE.md
rather than explaining obvious details. === boost rules === # Laravel Boost ## Tools - Laravel Boost is an MCP server with tools designed specifically for this application. Prefer Boost tools over manual alternatives like
Steady15 mentions in 2 weeks
No other project uses it yet
yusufkaraaslan/Skill_Seekers/CLAUDE.md
context-local (a `ContextVar` layered over the unchanged base singleton) — thread/async safe for the MCP server; propagate to worker threads via `copy_context`. ### Standalone subsystems (outside `cli/`) Four top-level
AndyMik90/Aperant/CLAUDE.md
debug # Debug mode with verbose output npm run dev:mcp # Electron MCP server for AI debugging # Project data: .auto-claude/specs/ (gitignored
semaphoreui/semaphore/.claude/CLAUDE.md
consider any solution that introduces security risks. ## How to do research Use MCP server `research` if your asks you to research something. ## Writing Tests Use `github.com/stretchr/testify/assert` (and `require` when
No other project uses it yet
Open-LLM-VTuber/Open-LLM-VTuber/CLAUDE.md
src/open_llm_vtuber/mcpp/`): - Tool execution and server registry - JSON detection and parameter extraction - Integration with various MCP servers for extended functionality ## Key Development Patterns ### Error Handling The codebase uses the missing `_cleanup
Steady5 mentions in 2 weeks
No other project uses it yet
yichuan-w/LEANN/CLAUDE.md
without rebuild - `leann-backend-diskann/`: DiskANN backend for larger-than-memory datasets - `leann-mcp/`: MCP server for Claude Code integration Backends are auto-discovered via `leann-backend-*` naming convention
ccfos/nightingale/CLAUDE.md
scripts/build-sandbox-assets.sh`). `/mcp` and `/a2a` endpoints are in `aiagent/a2a` and use the external `n9e-mcp-server` toolset in-process. - **Other top-level pkgs**: `pushgw/` (remote-write receiver + writers + ident/host registry), `tsdb
Steady3 mentions in 2 weeks
No other project uses it yet
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.