DeskcommCRM
melgarafael/DeskcommCRM/CLAUDE.md
tenant atendem, qualificam e movem o funil junto com humanos; CRM inteiro exposto via MCP. Monetização = self-host em VPS (parceria HostGator), não assinatura. Arquitetura multi-tenant com RLS desde
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.
melgarafael/DeskcommCRM/CLAUDE.md
tenant atendem, qualificam e movem o funil junto com humanos; CRM inteiro exposto via MCP. Monetização = self-host em VPS (parceria HostGator), não assinatura. Arquitetura multi-tenant com RLS desde
getzep/zep/integrations/CLAUDE.md
failure. Use the bundled **building-with-zep** skill and the **zep-docs MCP server** to confirm exact SDK signatures before writing Zep code. ## Choosing the extension point Implement the framework
campfirein/byterover-cli/CLAUDE.md
campfirein/brv-transport-client` - Agent pool manages forked child processes per project; task routing in `server/infra/process/` - MCP server in `server/infra/mcp/` exposes tools via Model Context Protocol; `tools/` subdir has dedicated implementations (`brv-query
aipotheosis-labs/aci/CLAUDE.md
providing 600+ integrations for AI agents. It serves as infrastructure for Unified MCP (Model Context Protocol) servers and VibeOps automated DevOps workflows. The platform handles multi-tenant authentication, granular permissions
statamic/cms/CLAUDE.md
their docs pages in `resources/js/stories/docs/*.mdx`. - `npm run storybook` starts Storybook along with its MCP server at `http://localhost:6006/mcp` (configured in `.mcp.json`). - Use its documentation tools to look
eastlondoner/vibe-tools/CLAUDE.md
task_id"`) **Model Context Protocol (MCP) Commands:** Use the following commands to interact with MCP servers and their specialized tools: `vibe-tools mcp search " "` - Search the MCP Marketplace for available
makenotion/notion-mcp-server/CLAUDE.md
Claude Code when working with this repository. ## Project Overview This is the Notion MCP Server - an [MCP (Model Context Protocol)](https://spec.modelcontextprotocol.io/) server that exposes the [Notion
amantus-ai/vibetunnel/mac/CLAUDE.md
prefix to identify frontend-originated logs ## XcodeBuildMCP Usage Guide XcodeBuildMCP is an MCP (Model Context Protocol) server that provides comprehensive Xcode build and automation capabilities. It's the recommended
ruvnet/RuVector/CLAUDE.md
cleanup, full) ## Project Structure Quick Reference | Directory | Contents | |-----------|----------| | `crates/` | Rust crates (ruvector-cnn, mcp-brain-server, sparsifier, mincut, solver, etc.) | | `npm/packages/` | NPM packages (@ruvector/cnn, rvf, pi-brain, etc.) | | `ui/ruvocal/` | RuVocal
Steady3 mentions in 2 weeks
1 project uses a version of this
NateBJones-Projects/OB1/CLAUDE.md
docs, examples, seed data, UI copy, prompts, walkthroughs, and generated assets clean and professional. - **MCP servers must be remote (Supabase Edge Functions), not local.** Never use `claude_desktop_config.json`, `StdioServerTransport`, or local
supabase/supabase-js/.claude/CLAUDE.md
exec nx test`) - avoids using globally installed CLI - You have access to the Nx MCP server and its tools, use them to help the user - For Nx plugin best practices
algorithmicsuperintelligence/optillm/CLAUDE.md
lora1+lora2` - Advanced decoding: `{"decoding": "cot_decoding", "k": 10}` ### Plugin Configuration - MCP: `~/.optillm/mcp_config.json` for Model Context Protocol servers - SPL: Built-in system prompt learning for solving strategies - Memory: Automatic unbounded
spacering-net/codeg/CLAUDE.md
server --lib cargo clippy --no-default-features --features server-bin --bin codeg-server --lib -- -D warnings # codeg-mcp 协作伴生进程(多智能体委托) cargo check --no-default-features --features mcp-bin --bin codeg
Surging9 mentions in 2 weeks
1 project uses a version of this
langroid/langroid/CLAUDE.md
mcp_tool decorator async def handle_async(self): # Get raw result from MCP server result = await self.call_tool_async() # Option 1: Return processed result to LLM (continues conversation) return
Steady14 mentions in 2 weeks
No other project uses it yet
rotki/rotki/CLAUDE.md
external CDP client (Chrome DevTools, `connectOverCDP` from Playwright or Puppeteer, an MCP devtools server) can inspect and drive the running app. It is off unless
anthropics/anthropic-sdk-python/CLAUDE.md
code blocks in `README.md` and `api.md`. | | `./scripts/test` | Runs the suite. Starts a Steady mock server on port 4010 unless `TEST_API_BASE_URL` is set. | ### Test matrix - **Python and Pydantic
skyhook-io/radar/CLAUDE.md
their own screens, like `/cnpg` or `/capacity`) | [docs/INTEGRATION_GUIDE.md](docs/INTEGRATION_GUIDE.md#3-workspace-integrations) — the shared server, UI and action pieces to import, and what is not shared yet; [DESIGN.md](DESIGN.md#unknown
gadievron/raptor/CLAUDE.md
full list. 3. If the `sage_inception` tool is present in your available MCP tools, load `core/sage/CLAUDE.md` (persistent-memory workflow). If absent, SAGE is not installed — skip silently
thevangelist/dembrandt/CLAUDE.md
frameworks, logoInstances, manifest, siteName } ``` ## Dependencies - `playwright-core` — browser automation (browsers install separately) - `@modelcontextprotocol/sdk`, `zod` — MCP server; both must stay regular dependencies, optional peers broke `npx` installs - `chalk` — terminal colors - `commander
simonlin1212/TradingAgents-astock/CLAUDE.md
一路污染记忆日志与绩效统计。 ### 探测 mootdx 不能覆写用户配置(v0.5.10,v0.5.12 重构) `StdQuotes.__init__` 里有 `config.set('BESTIP', {'HQ': self.server})`——**每建一次带 `server` 的 client 都会持久化写进 mootdx 配置文件**。逐台探测会把用户原本配好的服务器 一路覆写,最后留下一台死的,还会连累同机其它用 mootdx 的程序。 用 `with _preserve_mootdx
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.