gold
This project uses OpenLore for persistent architectural memory.
Call `orient " "` (via the openlore MCPserver, or
`npx openlore orient --json`) **before touching a module you have not yet read
3656mo agoReviewMountCreate a free account to mount
binary for running a small home server: CLI, TUI, web dashboard, and
an MCPserver, with no database and nothing running on the machines it watches.
## Verify before claiming anything
3659mo agoReviewMountCreate a free account to mount
taskdog-ui**: CLI (Click + Rich) and TUI (Textual), depends on core + client.
- **taskdog-mcp**: MCPserver for Claude Desktop (depends on client).
**Communication**: CLI/TUI/MCP reach all data through the HTTP
36412mo agoReviewMountCreate a free account to mount
Model Context Protocol integration:
- `StdioMCPClient.swift` — local process transport
- `HTTPMCPClient.swift` — HTTP/SSE transport
- `MCPRegistry.swift` — manages configured MCPservers
- `MCPToolAdapter.swift` — adapts MCP tools to the `AgentTool` protocol used by Ask
### Data Storage
| Store
3646mo agoReviewMountCreate a free account to mount
gold
This project uses OpenLore for persistent architectural memory.
Call `orient " "` (via the openlore MCPserver, or
`npx openlore orient --json`) **before touching a module you have not yet read
3596mo agoReviewMountCreate a free account to mount
Project: mcp-server-macos-use
## Build Rules (overrides global CLAUDE.md)
After making any changes to `Sources/`, **always rebuild immediately**:
```
xcrun --toolchain com.apple.dt.toolchain.XcodeDefault swift build 2>&1 | tail
3579mo agoReviewMountCreate a free account to mount
install and use file search tools for best results. If needed, use the docs MCPserver as defined in `.mcp.json` for programmatic access.
- **Contributing Guide:** [`.github/CONTRIBUTING.md`](https://docs.langchain.com/oss/python/contributing/overview)
## Important
3548mo agoReviewMountCreate a free account to mount
this repository.
## Project Overview
This is an Obsidian plugin that implements MCP (Model Context Protocol) servers to enable Claude Code and Claude Desktop integration with Obsidian vaults. The plugin provides
34717mo agoReviewMountCreate a free account to mount
BEFORE grep/find or reading files when you need to understand or locate code:
- **MCP tool** (when available): `codegraph_explore` answers most code questions in one call — the relevant symbols' verbatim
34745d agoReviewMountCreate a free account to mount
every block has deltas: some arrive complete in `content_block_start` (`redacted_thinking`, server-tool and MCP tool *results*, and new block types keep appearing), so default to passing whole
34659d agoReviewMountCreate a free account to mount
project unit
# Zambda integration tests (needs Auth0 test secrets; globalSetup starts its own server + runs the leak gate)
cd packages/zambdas && npx vitest run --project integration
```
### E2E Tests (Playwright)
```bash
34322mo agoReviewMountCreate a free account to mount
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
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.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.