interface** (`fli/cli/`) - Typer-based command line tool with `flights` and `dates` commands
- **MCPserver** (`fli/mcp/`) - Model Context Protocol server for AI assistant integration
- **Core utilities** (`fli/core/`) - Shared parsing and building
3.2k43d agoReviewMountCreate a free account to mount
graph
**IMPORTANT: This project has a knowledge graph. ALWAYS use the `code-review-graph` MCP tools BEFORE using Grep, Glob, Read, or broad filesystem exploration.**
The graph is faster, cheaper
3.2k8mo agoReviewMountCreate a free account to mount
needed
- Limit tool search to maximum 2 searches per turn to avoid overhead
- Essential MCPservers (nogic, code-graph) are never disabled
- Non-essential servers (EXA, Apify, Playwright) load
3.1k5mo agoReviewMountCreate a free account to mount
apple-mcp Development Guidelines
## Commands
- `bun run dev` - Start the development server
- No specific test or lint commands defined in package.json
## Code Style
### TypeScript Configuration
- Target: ESNext
- Module: ESNext
- Strict
3.1k19mo agoReviewMountCreate a free account to mount
page sells **how that runtime gains self-driving agents** — not how a plugin or MCPserver works.
## Per-harness page structure
Every harness page (`/harnesses/ `) follows the same three-section
3k6mo agoReviewMountCreate a free account to mount
import`.
- Svelte 5: runes syntax only — no legacy Svelte patterns. Use the Svelte MCPserver / `svelte-file-editor` agent for any `.svelte` or `.svelte.js`/`.svelte.ts` work.
- Prose: Canadian English
3k9mo agoReviewMountCreate a free account to mount
writes .mcp.json/AGENTS.md/skill into a project; its `.mcp.json` entry runs `lowdefy mcp`, a stdio MCPserver that routes each tool call to the right app/worktree's dev server and starts
3k11d agoReviewMountCreate a free account to mount
canvas (`@eventcatalog/visualiser/studio`)
And one app:
- `@eventcatalog/studio-web` (`apps/studio-web`, MIT) - Studio on the web: a public MCPserver and canvas (no sign-in, stores nothing), deployed on its own
## Quick Reference Commands
3k3mo agoReviewMountCreate a free account to mount
that accepts connections over a Unix socket (Windows: named pipe). The `ccc` CLI and MCPserver communicate with it via short-lived **per-request connections** (`client.py`): connect → handshake → send
No other project uses it yet
2.9k10d agoReviewMountCreate a free account to mount
cannot set custom HTTP headers. This is an accepted architectural trade-off.
- The stdio MCPserver (`mcp/mcpserver.py`) is local-only and not remotely exposed. `blueprints/mcp_http.py` and `blueprints/mcp_oauth.py` are the remote
2.9k1d agoReviewMountCreate a free account to mount
console.
- `*/managed-agents/`: the manifest directory (with the derived `system.md`) and the role's MCPserver.
- `examples/demo_common/` and `examples/web-shared/`: what the verticals' APIs and web apps share; `examples
2.9k2mo agoReviewMountCreate a free account to mount
more. It operates in multiple modes: TUI (default), HTTP API server, daemon, and MCPserver.
## Build & Development Commands
```bash
make build # Build binary to bin/process-compose (CGO_ENABLED=0)
make test
Steady3 mentions in 2 weeks
No other project uses it yet
2.9k6d agoReviewMountCreate a free account to mount
knowledgePolicy`) by cross-referencing `getInlineSourceMap()` and propagates policy to descendants. **Read-only is enforced server-side:** `assertWritablePath()` returns 403 for any write *strictly under* a read-only inline mount
2.9k4mo agoReviewMountCreate a free account to mount
read on demand, depending on the task at hand:
- `.cursor/commands/add-mcp.md` - how to add MCPservers to an agent
- `.cursor/commands/mcp-code-exec.md` - how to convert an MCPserver into the Code Execution Pattern
2.9k7mo 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.