An open API service indexing awesome lists of open source software.

https://github.com/linklyai/linkly-ai-cli

Linkly AI CLI Tools
https://github.com/linklyai/linkly-ai-cli

agent-skills agent-tools knowledge-base mcp search-engine

Last synced: 4 months ago
JSON representation

Linkly AI CLI Tools

Awesome Lists containing this project

README

          

# Linkly AI CLI

Command-line interface for [Linkly AI](https://linkly.ai) — search your local documents from the terminal.

The CLI connects to the Linkly AI desktop app's MCP server, giving you fast access to your indexed documents without leaving the terminal.

## Prerequisites

The **Linkly AI desktop app** must be running with MCP server enabled. The CLI automatically discovers the app via `~/.linkly/port`.

## Installation

### macOS / Linux

```bash
curl -sSL https://updater.linkly.ai/cli/install.sh | sh
```

### Windows (PowerShell)

```powershell
irm https://updater.linkly.ai/cli/install.ps1 | iex
```

### Homebrew (macOS / Linux)

```bash
brew tap LinklyAI/tap
brew install linkly
```

### Cargo

```bash
cargo install linkly-ai-cli
```

### GitHub Releases

Pre-built binaries for all platforms are available on the [Releases](https://github.com/LinklyAI/linkly-ai-cli/releases) page.

| Platform | File |
| --------------------- | ----------------------------------------- |
| macOS (Apple Silicon) | `linkly-aarch64-apple-darwin.tar.gz` |
| macOS (Intel) | `linkly-x86_64-apple-darwin.tar.gz` |
| Linux (x86_64) | `linkly-x86_64-unknown-linux-gnu.tar.gz` |
| Linux (ARM64) | `linkly-aarch64-unknown-linux-gnu.tar.gz` |
| Windows (x64) | `linkly-x86_64-pc-windows-msvc.zip` |

### From Source

```bash
cargo install --path .
```

## Usage

### Search Documents

```bash
linkly search "machine learning"
linkly search "API design" --limit 5
linkly search "notes" --type pdf,md,docx
```

| Option | Description |
| ---------------- | ----------------------------------------------------------------------- |
| `--limit ` | Maximum results (default: 20, max: 50) |
| `--type ` | Filter by document types, comma-separated (e.g. `pdf,md,docx,txt,html`) |

### View Document Outline

Get structural outlines for one or more documents (IDs come from search results):

```bash
linkly outline
linkly outline
```

### Read Document Content

```bash
linkly read
linkly read --offset 50 --limit 100
```

| Option | Description |
| -------------- | ---------------------------------- |
| `--offset ` | Starting line number (1-based) |
| `--limit ` | Number of lines to read (max: 500) |

### Check Status

```bash
linkly status
```

### MCP Bridge Mode

Run as a stdio MCP server for Claude Desktop, Cursor, or other MCP clients:

```bash
linkly mcp
```

Claude Desktop configuration (`claude_desktop_config.json`):

```json
{
"mcpServers": {
"linkly-ai": {
"command": "linkly",
"args": ["mcp"]
}
}
}
```

### Self-Update

```bash
linkly self-update
```

## Global Options

| Flag | Description |
| ------------------ | -------------------------------------------------------------------------- |
| `--endpoint ` | Connect to a specific MCP endpoint (e.g. `http://192.168.1.100:60606/mcp`) |
| `--json` | Output in JSON format (useful for scripting) |
| `-V, --version` | Print version |
| `-h, --help` | Print help |

## Examples

```bash
# Search across LAN
linkly search "budget report" --endpoint http://192.168.1.100:60606/mcp

# JSON output for scripting
linkly search "TODO" --json | jq '.content'

# Pipe document content
linkly read abc123 --limit 50 | head -20
```

## License

Apache-2.0