- Logo: Nakama
- Product
- Solutions
- Resources
- Docs
- Pricing
| #!/usr/bin/env python3 | |
| """Download Instagram Reels (or any yt-dlp URL) and print a Whisper transcript.""" | |
| from __future__ import annotations | |
| import argparse | |
| import shutil | |
| import subprocess | |
| import sys | |
| import tempfile |
Link to github project: https://github.com/ahmadrosid/tinyclaw
TinyClaw is your own personal AI assistant that you can run yourself β like having your own private ChatGPT, but one that you fully control and can customize to be exactly what you want.
Think of it as a digital assistant that lives on your computer, remembers things about you, and can help you with tasks across multiple apps and platforms. You can chat with it through a web dashboard, your computer's terminal, Telegram, or WhatsApp β all from the same assistant.
| # βββββββββββββββββββββββββββββββββββββββββββ | |
| # 1. Use a stable Node LTS image (22-slim) | |
| # This tag provides both amd64 and arm64 variants. | |
| # BuildKit will pick the correct one for the current platform | |
| # βββββββββββββββββββββββββββββββββββββββββββ | |
| FROM --platform=linux/amd64 node:22-slim | |
| # βββββββββββββββββββββββββββββββββββββββββββ | |
| # 2. Minimal OS tooling | |
| # βββββββββββββββββββββββββββββββββββββββββββ |
| #!/bin/bash | |
| # Migration script to move project files under src/ directory | |
| # This script will move app/, components/, lib/, and styles/ directories into src/ | |
| set -e | |
| echo "π Starting migration to src/ directory structure..." | |
| # Create src directory if it doesn't exist |
yt-dlp is excellent for use as a library in your API! Here's how you can use it programmatically for Instagram video downloads:
Basic Usage Example
import yt_dlp
import json
def download_instagram_video(url, output_path='downloads/'):
ydl_opts = {The web search tool gives Claude direct access to real-time web content, allowing it to answer questions with up-to-date information beyond its knowledge cutoff. Claude automatically cites sources from search results as part of its answer.
Please reach out through our feedback form to share your experience with the web search tool.
Web search is available on:
To handle and render custom UI in the client when a tool call runs using @ai-sdk/react, you can use the useChat hookβs built-in tooling supportβspecifically onToolCall, message.parts, and addToolResult.
Import the hook and set up onToolCall and addToolResult in your React page:
'use client';Hereβs a full breakdown of the AI SDK data stream protocol, which is used by tools, frontends (like useChat), and custom backendsβeven in non-JS environments:
When you stream from the backend (e.g., your Python/FastAPI server), you must use the Data Stream Protocol. Make sure to set the HTTP header:
x-vercel-ai-data-stream: v1
Animated Globe with vantajs and threeminjs. Globe animation.
A Pen by Sachin Samal on CodePen.