OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

X Reader

X Reader is a Python-based URL reader that provides an Agent Skill, CLI, and MCP server for retrieving content from supported web and media platforms. It reports whether the original source and relevant attached media were actually accessed, separating page text, metadata, captions, and transcripts where those layers differ.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

X Reader — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use X Reader when an agent needs to inspect URL content and report whether it retrieved the material relevant to a question, especially when posts include attached media or video and spoken content must be distinguished from page metadata.

Who it is for

  • People building AI-agent research workflows that need URL content rather than search previews.
  • Developers who want CLI or machine-readable URL retrieval across supported platforms.
  • Researchers checking whether an answer rests on a page, post, transcript, or other retrieved source layer.

Documented uses

  • Read content from a supported URL for an agent or CLI workflow.
  • Retrieve multiple URLs and request machine-readable output.
  • Check whether relevant attached video or audio was consumed, rather than relying on post text or metadata alone.
  • Identify missing source layers or retrieval failures before asking an agent to analyze material.
Before you choose

Requirements & limits

The repository documents a CLI requiring Python 3.10 or later and an MIT license. Telegram retrieval requires Telegram credentials; the Groq Whisper fallback requires a Groq API key. Browser fallback is installed separately and uses Playwright.

  • Coverage depends on the platform and retrieval path; X Reader represents missing material with PARTIAL, FAIL, or UNKNOWN rather than implying it was read.
  • For podcast pages from Xiaoyuzhou and Apple Podcasts, the documented generic web read retrieves page text and metadata, not audio; transcribe audio locally before making spoken-content claims.
  • Some sources have additional prerequisites, including Telegram credentials and, for Xiaohongshu, a possible one-time local login.
  • The browser fallback requires the browser extra and a Playwright Chromium installation.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the X Reader Agent Skill

Add the x-reader skill to an agent environment so it can read URLs with source coverage states.

Before you start

  • An AI agent environment that supports skills, such as Claude Code, Codex, or Cursor.
  • The npx command-line tool.

Steps

  1. Run the command below.

    Documented command
    npx skills add runesleo/x-reader --skill x-reader

  2. Give the agent a URL and ask it to read the original source.

  3. If attached video or audio matters, ask it to consume that material too and report what it read and what remains missing.

Expected outcome

The agent can use the x-reader skill to read URLs and report source coverage as PASS, PARTIAL, FAIL, or UNKNOWN.

Guide limitations

  • Media inspection may require local media tools; a page read alone does not establish that attached media was consumed.
  • A status reports retrieval coverage and does not guarantee that every source can be fetched.
Documentation 1 ↗
Source-based practical guide

Read URLs with the CLI

Install the CLI and retrieve URL content, optionally as machine-readable JSON.

Before you start

  • Python 3.10 or later.
  • A shell with pip available.

Steps

  1. Install from the GitHub repository with the command below.

    Documented command
    pip install "x-reader @ git+https://github.com/runesleo/x-reader.git"

  2. Run x-reader doctor to check readiness and identify missing items.

  3. Run x-reader https://example.com with the URL to read it.

  4. Add --json to request a machine-readable result, or provide multiple URLs for a multi-URL read.

Expected outcome

The CLI returns retrieved content and can provide a machine-readable payload for agent workflows.

Guide limitations

  • Retrieval paths and media coverage vary by source; missing material can remain partial or unavailable.
  • Telegram requires Telegram credentials; Groq Whisper fallback requires a Groq API key.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
runesleo/x-reader · Official homepage title · retained in its source language
How we review sourcesSuggest a correction