meGPT - upload an author's content into an LLM

Created By
adriancoa year ago
Code to process many kinds of content by an author into an MCP server
Overview

What is meGPT?

meGPT is a project designed to process an author's diverse content into a Model Context Protocol (MCP) server, enabling the creation of a personalized language model that can answer questions and generate summaries in the author's voice.

How to use meGPT?

To use meGPT, clone the repository, set up the Python environment, and run the build script to process the author's content. You can also contribute your own content by adding it to the repository and submitting a pull request.

Key features of meGPT?

  • Supports various content types including books, blog posts, podcasts, and videos.
  • Automatic processing of YouTube content, including individual videos, playlists, and channels.
  • Integration with an MCP server for AI applications, allowing semantic search and content filtering.
  • Robust error handling and logging for content processing.

Use cases of meGPT?

  1. Authors can create a personalized chatbot that answers questions based on their published content.
  2. Researchers can utilize the MCP server to access a wide range of processed content for analysis.
  3. Educators can leverage the content to develop teaching materials or interactive learning tools.

FAQ from meGPT?

  • Can I use meGPT for any author?

Yes! You can clone the repository and add your own content to create a personalized model.

  • Is there a cost to use meGPT?

No, meGPT is free to use and encourages contributions from other authors.

  • What types of content can be processed?

meGPT supports a variety of content types including text, audio, and video, making it versatile for different authors.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
adrianco
Star
256
Language
Python
License
Apache-2.0 license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago