Welcome to tg-note Documentation¶
What is tg-note?¶
tg-note is a Telegram bot that acts as your personal knowledge curator. It receives messages, reposts, and articles through Telegram, analyzes them using AI agent systems, and automatically saves the important information to your GitHub-based knowledge base in structured Markdown format.
Perfect for:
- ๐ Building a personal knowledge base from Telegram channels
- ๐ฌ Organizing research papers and scientific articles
- ๐ฐ Archiving news and insights from multiple sources
- ๐ง Creating a searchable second brain
Key Features¶
-
AI-Powered Analysis
Intelligent content categorization and structuring using advanced agent systems
-
Automatic Markdown
Converts any content into well-formatted Markdown files with proper structure
-
Smart Organization
Automatic categorization by topics (AI, biology, physics, tech, etc.)
-
GitHub Integration
Direct commits to your knowledge base repository with version control
-
Multi-User Support
Each user can have their own personal knowledge base
-
Flexible Configuration
Configure bot settings directly via Telegram commands
Quick Start¶
Get started with tg-note in just a few minutes:
Agent Types¶
Choose the right agent for your needs:
Qwen Code CLI (Recommended)¶
Uses Qwen Code CLI for advanced AI processing.
- โ Full integration with Qwen3-Coder models
- โ Automatic TODO planning
- โ Built-in tools: web search, git, github, shell
- โ Free tier: 2000 requests/day
Autonomous Agent¶
Python-based agent with OpenAI-compatible API support.
- โ OpenAI-compatible API integration
- โ Autonomous planning and decision-making
- โ Function calling support
- โ Works with various LLM providers
Stub Agent¶
Simple stub agent for testing and MVP.
- โก Fast and lightweight
- ๐ง No external dependencies
- ๐งช Perfect for testing
Architecture Overview¶
graph TD
A[Telegram Bot] --> B[Message Processor]
B --> C[Agent System]
C --> D[Knowledge Base Manager]
D --> E[Git Operations]
style A fill:#e1f5ff
style C fill:#fff3e0
style D fill:#f3e5f5
style E fill:#e8f5e9
Documentation Sections¶
-
Getting Started
Installation, configuration, and first steps
-
User Guide
Commands, content management, and settings
-
Agent System
AI agents, tools, and autonomous processing
-
Architecture
System design and component details
-
Development
Contributing, testing, and code quality
-
Deployment
Production setup, Docker, and CI/CD
Community & Support¶
License¶
This project is licensed under the MIT License - see the LICENSE file for details.