#58 · Primary category： Knowledge Base & RAG
telegram-search
Export and fuzzy search your Telegram chat history
Project last updated：08/26/26
GitHub Stars
4.1K
Forks
274
Contributors
38
License
AGPL-3.0
Why we included this project
Telegram's built-in search struggles with Chinese, Japanese, and Korean text, which is frustrating when you know the message you need is buried somewhere in your history. This project syncs your chats into PostgreSQL or PGlite, tokenizes the content for multilingual lookup, and embeds text and images so you can search for a sentence or describe a photo you remember and still find it. Beyond retrieval, it adds an AI chat layer that answers questions using your own past conversations, and it can summarize unread messages. Media files can also be backed up to MinIO automatically. For anyone who wants their Telegram data under their own control and actually findable, this covers the practical bases.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
docling
Get your documents ready for gen AI
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience