ollama-telegram
Self-hosted Telegram bot for chatting with local LLMs through Ollama. Open source under MIT; archived and no longer maintained.
ollama-telegram connects Telegram chats to a local LLM through Ollama. The project is archived and no longer maintained. It's for people who want to access their own model through Telegram, with the bot and model backend running on hardware or a server they control.
The model runs locally through Ollama, but Telegram remains the messaging service. This isn't a fully offline chat interface: messages pass through Telegram, so local inference doesn't keep the entire conversation on your machine.
The Python bot includes system prompt controls and model management features, along with permissions for users and groups. These give it scope beyond a single personal chat, such as letting selected people access an Ollama backend through a shared messaging app. Docker support provides a way to host the bot, and its Docker Compose setup includes persistent data storage.
Its main distinction is the Telegram interface. People already using Telegram can reach an Ollama model through that app rather than a separate chat frontend. The code is open source under the MIT license, so you can inspect and adapt it, but the archived project receives no further maintenance or updates.
