MiniBot 🤖
Your personal AI assistant for Telegram - self-hosted, auditable, and intentionally opinionated.
Top features
- 🤖 Personal assistant, not SaaS: your chats, memory, and scheduled prompts stay in your instance.
- 🎯 Opinionated by design: Telegram-centric flow, small tool surface, and explicit config over hidden magic.
- 🏠 Self-hostable: Dockerfile + docker-compose provided for easy local deployment.
- 💻 Local console channel for development/testing without Telegram.
- 💬 Telegram channel with chat/user allowlists, long-polling or webhook modes, and multimodal inputs.
- 🧠 Provider support via llm-async:
openai,openai_responses,openrouter, and more. - 🧰 Configurable tools: chat memory, KV notes, HTTP fetch, calculator, datetime, Python execution, Bash, file storage, grep, speech-to-text, and MCP server bridges.
- ⏰ Scheduled prompts (one-shot, fixed-interval, and cron recurrence) persisted in SQLite.
- 🤝 Multi-agent orchestration with specialist agent definitions and skill packs.
- ⚙️
minibot configure: interactive terminal wizard to create or updateconfig.toml. - 📊 Structured logfmt logs and a focused async test suite.
Quick start
pip install minibot
# add extras as needed, e.g.: pip install "minibot[mcp,stt,rabbitmq]"
minibot configure # interactive wizard, writes config.toml
minibot # start the daemon
Extras: mcp (MCP server tools), stt (speech-to-text via faster-whisper), rabbitmq (RabbitMQ task
queue backend — not needed with the default sqlite backend).
Docker
cp config.example.toml config.toml
# edit config.toml (or run `minibot configure` in a venv first)
docker compose up -d
docker-compose.yml builds the minibot image and starts Qdrant alongside it (used by the RAG tool);
the RabbitMQ service is commented out and only needed if you set [tasks].backend = "rabbitmq".
Demo
Example: generate images with the python_execute tool and receive them in Telegram.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file minibot-0.9.0.tar.gz.
File metadata
- Download URL: minibot-0.9.0.tar.gz
- Upload date:
- Size: 193.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
666dc8884f2033f096169c6f937856d49c7ee4d657580de0053088aba5a7a3ae
|
|
| MD5 |
1e4d1b66e6e9ce4ece15e1d050875191
|
|
| BLAKE2b-256 |
85bf1b2130e78892414c561e2e510f0e6288f69904edf320a6db43d145dcee22
|
File details
Details for the file minibot-0.9.0-py3-none-any.whl.
File metadata
- Download URL: minibot-0.9.0-py3-none-any.whl
- Upload date:
- Size: 270.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
10c1668d4e2714519be973fb8364f41430cc03ec7708591e29ad533d2925eacd
|
|
| MD5 |
10e6ab2b64f654b9e6229abe32f9e39c
|
|
| BLAKE2b-256 |
7417b9890cba6b82b0bee1b6c053b8db8b6e33ad9910ae4a91efe775dc95a2af
|
