Add minibot - #3331
Open
sonic182 wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Project
minibot
Checklist
Add project-name- [pypi-name](https://github.com/owner/repo) - Description ending with period.Which Tier
Pick one:
Explain:
Personal Assistants currently lists one entry, hermes-agent, which is a conversational assistant you talk to. minibot covers the self-hosted, operational end of the same use case: an always-on instance you run yourself, where chats, memory, and scheduled prompts stay on your infrastructure rather than a vendor's.
The distinguishing property is weight. A default install pulls pydantic, sqlalchemy with aiosqlite, aiosonic, llm-async, rich, selectolax, croniter, and tomlkit, and nothing else. There is no torch, no langchain, and no llama-index in the dependency tree. The MCP bridge is a self-contained JSON-RPC client that does not require the mcp package at runtime. Everything heavy is opt-in: Telegram, speech-to-text, RabbitMQ, and PDF parsing are optional extras, and the RAG stack is deliberately left unmanaged so torch and sentence-transformers are installed only by users who actually enable it. Persistence is SQLite by default. The result is a personal assistant that runs on a small always-on box without dragging in an ML training stack.
What it does within this use case: Telegram-first delivery with chat and user allowlists in long-polling or webhook mode; scheduled prompts with one-shot, fixed-interval, and cron recurrence persisted in SQLite; provider-agnostic LLM access via llm-async covering openai, openai_responses, and openrouter; MCP server bridges alongside a Python extension API for custom tools, event subscribers, background services, and channels; optional Qdrant-backed RAG over local documents; async task workers for long-running jobs; and Docker plus docker-compose deployment with structured logfmt logs.
Adoption trajectory: ~630 PyPI downloads per month, released steadily since February 2026, currently at v0.11.0 with an active release cadence and full documentation at https://sonic182.github.io/minibot.
Displacement
Not applicable. Personal Assistants holds 1 of 5 permitted entries, so no displacement is required.