Catalog PyPI
PACKAGE EXPLORERView in registry

ai-boss

PyPI

AI BOSS (Brain-Operating Support System) — a local AI mentor and life-assistant powered by any OpenAI-compatible LLM.

aiassistantbossbrain-operating-support-systemchatgptcoachllmlm-studiolocal-llmmentorollamaopenaiproductivity
Versions collected1
Direct dependencies6From release 0.1.0
Last observed21 Oct, 10:02 UTC

README

Version 0.1.0 documentation

AI BOSS (Brain-Operating Support System)

License: Apache 2.0 Python 3.10+ Status: Alpha

English | Русский

AI BOSS is a local AI mentor and life-assistant that runs entirely in your terminal.
It connects to any OpenAI-compatible LLM (local or remote) and helps you manage tasks, plans, diary, reminders, and personal growth through a structured workspace.

Note: This project is in active alpha development. APIs and file formats may change.

Features

  • Local & Private – Works with local LLMs (Ollama, LM Studio, vLLM, llama.cpp) or any OpenAI-compatible API.
  • Persistent Workspace – Keeps your profile, plans (today/tomorrow), diary, and custom files in a dedicated folder.
  • AI Tools – The assistant can create/update/delete files, set timers, send system notifications, update your profile, and more.
  • Preprocessors & Postprocessors – Background tasks that run before/after the main conversation (e.g., morning routine, evening reflection).
  • Timer Manager – Set reminders; the AI wakes up automatically and notifies you.
  • Rich Terminal UI – Beautiful markdown rendering, syntax highlighting, reasoning display, and usage/timings.
  • Multilingual – Russian and English interfaces (more can be added via locale files).
  • Debugging & Transparency – Optional logging of all LLM traffic, tool calls, and pre/postprocessor snapshots.

Installation

pip install ai-boss

Requires Python 3.10 or newer.

Quick Start

After installation, simply run:

ai-boss

On first launch, an onboarding wizard will guide you through:

  1. Choosing the interface language.
  2. Selecting a workspace directory (where state files are stored).
  3. Configuring the LLM connection (API base URL, API key, model name).
  4. Advanced options (logging, reasoning effort, postprocessor quiet mode, etc.).

The wizard creates config.json and a workspace/ folder with template files.

Usage

Once running, you can chat with the AI naturally. Commands start with ! (e.g., !help).
The AI can also use tools autonomously to manage your workspace.

Common Commands

CommandDescription
!helpShow all available commands
!statusList files managed by the AI
!profileView or edit your user profile
!system_promptView or edit the system prompt
!modelChange the LLM model
!languageSwitch interface language (ru/en)
!resetClear conversation history
!redoRegenerate the last assistant response
!exitQuit the application

To view a file from the files/ folder directly in the terminal, type:

/files/path/to/file.md

Without a path, it lists all files.

How It Works

AI BOSS maintains a workspace with the following structure:

workspace/
├── system_prompt.txt      # Core instructions for the AI
├── user_profile.txt       # Information about you
├── chat_history.json      # Conversation history
├── plan_today.txt         # Today's plan (read-only after morning reset)
├── plan_tomorrow.txt      # Tomorrow's plan (editable)
├── diary.txt              # Success diary
├── timers.json            # Active reminders
└── files/                 # Custom files created by the AI

Before each LLM call, the system assembles context from these files and injects it as tool results.
The AI can call tools to modify the workspace.
After the main response, postprocessors run in background threads to perform tasks like updating plans or reflecting on the conversation.
Preprocessors run before the main call (e.g., morning actualization).

Configuration

Configuration is stored in config.json in the current working directory.
You can edit it manually or use interactive commands.

Key settings include:

  • llm: API base, key, model, context window, max tokens, reasoning effort.
  • workspace_dir: Where state files are stored.
  • preprocessors / postprocessors: Background task definitions.
  • language: Interface language (ru or en).
  • debug_traffic: Enable detailed logging to logs/.

Contributing

Contributions are welcome!
Please open an issue or pull request on GitHub.

License

This project is licensed under the Apache License 2.0 – see the LICENSE file for details.


Made with ❤️ for personal growth and productivity.

🇷🇺 Русская версия

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Versions 1

Collected releases
VersionPublishedDirect dependenciesOpen version
0.1.09 Oct 20266

Package advisories

0
No matching advisories collected

This describes our collected data; it is not a security assessment.

Repository

PENDING
backup64back-afk/ai-boss

Shared repository data · GitHub

License detected in repository
Not collected

Metadata history

Meaningful changes
Current collected state Current

Observed since 21 Oct, 10:02 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package:f1885c58ae21e3ef60247d3ad8c5fb70342196fa5a01563a4f482c80e21c0f76