Metadata-Version: 2.4
Name: expert-mentor
Version: 0.6.0
Summary: Turn any LLM (Claude, ChatGPT, Gemini, Ollama, llama.cpp) into a professional teacher for any field.
Author: expert-mentor contributors
License: MIT
Project-URL: Homepage, https://github.com/voidstackloop/expert-mentor
Project-URL: Repository, https://github.com/voidstackloop/expert-mentor
Project-URL: Issues, https://github.com/voidstackloop/expert-mentor/issues
Project-URL: Changelog, https://github.com/voidstackloop/expert-mentor/releases
Project-URL: PyPI, https://pypi.org/project/expert-mentor/
Keywords: llm,mentor,tutor,education,claude,chatgpt,ollama,prompt
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Education
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# expert-mentor

Turn any capable LLM — Claude, ChatGPT, Gemini, or a local Ollama / llama.cpp
model — into a **professional teacher for any field**.

`expert-mentor` generates a calibrated expert-mentor system prompt for a given
field and level, runs the tutoring session directly, remembers what the learner
has mastered across sessions, and assesses progress from the transcript.

## Highlights

- **Provider-native prompts** — XML-shaped, prompt-cached system blocks for
  Claude; `developer` role, `max_completion_tokens`, and `reasoning_effort` for
  ChatGPT reasoning models.
- **Live sessions** over Anthropic, OpenAI, Ollama, and llama.cpp (standard
  library only, no `pip install` needed to run).
- **Persistent learner memory** — mastered / shaky / misconceptions / open
  questions, injected into every future session.
- **Model-assisted review** — turn a session transcript into an updated profile.
- **Curriculum design**, saved mentors, live model discovery, and a config file.
- **Zero runtime dependencies**; Python 3.8+.

## Install

```bash
pipx install expert-mentor      # or: pip install expert-mentor
mentor --field "quantum computing" --level beginner
```

## Quick start

```bash
mentor run --field "Rust" --provider claude --remember
mentor curriculum --field "Rust" --duration "6 weeks"
mentor fields
```

MIT licensed.
