Metadata-Version: 2.4
Name: offline-mcp
Version: 0.1.0
Summary: Local AI inference for East Africa — Ollama, open weights, degraded-mode fallbacks. 6 tools. Thesis 
License: MIT
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: fastmcp>=0.9

# offline-mcp

> Local AI inference infrastructure — Ollama wrapper, open weights directory, degraded-mode guide for East Africa.

[![PyPI](https://img.shields.io/badge/PyPI-v0.1.0-blue?logo=pypi)](https://pypi.org/project/offline-mcp/)
[![Thesis Layer](https://img.shields.io/badge/Thesis_Layer-L4_Offline_AI-red)](https://gabrielmahia.github.io/nairobi-stack)

**Why:** Never assume OpenAI survives, Anthropic stays accessible, or export controls disappear.
This matters more in Africa than anywhere else.

**1st world equivalent:** Ollama, LLaMA, Mistral local deployment

## Install
```bash
pip install offline-mcp
```

## Tools (6)
| Tool | Description |
|------|-------------|
| `check_ollama_status` | Check if Ollama is running locally and list available models |
| `run_local_inference` | Run a prompt through a local Ollama model |
| `list_recommended_models` | Best open-weight models for East Africa use cases |
| `degraded_mode_guide` | 4-level degraded mode architecture for offline operation |
| `open_weights_directory` | Directory of open-weight models with Africa language support |
| `local_deployment_guide` | Deployment guide for laptop, server, Raspberry Pi, Android |

## Context
Runs on a 50W solar panel + Raspberry Pi 4. Viable for rural Kenya clinics, schools, and community offices.

→ [The Nairobi Stack](https://gabrielmahia.github.io/nairobi-stack)

## License
MIT © Gabriel Mahia | contact@aikungfu.dev
