# meshbot

Bridges a [MeshCore](https://meshcore.io) companion radio to any OpenAI-compatible LLM endpoint
(e.g. `llama-server`, vLLM, Ollama). Listens for direct messages on the device, runs each
conversation through the LLM with full per-sender history stored in SQLite, and replies back
over the mesh — trimmed to the MeshCore packet payload limit.

## Quick start

```sh
python -m venv .venv && source .venv/bin/activate
pip install -e .

cp config.example.toml config.toml
# edit serial_port and [llm] in config.toml

python -m meshbot
```

Config file path defaults to `./config.toml` and can be overridden with `MESHBOT_CONFIG`.
Any field can be overridden via env vars, e.g. `MESHBOT_LLM__API_KEY=sk-...`.

## Layout

- `src/meshbot/bot.py` — connect, subscribe to `CONTACT_MSG_RECV`, dispatch each DM.
- `src/meshbot/db.py` — SQLite schema and per-conversation repo functions.
- `src/meshbot/llm.py` — `AsyncOpenAI` wrapper.
- `src/meshbot/messages.py` — UTF-8-safe byte-length trimming.
- `src/meshbot/config.py` — TOML + env-var settings (pydantic-settings).