dottie-local

Local llama.cpp inference + optional dotbot harness.

Replaces local-ai-cli for LLM (ask + llm-server). Same CLI names on PATH after install. STT/TTS stays dottie-talk (transcribe / speak).

Same product shape as dottie-talk: HTTP + MCP + CLI. Talk is voice; this is tokens.

MIT. Public.

What it is

Two processes. Never vendors Metal into the harness.

Related MCP server: MCP LLM Integration Server

Requirements

• Node.js ≥ 22

• llama-server on PATH

• A GGUF (or let -hf download). Default model: ggml-org/gemma-4-12B-it-GGUF (prefers cached Q8_0)

Install

git clone https://github.com/stevederico/dottie-local.git
cd dottie-local
npm install
npm link          # puts ask, llm-server, dottie-local on PATH

Remove or unlink old local-ai-cli ask / llm-server first so PATH does not shadow.

Quick start

ask "hello"                                    # drop-in for local-ai-cli
echo "$(cat article.txt)" | ask "summarize this"
LLM_REASON=1 ask "prove it"

llm-server start|stop|restart|status|log

dottie-local agent "What tools do you have?"   # harness + dot_* tools
dottie-local start                             # HTTP :1318
dottie-local health

Use with dottie-desktop

Point Settings Provider at Dottie Local (or set localBaseUrl). Base URL is the façade — not raw :8080:

http://127.0.0.1:1318 — needs llama-server on PATH + dottie-local start. Model list: GET /api/tags. Chat: POST /v1/chat/completions.

Ports

HTTP

MCP tools

npm run mcp

CLI

dottie-local stop only kills an engine this package spawned. llm-server stop also matches llama-server on the engine port (full drop-in).

Related

• dottie-talk — local STT/TTS (replaces local-ai-cli transcribe)

• local-ai-cli — predecessor; LLM half superseded here

• dotbot — agent harness

• llama.cpp — inference engine

• dottie-desktop — desktop app

License

MIT