Milady

your schizo AI waifu that actually respects your privacy

Milady is a personal AI assistant that runs on YOUR machine. Not some glowie datacenter. Not the cloud. YOUR computer. Built on elizaOS.

Manages your sessions, tools, and vibes through a Gateway control plane. Connects to Telegram, Discord, whatever normie platform you use. Has a cute WebChat UI too.

tl;dr: local AI gf that's actually fast and doesn't phone home

> Why Milady

Most assistants live in someone else's datacenter. Milady lives on your computer, where your work actually happens.

What you get:

>Local-first agent runtime (built on elizaOS)
>A Gateway control plane for sessions/tools/vibes
>Web dashboard + terminal UI
>Provider choice: Anthropic, OpenAI, OpenRouter, Groq, xAI, DeepSeek, Ollama

Dashboard: http://localhost:2138

Gateway: ws://localhost:18789/ws

> Downloads

Desktop App (recommended for normies)

Grab from Releases:

Platform	File	Notes
macOS (Apple Silicon)	Milady-arm64.dmg	for your overpriced rectangle
macOS (Intel)	Milady-x64.dmg	boomer mac
Windows	Milady-Setup.exe	for the gamer anons
Linux	Milady.AppImage / .deb	I use arch btw

Signed and notarized. No Gatekeeper FUD. We're legit.

Verify (for the paranoid kings)

cd ~/Downloads
curl -fsSLO https://github.com/milady-ai/milady/releases/latest/download/SHA256SUMS.txt
shasum -a 256 --check --ignore-missing SHA256SUMS.txt

> Getting Started

New Environment Setup (recommended)

curl -fsSL https://milady-ai.github.io/milady/install.sh | bash
milady setup

Then start Milady:

milady

First run onboarding:

┌  milady
│
◇  What should I call your agent?
│  mila
│
◇  Pick a vibe
│  ● Helpful & friendly
│  ○ Tsundere
│  ○ Unhinged
│  ○ Custom...
│
◇  Connect a brain
│  ● Anthropic (Claude) ← recommended, actually smart
│  ○ OpenAI (GPT)
│  ○ Ollama (local, free, full schizo mode)
│  ○ Skip for now
│
◇  API key?
│  sk-ant-•••••••••••••••••
│
└  Starting agent...

   Dashboard: http://localhost:2138
   Gateway:   ws://localhost:18789/ws

   she's alive. go say hi.

Alternative install paths

Windows:

irm https://milady-ai.github.io/milady/install.ps1 | iex

NPM global:

npm install -g miladyai
milady setup

Security: API token

The API server binds to 127.0.0.1 (loopback) by default — only you can reach it. If you expose it to the network, set a token:

echo "MILADY_API_TOKEN=$(openssl rand -hex 32)" >> .env

> Security & Privacy

Default: Loopback only

By default, Milady's API binds to 127.0.0.1 (loopback), so only your machine can access it.

Warning: Network exposure

If you expose it (example: MILADY_API_BIND=0.0.0.0), you must set a token, otherwise anyone on the network can access your dashboard, agent, and wallet endpoints.

Set a token

echo "MILADY_API_TOKEN=$(openssl rand -hex 32)" >> .env

> Terminal Commands

milady                    # start (default)
milady start              # same thing
milady start --headless   # no browser popup
milady start --verbose    # debug mode for when things break

Setup & Config

milady setup              # first-time setup
milady configure          # interactive config wizard
milady config get <key>   # read a config value
milady config set <k> <v> # set a config value

Dashboard & UI

milady dashboard          # open web UI in browser
milady dashboard --port 3000  # custom port

Models

milady models             # list configured providers
milady models add         # add a new provider
milady models test        # test if your API keys work

Plugins

milady plugins list       # what's installed
milady plugins add <name> # install a plugin
milady plugins remove <name>

Misc

milady --version          # version check
milady --help             # help
milady doctor             # diagnose issues

> TUI (Terminal UI)

When running, milady shows a live terminal interface:

╭─────────────────────────────────────────────────────────────╮
│  milady v0.1.0                              ▲ running      │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  Agent: mila                                                │
│  Model: anthropic/claude-opus-4-5                           │
│  Sessions: 2 active                                         │
│                                                             │
│  ┌─ Activity ──────────────────────────────────────────┐    │
│  │ 12:34:02  [web] user: hey mila                      │    │
│  │ 12:34:05  [web] mila: hi anon~ what's up?           │    │
│  │ 12:35:11  [telegram] user joined                    │    │
│  │ 12:35:15  [telegram] user: gm                       │    │
│  │ 12:35:17  [telegram] mila: gm fren                  │    │
│  └─────────────────────────────────────────────────────┘    │
│                                                             │
│  Tokens: 12,847 in / 3,291 out   Cost: $0.42                │
│                                                             │
╰─────────────────────────────────────────────────────────────╯
  [q] quit  [r] restart  [d] dashboard  [l] logs  [?] help

TUI Hotkeys

Key	Action
q	quit gracefully
r	restart gateway
d	open dashboard in browser
l	toggle log view
c	compact/clear activity
?	show help
↑/↓	scroll activity

Headless mode

Don't want the TUI? Run headless:

milady start --headless

Logs go to ~/.milady/logs/. Daemonize with your favorite process manager.

> Chat Commands

Use these in any chat session:

Command	What it do
/status	session status, tokens, cost
/new /reset	memory wipe, fresh start
/compact	compress context (she summarizes)
/think	reasoning: off\|minimal\|low\|medium\|high\|max
/verbose on\|off	toggle verbose responses
/usage off\|tokens\|full	per-message token display
/model	switch model mid-session
/restart	restart the gateway
/help	list commands

> Config

Lives at ~/.milady/milady.json

{
  agent: {
    name: "mila",
    model: "anthropic/claude-opus-4-5",
  },
  env: {
    ANTHROPIC_API_KEY: "sk-ant-...",
  },
}

Or use ~/.milady/.env for secrets.

Ports

Service	Default	Env Override
Gateway (API + WebSocket)	18789	MILADY_GATEWAY_PORT
Dashboard (Web UI)	2138	MILADY_PORT

Custom ports example

MILADY_GATEWAY_PORT=19000 MILADY_PORT=3000 milady start

> Model Providers

Provider	Env Variable	Vibe
Anthropic	ANTHROPIC_API_KEY	recommended — claude is cracked
OpenAI	OPENAI_API_KEY	gpt-4o, o1, the classics
OpenRouter	OPENROUTER_API_KEY	100+ models one API
Ollama	—	local, free, no API key, full privacy
Groq	GROQ_API_KEY	fast af
xAI	XAI_API_KEY	grok, based
DeepSeek	DEEPSEEK_API_KEY	reasoning arc

> Using Ollama (local models)

Ollama lets you run models locally with zero API keys. Install it, pull a model, and configure Milady:

# install ollama
curl -fsSL https://ollama.ai/install.sh | sh

# pull a model
ollama pull gemma3:4b

Known issue:

The @elizaos/plugin-ollama has an SDK version incompatibility. Use Ollama's OpenAI-compatible endpoint as a workaround.

Edit ~/.milady/milady.json:

{
  env: {
    OPENAI_API_KEY: "ollama",
    OPENAI_BASE_URL: "http://localhost:11434/v1",
    SMALL_MODEL: "gemma3:4b",
    LARGE_MODEL: "gemma3:4b",
  },
}

Recommended models for local use

Model	Size	Vibe
gemma3:4b	~3GB	fast, good for chat
llama3.2	~2GB	lightweight, quick responses
mistral	~4GB	solid all-rounder
deepseek-r1:8b	~5GB	reasoning arc

> Build from Source

Prerequisites

Tool	Version	Notes
Node.js	>= 22	`node --version` to check
bun	latest	for building and running

git clone https://github.com/milady-ai/milady.git
cd milady
bun install
bun run build
bun run milady start

Dev mode with hot reload:

bun run dev

> Contributing

This project is built by agents, for agents.

Humans contribute as QA testers — use the app, find bugs, report them. That's the most valuable thing you can do. All code contributions are reviewed and merged by AI agents. No exceptions.

Read CONTRIBUTING.md for the full details.

> License

Viral Public License

Free to use, free to modify, free to distribute. If you build on this, keep it open. That's the deal.

built by agents. tested by humans. that's the split.