milady-ai / milady

Milady > *your schizo AI waifu that actually respects your privacy* **Milady** is a personal AI assistant that is **local-first by default** and can also connect to **Eliza Cloud** or a **remote self-hosted backend** when you want hosted runtime access. 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 --- Downloads Desktop App (recommended for normies) Grab from **Releases**: | Platform | File | | |----------|------|---| | macOS (Apple Silicon) | | for your overpriced rectangle | | macOS (Intel) | | boomer mac (why separate arm64/x64: Build & release) | | Windows | | for the gamer anons | | iOS | App Store | for the privacy-pilled | | Android | Google Play / APK | for the degen on the go | | Linux | / / Snap / Flatpak / APT repo | I use arch btw | Signed and notarized. No Gatekeeper FUD. We're legit. Verify (for the paranoid kings) --- Getting Started New Environment Setup (recommended) Then start Milady: First run walks you through onboarding: Alternative install paths Windows: NPM global: Homebrew (macOS / Linux) Snap Snap packages auto-update in the background. Available on Ubuntu, Fedora, Manjaro, and any distro with snapd installed. For the latest development builds: Flatpak Or sideload from a release bundle: Debian / Ubuntu (APT) Works on Debian 12+, Ubuntu 22.04+, Linux Mint 22+, Pop!_OS, and other Debian derivatives. Updates come through . Security: API token The API server binds to (loopback) by default — only you can reach it. If you expose it to the network (e.g. for container/cloud deployments), **set a token**: Without a token on a public bind, anyone who can reach the server gets full access to the dashboard, agent, and wallet endpoints. Hosting Modes On first run, onboarding now asks where the backend should live: • — run the backend on the current machine, exactly like the existing local flow. • — either use or attach to a backend with its address and access key. If you choose , the app provisions and connects to a managed backend. If you choose , the frontend rebinds to the backend you specify and continues against that API. Remote Backend Deployment Use this when you want the Milady frontend to connect to a backend running on your VPS, homelab box, or another machine. • Install Milady on the target machine. • Bind the API to a reachable address. • Generate a strong API token. • Allow the frontend origin explicitly. • Expose the backend over HTTPS or a private Tailscale URL. Recommended server environment: The access key the user enters in onboarding is the value of . If you want to connect from the desktop shell instead of the web frontend: Tailscale For private remote access without opening the backend publicly, expose it over your tailnet: If you intentionally want a public Tailscale URL: Then use the Tailscale HTTPS URL as the backend address in onboarding and keep using the same as the access key. Eliza Cloud uses the existing deployment directly at . The managed control plane, auth surface, billing, and instance dashboard all live there; there is no separate Milady-hosted cloud control plane to deploy. Managed browser flow: • Sign in on • Open or create a Milady instance in • Eliza Cloud redirects to with a one-time launch session • exchanges that launch session directly with Eliza Cloud and attaches to the selected managed backend The desktop/local app still exposes local passthrough routes for cloud login, billing, and compat management so it can persist the Eliza Cloud API key into the local config/runtime. That is local app plumbing, not a separate hosted Milady server. The integration plan lives in docs/eliza-cloud-rollout.md. The implementation and proxy runbook lives in docs/eliza-cloud-deployment.md. --- Terminal Commands Setup & Config Dashboard & UI Models Plugins Misc --- TUI (Terminal UI) When running, milady shows a live terminal interface: TUI Hotkeys | Key | Action | |-----|--------| | | quit gracefully | | | restart gateway | | | open dashboard in browser | | | toggle log view | | | compact/clear activity | | | show help | | | scroll activity | Headless mode Don't want the TUI? Run headless: Logs go to . Daemonize with your favorite process manager. --- Chat Commands (in any chat session) | Command | What it do | |---------|------------| | | session status, tokens, cost | | | memory wipe, fresh start | | | compress context (she summarizes) | | | reasoning: off\|minimal\|low\|medium\|high\|max | | | toggle verbose responses | | | per-message token display | | | switch model mid-session | | | restart the gateway | | | list commands | --- Ports | Service | Default | Env Override | |---------|---------|--------------| | Gateway (API + WebSocket) | | | | Dashboard (Web UI) | | | --- Config Lives at Or use for secrets. --- Model Providers | Provider | Env Variable | Vibe | |----------|--------------|------| | Anthropic | | **recommended** — claude is cracked | | OpenAI | | gpt-4o, o1, the classics | | OpenRouter | | 100+ models one API | | Ollama | — | local, free, no API key, full privacy | | Groq | | fast af | | xAI | | grok, based | | DeepSeek | | reasoning arc | Using Ollama (local models) Ollama lets you run models locally with zero API keys. Install it, pull a model, and configure Milady: > **⚠️ Known issue:** The has an SDK version incompatibility with the current AI SDK. Use Ollama's **OpenAI-compatible endpoint** as a workaround: Edit : This routes through the OpenAI plugin instead of the broken Ollama plugin. Works with any Ollama model — just make sure is running. **Recommended models for local use:** | Model | Size | Vibe | |-------|------|------| | | ~3GB | fast, good for chat | | | ~2GB | lightweight, quick responses | | | ~4GB | solid all-rounder | | | ~5GB | reason…