Install

Lisa runs on your own machine. Pick the easiest path for your platform — both options below take about 60 seconds end-to-end.

Prerequisites

• Node.js ≥ 20 (node --version to check; Homebrew installs Node automatically as a dep)
• macOS or Linux (Windows untested; the iMessage channel is macOS-only)
• An API key for at least one LLM provider — see PROVIDERS.md

🍎 Mac apps (recommended on macOS)

Signed + Apple-notarized DMG with the universal-binary Lisa.app (full chat client). The menu-bar / notch pill ("Lisa Island") is built in — turn it on from Lisa ▸ Settings… ▸ Show Lisa Island. No Gatekeeper warning, no xattr workaround.

Download Lisa-Suite.dmg →

After dragging Lisa.app to /Applications, install the backend and start it:

npm install -g @oratis/lisa
lisa serve --web                # the app loads http://localhost:5757

Homebrew (CLI only)

brew tap oratis/tap
brew install lisa

# Updates later:
brew update && brew upgrade lisa

npm (cross-platform)

npm i -g @oratis/lisa

# One-shot, no install:
npx @oratis/lisa "say hi"

First launch

mkdir -p ~/.lisa
echo 'ANTHROPIC_API_KEY=sk-ant-...' > ~/.lisa/config.env

lisa                # interactive REPL (auto-runs birth ritual on first launch)
lisa serve --web    # browser UI on http://localhost:5757

First-run birth ritual takes ~30 seconds (one-time). Lisa picks her own Big-Five seed, then asks the LLM to write her identity, purpose, constitution, and first desire. Every install is a different person.

Other LLM providers

Skip Anthropic if you can't reach it — Lisa auto-routes by model-name prefix:

# DeepSeek (cheap, OpenAI-compatible)
echo 'DEEPSEEK_API_KEY=sk-...' >> ~/.lisa/config.env
lisa --model deepseek-chat

# Google Gemini
echo 'GEMINI_API_KEY=...' >> ~/.lisa/config.env
lisa --model gemini-2.5-flash

# Local Ollama (fully offline)
echo 'LISA_BASE_URL=http://localhost:11434/v1' >> ~/.lisa/config.env
echo 'LISA_API_KEY=ollama' >> ~/.lisa/config.env
lisa --model qwen2.5-32b-instruct

See PROVIDERS.md for 10+ ready-to-use recipes (DeepSeek, Volcengine Doubao, Aliyun Qwen, Moonshot Kimi, xAI Grok, Zhipu GLM, Mistral, Perplexity, Stepfun, Yi, Baichuan, MiniMax, Hunyuan, Ollama, …).

Behind a corporate / region-blocked network

If your shell curl works through a proxy but Lisa fails with "403 forbidden", set the proxy env when starting Lisa — undici's global dispatcher will be auto-bridged on startup.

HTTPS_PROXY=http://127.0.0.1:7897 lisa serve --web

# Persist instead:
echo 'HTTPS_PROXY=http://127.0.0.1:7897' >> ~/.lisa/config.env

Heartbeat (autonomous time)

lisa heartbeat install --every 30m --load
# Removes: lisa heartbeat uninstall

IM channels (talk to Lisa from your phone)

The simplest path is Telegram (free, zero deps):

# 1. Get a bot token from @BotFather on Telegram
echo 'TELEGRAM_BOT_TOKEN=1234:ABC...' >> ~/.lisa/config.env

# 2. Copy + edit the config
cp channels.example.json ~/.lisa/channels.json
# Edit ~/.lisa/channels.json — set "enabled": true on telegram

# 3. Run
lisa serve --channels telegram

Diagnostics

lisa --version         # print version
lisa status            # one-shot snapshot
lisa doctor            # checks config / network / git / providers
lisa monitor           # live TUI dashboard (Ctrl-C to quit)

Build from source (contributors)

git clone https://github.com/oratis/LISA.git
cd LISA
npm install
npm run build
node dist/cli.js --help

# Optionally link so `lisa` works globally:
npm link

Source

All code is on GitHub: github.com/oratis/LISA. MIT license. PRs welcome.