Install Seris

Seris ships as a DMG for Macs with Apple Silicon. Download Seris_0.1.1_aarch64.dmg from the latest GitHub release, drag Seris to Applications, approve the first launch in System Settings, then connect a model.

Download and install

Download Seris_0.1.1_aarch64.dmg from the latest release.
Open the disk image and drag Seris.app to Applications.
Open Seris from Applications.

First launch

Seris is ad-hoc signed and not Apple-notarized. If macOS blocks the first launch, open System Settings → Privacy & Security and choose Open Anyway for Seris. Apple describes the steps in its support article.

Connect a model

Open Settings → Models, configure a provider and choose a default model. For Ollama or LM Studio, start the local server first. Testing a connection sends a short model request and may incur provider charges. See Models for every provider.

Upgrade

Quit Seris, open the new DMG and replace the app in Applications. Conversations, model metadata, watchlists, strategies and backtest results live outside the app bundle, so they carry over. After an upgrade, macOS may ask you to allow access to an existing model credential in the keychain.

Run from source

Use the Node version in .node-version, pnpm 12.5.1, Rust, and the Tauri build prerequisites for your operating system.

git clone https://github.com/aowang-ai/seris.git
cd seris
pnpm install --frozen-lockfile
pnpm tauri:dev

Check with pnpm typecheck and pnpm test, and package with pnpm tauri:build. For standalone gateway development, run pnpm build and then pnpm core:gateway; it prints a one-time browser launch URL and can start without model credentials.

Where your data lives

The desktop app keeps conversations, settings, installed skills, strategies and generated files in the system application-data directory. Set SERIS_DATA_DIR to use another directory and SERIS_WORKSPACE for the agent's task directory. Model API keys are stored in the macOS credential store.