Sesori AI

Coding agents often stop on a question or a permission prompt minutes after you walk away, and sit idle until you're back. Sesori notifies you the moment an agent needs you, and you answer from your phone.

Sesori shows the coding-agent sessions running on your computer in two places: Sesori Desktop (macOS, Linux) and the Sesori app for iPhone and Android. Both follow the same sessions, so you can start a task at your desk and answer the agent's question from your phone later.

It works with Claude Code, Codex, OpenCode, GitHub Copilot, Cursor, Pi, OMP, Hermes, DeepSeek and Grok Build. You can read progress, review diffs, answer permission requests where the agent exposes them, send follow-up prompts, and speak instead of typing.

Nothing moves to the cloud. The repository, the agent and the Sesori Bridge stay on your machine. A hosted relay routes the traffic between the Bridge and your phone with end-to-end encryption (X25519 + XChaCha20-Poly1305), so it sees ciphertext, not your code, prompts or AI responses.

Sesori Desktop runs the Bridge for you. On a server, over SSH or on Windows, run the headless Bridge CLI instead (npx @sesori/bridge). Sign in with GitHub, Google, Apple or email on each device and they pair automatically.

Free, no paid plan; you keep paying your AI provider directly. The source is on GitHub under the Functional Source License (FSL-1.1-ALv2).