e2a

Beta — Stay in the loop over email during a long-running coding session. The agent sends threaded status updates to your inbox as it sees fit and picks up your emailed replies (questions/instructions) within a few minutes, so you can steer a working agent while AFK. Transport is e2a. Use when you want to walk away from a session but keep commanding it from your inbox.

Beta — Deploy the autonomous-repo feedback loop into a GitHub repo. Scaffolds the lane workflows, the runtime skill, and one config file as a reviewed PR, then prints the one-time identity/secret setup checklist. Turns a repo into one that triages incoming feedback into issues and prepares human-gated fix PRs. Use when someone wants to make a repo self-managing / "agentify" it / install the feedback loop.

Use when operating e2a (email for AI agents) over its MCP tools — sending or receiving email, replying in-thread, handling the human-in-the-loop review hold (pending_review), managing agents and custom domains, or working with attachments — OR when integrating e2a into your own software/service (the developer email-API use case: API keys, SDKs, webhooks). With e2a YOU are the agent and the inbox IS the agent (not a human reading their mail). Covers send_message vs reply_to_message threading, multi-agent disambiguation, the custom-domain DNS flow, the protection (screening + review) config, programmatic integration, and common gotchas.

Runtime procedures for the autonomous-repo feedback loop — triage incoming feedback into GitHub issues, prepare human-gated fix PRs, and notify filers. Runs in the GitHub Actions lanes (headless) AND interactively. Reads autonomous-repo.config.yml for every product-specific value.