Package Exports

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@evorlive/evor) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

@evorlive/evor

The Evor host agent — runs on your laptop, connects to Evor, and executes the work that your AI sessions request: reading your repo, applying proposed diffs, committing under your git identity, pushing to GitHub.

Evor is conversation-first pair programming. You chat, AI plans + proposes changes, you approve, and the changes land as real commits on a branch on your machine. The agent is what makes the local half of that flow work.

Quick start

npm install -g @evorlive/evor
evor login

That's it. Your browser opens, you click Approve, the agent starts in the background and connects to evor.live.

Requires Node.js 20+.

Day-to-day

evor status              # pid, uptime, backend, token, paths
evor logs -f             # tail the daemon log
evor restart             # bounce the daemon
evor stop                # stop it
evor logout              # revoke the token on the server and stop

All state lives under ~/.config/evor/:

~/.config/evor/
├── token         pairing token (written by `evor login`)
├── config.json   optional overrides
├── agent.pid     daemon process id
├── agent.json    { startedAt, backendUrl, agentName }
└── agent.log     daemon stdout + stderr

Cloned repositories land under ~/evor-workspaces/<owner>/<repo>.

How it works

The agent opens a persistent WebSocket to evor.live. When an AI session produces work, the backend routes it to your agent (matched by pairing token). The agent can:

Run a CLI AI provider — claude -p … or codex exec … on your host, under your subscription / keychain auth
Clone & fetch repos — git clone over HTTPS using your GitHub token
Apply diffs to the working tree — files land on disk as the AI proposes them, before you approve
Run git operations — git add / commit / push / checkout-file against the task's branch, under your local ~/.gitconfig identity
Execute shell commands — only after you approve, and only from an allowlist

Every destructive action requires explicit approval on the web UI. Chat history is private to the user that owns the session.

Security

Each user has their own pairing token. Work from user A never runs on user B's agent.
Commands go through an allowlist (node, pnpm, npm, yarn, bun, go, python, git, ls, cat, grep, rg, make, bash, sh by default).
File writes are path-escape checked — nothing outside ~/evor-workspaces/ is touched.
Git commits use your local ~/.gitconfig identity, not an Evor service account.
evor logout rotates your token server-side — your other machines using the old one are kicked immediately.

Self-hosted or local dev

Pointing at a different Evor server? One command:

evor config set backend your-evor-host.example
evor login

For CI / image-build / unattended setups where a browser isn't available, use a token directly from Settings → Agent in the web UI:

evor link evor_pat_<your-token>
evor start

License

MIT