Skip to main content

Local daemon for Neruva Cockpit -- the web dashboard for AI that runs your computer and writes code. Two agents: Neruva Computer (sees your screen, clicks, types, navigates apps for you) and Neruva Code (writes code, edits files, runs commands, debugs). Remembers what you've done across sessions. Chat with it mid-task to redirect. Loopback-only; runs on your machine.

Project description

neruva-control

Local daemon for Neruva Cockpit — the web dashboard for AI that runs your computer and writes code for you.

Cockpit runs in your browser. This daemon runs on your laptop. Together they let an AI:

  • Neruva Computer — see your screen, click, type, navigate apps (organize files, fill forms, drive Excel, browse the web)
  • Neruva Code — write code, edit files, run commands, debug — drop it in any project folder
  • Remember what you've done across sessions so it gets better at your work
  • Take direction mid-task — type a message while it's working and it adjusts

Everything runs on your machine. The daemon binds to loopback (127.0.0.1) and never opens a network port.

Install

pip install "neruva-control[agent]"
neruva-control-install

The installer:

  1. Generates an auth token at ~/.config/neruva/control.token
  2. Registers a background service (launchd / systemd-user / Task Scheduler)
  3. Starts the daemon on 127.0.0.1:7331
  4. Prints a one-time link https://neruva.io/cockpit#token=<TOKEN> — open once, browser remembers your machine

The [agent] extra installs pyautogui + Pillow for the Neruva Computer screen control. Skip it if you only want Neruva Code (text/file work).

How it works

[browser at neruva.io/cockpit]
       ↕ WebSocket (loopback :7331, token-authed)
[neruva-control daemon]
   ├─ POST /v1/sessions {agent_type: "code"|"computer", task}
   ├─ Streams every step (screenshots, actions, results) to the browser
   ├─ Accepts mid-flight chat messages — type to redirect
   └─ Records to your Neruva account so the agent learns
       ↕ HTTPS (your Neruva API key only)
[api.neruva.io]

The daemon binds to 127.0.0.1 only. The browser tab at neruva.io/cockpit connects via loopback WebSocket using a one-time token. Sessions never leave your machine in transit.

Quick start (after install)

  1. Open the link the installer printed (or run neruva-control link to print it again)
  2. In Cockpit, pick a Mode — Neruva Code or Neruva Computer
  3. Type what you want done:
    • "Open my budget spreadsheet and add this month's expenses"
    • "Write a Python script that renames all photos in this folder by date"
    • "Fix the failing test in tests/auth.py"
  4. Watch it work. Type into the chat any time to redirect.

Configuration

Drop your Neruva API key into ~/.config/neruva/.env (Linux/macOS) or %APPDATA%\neruva\neruva\.env (Windows). The daemon auto-loads it at startup so you never touch your shell profile.

NERUVA_API_KEY=nv_...

That's the only key you need — everything else is handled server-side.

Commands

Command What it does
neruva-control-install One-shot install (generates token, registers service, prints link URL)
neruva-control start Run the daemon foreground (used by the background service)
neruva-control status Show install + daemon health + version
neruva-control link Print the link URL again (re-link or new browser)
neruva-control stop Stop the daemon

Requirements

  • Python ≥3.10
  • [agent] extra: pyautogui + Pillow (skip if Code-only)
  • A Neruva account at neruva.io

Privacy

  • Daemon listens on 127.0.0.1 only — never on a network interface
  • Sessions stream over loopback WebSocket; never leave your machine in transit
  • Memory writes are encrypted and tied to your account
  • Export or delete everything as a portable .neruva file anytime
  • For Neruva Computer: screenshots are sent securely to advance the task and not retained beyond that turn

License

MIT — see LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

neruva_control-0.7.3.tar.gz (84.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

neruva_control-0.7.3-py3-none-any.whl (91.5 kB view details)

Uploaded Python 3

File details

Details for the file neruva_control-0.7.3.tar.gz.

File metadata

  • Download URL: neruva_control-0.7.3.tar.gz
  • Upload date:
  • Size: 84.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for neruva_control-0.7.3.tar.gz
Algorithm Hash digest
SHA256 6482beff012c2de14f26fbd9f50070d2a1f46ee0de39702c1353a3638b272bdb
MD5 b902b2d1cb62865124508a99472e8c0b
BLAKE2b-256 c8f42446e8f7f1ef700570294da5a81e82b3b2fef2035a3c07b14e9566827d07

See more details on using hashes here.

File details

Details for the file neruva_control-0.7.3-py3-none-any.whl.

File metadata

  • Download URL: neruva_control-0.7.3-py3-none-any.whl
  • Upload date:
  • Size: 91.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for neruva_control-0.7.3-py3-none-any.whl
Algorithm Hash digest
SHA256 4db973310eca9df2cdbf65ae349e4e93279555f6cc7c161f54a440ce7ed26628
MD5 becae921ec29f80f5bade4e93f9fa64e
BLAKE2b-256 378b3a2ff16691b3a41f1345262d0fb6226a712a92e42cf254580354296e037b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page