Skip to main content

Open-source, handheld-native, system-level AI gaming assistant — placeholder release

Project description

Levelwright

Open-source, handheld-native, system-level AI gaming assistant. Starting with Steam Deck.

Status: Design phase complete; Phase 1 implementation starting.

Inspired by TechDweeb's April Fools "PocketDweeb" concept, built for real. Think NVIDIA's Project G-Assist, but open-source, handheld-first, AMD-compatible.

What it is

A locally-running AI agent on your Steam Deck (and eventually other handhelds) that can:

  • Answer "what's my battery / CPU temp / TDP?" without tabbing out of a game
  • Check ProtonDB compatibility and Deck Verified status before you buy or launch
  • Recommend games from your library based on playtime, compat, and session context
  • Scale to ROG Ally, Legion Go, and MSI Claw via a pluggable HardwareAdapter

Built on Hermes-Agent (Python, MIT). UI via Decky Loader.

Status

This PyPI package is a placeholder while the real implementation is built. The actual Hermes plugins ship as:

  • levelwright-system — hardware telemetry (CPU/GPU temps, battery, TDP)
  • levelwright-steam — Steam Web API + ProtonDB compatibility

See:

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

levelwright-0.0.1.tar.gz (45.4 kB view details)

Uploaded Source

Built Distribution

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

levelwright-0.0.1-py3-none-any.whl (3.8 kB view details)

Uploaded Python 3

File details

Details for the file levelwright-0.0.1.tar.gz.

File metadata

  • Download URL: levelwright-0.0.1.tar.gz
  • Upload date:
  • Size: 45.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for levelwright-0.0.1.tar.gz
Algorithm Hash digest
SHA256 d7c1820490bf770866d45038a623ffbe286142fc3fd5e1235237b9b0308e7a76
MD5 cfbe49d00ccbfc47180b336b64ad2390
BLAKE2b-256 06b765ce73e407b572ca46d6833f39958418d716dd0620a0b8c098c4277f2069

See more details on using hashes here.

File details

Details for the file levelwright-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: levelwright-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 3.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for levelwright-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0d5c00e29a542e444199d29618dedc076f2719324bd1fe5f7856126089c66a83
MD5 a575ea87d16b2167478612938fcef5f5
BLAKE2b-256 8a8e1a92775a94bc9b020bdf7ea60a858dbd4612493297dc95ba1bf0f951fa1c

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