Skip to main content

NeuronX AI — command-line coding assistant powered by 22 AI models and 185K+ code patterns

Project description

nx-ai — NeuronX AI CLI

Command-line coding assistant powered by NeuronX — 22 AI models, 185K+ code patterns, and AI security scanning.

Install

pip install nx-ai

Setup

nx-ai init
# or
nx-ai config --key YOUR_API_KEY

Get a free API key at neuronx.jagatab.uk/developers

Commands

# Chat with AI
nx-ai chat "explain async/await in Python"
nx-ai chat "how do I optimize a slow SQL query" --model neuronx-smart

# Generate code
nx-ai code "REST API with JWT auth" --lang python
nx-ai code "React hook for debounced search" --lang typescript --output hook.ts
nx-ai code "binary search tree" --lang go

# Security scan
nx-ai scan app.py
nx-ai scan --stdin < script.py
cat mycode.js | nx-ai scan --stdin --lang javascript

# AI code review
git diff HEAD | nx-ai review --stdin
nx-ai review my_changes.diff

# Search patterns
nx-ai search "connection pooling postgres"
nx-ai search "JWT authentication middleware" --limit 20

# Platform status
nx-ai status

Models

Model Use case Speed
neuronx-fast Quick questions ~1s
neuronx-smart Complex reasoning ~3s
neuronx-code Code generation ~3s
neuronx-32b Advanced coding ~8s

Environment Variables

export NEURONX_API_KEY=nx-your-key
export NEURONX_BASE_URL=https://neuronx.jagatab.uk  # default

License

MIT — built on NeuronX Platform

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

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

nx_ai-0.1.0-py3-none-any.whl (7.8 kB view details)

Uploaded Python 3

File details

Details for the file nx_ai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: nx_ai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 7.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for nx_ai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 97909ec9df8da13dbaa2139f0979f8511e4915126e0473e6290b2acd7180a1c8
MD5 080783bf8a71c7169c1c4c01814f9b65
BLAKE2b-256 452789a0eed96c7ecfafee7e29d80a8e74b04184682ce7e113bfea30c17b460f

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