nWave
Agentic AI software delivery framework for Claude Code. A set of slash commands and specialized subagents that guide a project from idea to shipped code, with the developer in control at each gate. MIT-licensed, Python-based, installed via pipx.
Framework for teams that want Claude Code to run their SDLC without giving up control — nWave structures the loop into reviewable steps (planning, implementation, review, ship) rather than one-shot agent runs. Appeals to engineers who tried "vibe coding" and found it shipped bugs.
Engineering teams that use Claude Code daily and want a disciplined multi-step delivery loop rather than a single-prompt output; developers who prefer human-in-the-loop gates between agent actions.
https://github.com/nWave-ai/nWave
By Quinton Quartel / nWave-ai
How to Get It
This is a methodology or approach. Paste the instructions below into a Claude conversation to get started.
pipx install nwave-ai && nwave-ai install
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Trust Signals Automated Scan
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Automated Scan review. These are observations, not a security certification.
Auto-evaluated on intake (scanned-only, NOT personally tested). 431 GitHub stars, 42 forks, MIT license, active weekly releases on PyPI (v3.12.0). Young project (created Feb 2026). Self-described as agentic multi-step SDLC framework with human-in-the-loop gates. Upgrade to tested-depth review after hands-on trial.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Auto-evaluated on intake (scanned-only, NOT personally tested). 431 GitHub stars, 42 forks, MIT license, active weekly releases on PyPI (v3.12.0). Young project (created Feb 2026). Self-described as agentic multi-step SDLC framework with human-in-the-loop gates. Upgrade to tested-depth review after hands-on trial.