Skillget

ninthwave

agent
Security Audit
Warn
Health Warn
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 7 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This agent orchestrates parallel AI coding sessions, breaking down project plans into small, isolated work items and coordinating them into reviewable Pull Requests while keeping your existing AI tools and local environment intact.

Security Assessment
The tool operates by executing shell commands to manage native AI CLI tools (like Claude Code or Codex) and git worktrees in parallel. Network requests are required to communicate with git hosts for CI/PR pipelines and an optional hosted broker. No hardcoded secrets were found, and the light code audit revealed no dangerous patterns or requests for excessive permissions. Because it acts as an orchestrator for external CLI tools and automatically manages local code execution, it inherently handles sensitive file operations. However, it keeps processes isolated in separate worktrees, and the broker can be self-hosted for full control over data transmission. Overall risk: Medium.

Quality Assessment
The project is under active development, with repository activity as recent as today. It is properly licensed under Apache-2.0, which is highly permissive and standard for open-source software. However, community trust and visibility are currently very low. With only 7 GitHub stars, the tool is effectively in its early stages, meaning bugs may be present and external community vetting is minimal.

Verdict
Use with caution: the code itself appears clean and safe, but early adoption carries the inherent risks of a low-community-visibility tool executing automated local shell commands.
SUMMARY

Orchestrate parallel AI coding into reviewable PRs.

README.md

Ninthwave logo

Ninthwave

Orchestrate parallel AI coding into reviewable PRs.

GitHub stars Apache 2.0 License Version Agent Skills

Ninthwave orchestrator managing parallel work items with live queue and PR pipeline status

Ninthwave is the orchestration layer for parallel AI coding. Turn plans into small, reviewable PRs while keeping your existing AI tool, billing, and local control.

Why try Ninthwave?

  • Turn a spec or plan into small work items, typically ~200-400 lines of meaningful change, so both humans and agents can reason about them during review
  • Run multiple native AI coding sessions in parallel, each isolated in its own worktree
  • Coordinate the full delivery loop through Implementer, CI, Reviewer, Rebaser, merge, and Forward-Fixer
  • Launch dependent work early as stacked PRs so reviewers get clean diffs
  • Share or join a crew to spread work across teammates or multiple machines, using the hosted broker by default or a self-hosted broker when you need full control
  • Use the native tools directly, while Ninthwave's TUI shows live queue and pipeline status
  • Stay multi-tool and no-lock-in: Claude Code, OpenCode, Codex CLI, or Copilot CLI

How I use it

I work in small iterations. I push planning down to a fairly detailed low spec, then use /decompose to break it into work items and let nw work through the queue.

Separately, I use scheduled Ninthwave work for more periodic high spec alignment, rationalization, and reconciliation: updating docs, checking for entropy or unnecessary complexity, and running broader security reviews.

When I'm confident in a breakdown, I leave Ninthwave in auto mode and let it merge as checks pass. When I want a closer look, I switch to manual mode and either review the PRs and leave feedback there, or jump straight into the worker session and iterate with the implementer directly.

How it works

Plan -> /decompose -> parallel native sessions -> stacked PRs -> review + feedback loop -> checks -> merge

  1. Use /decompose to turn a plan into markdown work items.
  2. Run nw to launch parallel native sessions of your AI tool.
  3. Review small PRs while the orchestrator keeps the queue moving through review, CI, and merge.

Ninthwave's orchestrator is deterministic.

For the transition states, flow diagrams, and deeper internals, see ARCHITECTURE.md.

Install

brew install ninthwave-sh/tap/ninthwave

Requires gh.

Run inside cmux or tmux for the best experience. Ninthwave can launch workers in headless mode, but attachable sessions are what let you jump straight into a worker when you need to inspect or steer it. If you are not already comfortable with tmux, start with cmux.

cmux showing active Ninthwave worker sessions and in-flight task output one step away while Ninthwave runs

Ninthwave works standalone; cmux or tmux keeps active worker sessions one step away when you need to inspect, steer, or unblock work in flight.

Quick start

  1. Install Ninthwave:

    brew install ninthwave-sh/tap/ninthwave
nw init # in a repo

  2. Optional but recommended: install cmux or tmux so you can attach to worker sessions when needed.

  3. Once you have a plan, create work items with /decompose, then run:

    nw

From there, Ninthwave launches the queue, opens reviewable PRs, watches checks, and keeps the pipeline moving. Leave it in auto mode when you want merges to keep flowing, or switch to manual mode when you want to review PRs and send feedback back through the loop.

License

Apache 2.0. See LICENSE.

Reviews (0)

No results found