If generating code is a commodity, then what is built, and how is the most critical question to answer.
This is the goal of Shotgun - to help you turn technical research and spec generation into context for software engineers, AI code-gen tools like Codex, Cursor, Claude Code, with complete codebase understanding, and agents doing the heavy lifting.
Shotgun produces clean, reusable artifacts and exports to the agents.md ecosystem to help you get the most out of code-gen tools and Agents.
New release highlights:
Shotgun CLI
Howdy, partners! 🤠
AI coding tools like Cursor, Claude Code, and Lovable are getting stronger by the day. But out here on the frontier, we’ve all seen the same trouble:
Code that looks right but won’t run
Features that miss the intent
Stacks and architectures you’d never saddle up with
That’s what happens when you send your AI riding blind. Garbage in → garbage out.
So we built Shotgun — your codebase-aware spec engine for AI code-gen tools. Think of it as your AI posse:
The Researcher scouts the landscape
The Architect maps your system
The Product Strategist charts the user journey
The Spec Writer wrangles it all into a buildable doc
And now, Shotgun goes one step further — it can actually read your repo, grounding specs and diagrams in your real codebase. Every artifact can be previewed in a clean Webview and — only if you choose — shared with your team or the wider campfire.
🔑 Spec → Code (export to Cursor, Claude Code, or Lovable with a single command)
🔑 Local-first (your keys, your data)
🔑 Multi-agent (a full posse working together)
🔑 Repo-aware (specs that fit your system, not generic templates)
🔑 On-demand sharing (you decide what leaves your machine)
Shotgun is still early, and we’d love for you to ride with us. Try it out, break it, and tell us where the trails should lead next.
Excited to hear what you think! 🚀