Write codebase-aware specs for AI coding agents (Codex, Cursor, Claude Code) so they don't derail.
Star Shotgun RepoResearch → Specify → Plan → Tasks → Export
Shotgun indexes your entire codebase, researches internal patterns + external solutions, writes specs with full context. Your AI agent gets complete context - what exists, why, and what to build.
Real case: We needed payments. AI agents suggested building a custom proxy (3-4 weeks). Shotgun found LiteLLM Proxy in 30 minutes. Implementation: 5 days. First customer: 14 hours later. 80% less dev time.
150+ developers building Shotgun together. Open source. MIT license.
Main repo: shotgun-sh/shotgun
What we're working on:
- Multiplayer mode for team collaboration
- Better codebase indexing with tree-sitter
⭐ Star the repo if spec-driven development sounds useful
🐛 Found a bug? Create an issue
💡 Feature idea? Submit a request
💬 Join Discord: 150+ developers online
📖 Read the case study: How we saved 80% dev time using Shotgun Case Study