# glebkudr/shotgun_code

One‑click codebase “blast” for Large‑Language‑Model workflows.

Repository: https://github.com/glebkudr/shotgun_code
Canonical: https://ross.abutalabs.com/products/shotgun_code
Language: Go
License: NOASSERTION
License Family: other
Last push: 2025-12-04T15:11:51+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 55, release rhythm 57, longevity 34
- inputs: {"age_days": 482, "days_push": 272, "days_rel": 288, "gap_med": 4, "n_releases_24m": 4}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1999, forks 231 (observed 2026-08-28T04:06:03.749136+00:00)

## What it is
Shotgun is a desktop application that packages a local codebase into a structured context payload for LLMs, with AI-powered file selection and direct API execution against OpenAI, Gemini, and OpenRouter. It is built with a Go backend using the Wails framework and includes prompt templates, history tracking, and repo summaries.

## Use cases
- package my codebase as context for an LLM
- stop copy-pasting files into Cursor manually
- let AI pick which files are relevant for a bug fix
- send a prompt directly to GPT-4o or Gemini with my repo context
- generate a full project context dump for AI reasoning
- keep a history of prompts and responses sent to LLMs
- create architecture summaries to ground LLM answers

## When to choose
- you need to give an LLM large, structured context from a local repository
- you want AI-assisted selection of relevant files instead of manual picking
- you want to send prompts directly to OpenAI, Gemini, or OpenRouter from a desktop app
- you use tools like Cursor or Windsurf and need better context payloads

## When to avoid
- you need a headless CLI or CI-integrated context generator
- your code cannot be sent to third-party LLM APIs
- you want an IDE plugin rather than a separate desktop application
- you need fine-grained code indexing or semantic search over the codebase

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, prompt-engineering, developer-tools, file-system
- domain: developer-tools, large-language-models
- platform: cross-platform, go
- tags: llm-client, codebase-context, context-payload, wails, ai-coding-assistant, openai, gemini, openrouter, command-line, desktop

## Member repositories
- glebkudr/shotgun_code (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:03.749136+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:02:10.472577+00:00, confidence not recorded.
  - readme: https://github.com/glebkudr/shotgun_code (fetched 2026-08-28T04:06:03.749136+00:00, sha dde21e4b0d76)
- Data as of 2026-08-30T08:39:29.467469+00:00.