[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73298":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":17,"rankGlobal":9,"rankLanguage":9,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":21,"hasPages":19,"topics":22,"createdAt":9,"pushedAt":9,"updatedAt":23,"readmeContent":24,"aiSummary":25,"trendingCount":15,"starSnapshotCount":15,"syncStatus":16,"lastSyncTime":26,"discoverSource":27},73298,"shotgun_code","glebkudr\u002Fshotgun_code","glebkudr","One‑click codebase “blast” for Large‑Language‑Model workflows.",null,"Go",2003,229,38,26,0,2,29.09,"Other",false,"main",true,[],"2026-06-12 02:03:11","# Shotgun App\n\n![Shotgun App Banner](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F6dd15389-4ad9-493a-a0e7-9813eb143e38)\n\n**Tired of Cursor cutting off context, missing your files, and spitting out empty responses?**\n\n**Shotgun** is the bridge between your local codebase and the world's most powerful LLMs.\nIt doesn't just copy files; it **intelligently packages your project context** and can **execute prompts directly** against OpenAI (GPT-4o\u002FGPT-5), Google Gemini, or OpenRouter.\n\n> **Stop copy-pasting 50 files manually.**\n> 1. Select your repo.\n> 2. Let AI pick the relevant files (Auto-Context).\n> 3. Blast the payload directly to the model or copy it for use in Cursor\u002FWindsurf.\n\n---\n\n## 1. What Shotgun Does\nShotgun is a desktop power-tool that **explodes your project into a structured payload** designed for AI reasoning.\n\nIt has evolved from a simple \"context dumper\" into a full-fledged **LLM Client for Codebases**:\n*   **Smart Selection:** Uses AI (\"Auto-Context\") to analyze your task and automatically select only the relevant files from your tree.\n*   **Direct Execution:** Configurable API integration with **OpenAI**, **Gemini**, and **OpenRouter**.\n*   **Prompt Engineering:** Built-in templates for different roles (Developer, Architect, Bug Hunter).\n*   **History & Audit:** Keeps a full log of every prompt sent and response received.\n\n---\n\n## 2. Key Features\n\n### 🧠 AI-Powered Context\n*   **Auto-Context:** Don't know which files are needed for a bug fix? Type your task, and Shotgun uses an LLM to scan your tree and select the relevant files for you.\n*   **Repo Scan:** supplement context retrieval with a `shotgun_reposcan.md` summary of your architecture to give the LLM high-level awareness before diving into code.\n\n### ⚡ Workflow Speed\n*   **Fast Tree Scan:** Go + Wails backend scans thousands of files in milliseconds.\n*   **Interactive Tree:** Manually toggle files\u002Ffolders or use `.gitignore` and custom rule sets to filter noise.\n*   **One-Click Blast:** Generate a massive context payload instantly.\n\n### 🔌 Direct Integrations\n*   **OpenAI:** Support for GPT-4o and experimental support for **GPT-5** family models.\n*   **Google Gemini:** Native integration for Gemini 2.5\u002F3 Pro & Flash.\n*   **OpenRouter:** Access hundreds of LLM's via a unified API.\n\n### 🛠 Developer Experience\n*   **Prompt Templates:** Switch modes easily (e.g., \"Find Bug\" vs \"Refactor\" vs \"Write Docs\").\n*   **History Tracking:** Never lose a generated patch. Browse past prompts, responses, and raw API payloads.\n*   **Privacy Focused:** Your code goes only to the API provider you choose. No intermediate servers.\n\n---\n\n## 3. The Workflow\n\nShotgun guides you through a 3-step process:\n\n### Step 1: Prepare Context\n*   **Select Project:** Open your local repository.\n*   **Filter:** Use the checkbox tree, `.gitignore`, or the **Auto-Context** button to define the scope.\n*   **Repo Scan:** Edit or load the high-level repository summary for better AI grounding.\n*   **Result:** A structured XML-like dump of your selected codebase.\n\n### Step 2: Compose & Execute\n*   **Define Task:** Describe what you need (e.g., \"Refactor the auth middleware to use JWT\").\n*   **Select Template:** Choose a persona (Dev, Architect, QA).\n*   **Execute:** Click **\"Execute Prompt\"** to send it to the configured LLM API immediately, OR copy the full payload to your clipboard for use in external tools like ChatGPT or Cursor.\n\n### Step 3: History & Apply\n*   **Review:** View the AI's response alongside your original prompt.\n*   **Diffs:** The AI output is optimized for `diff` generation.\n*   **Audit:** Inspect raw API calls for debugging or token usage analysis.\n\n---\n\n## 4. Installation\n\n### Prerequisites\n*   **Go ≥ 1.20**\n*   **Node.js LTS**\n*   **Wails CLI:** `go install github.com\u002Fwailsapp\u002Fwails\u002Fv2\u002Fcmd\u002Fwails@latest`\n\n### Clone & Build\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fglebkudr\u002Fshotgun_code\ncd shotgun_code\n\n# Install frontend dependencies\ncd frontend\nnpm install\ncd ..\n\n# Run in Development Mode (Hot Reload)\nwails dev\n\n# Build Production Binary\nwails build\n```\n*Binaries will be located in `build\u002Fbin\u002F`.*\n\n---\n\n## 5. Configuration\n\n### LLM Setup\nClick the **Settings** (gear icon) in the app to configure providers:\n1.  **Provider:** Select OpenAI, Gemini, or OpenRouter.\n2.  **API Key:** Paste your key (stored locally).\n3.  **Model:** Select your preferred model (e.g., `gpt-4o`, `gemini-2.5-pro`, `claude-3.5-sonnet`).\n\n### Custom Rules\nYou can define global excludes (like `node_modules`, `dist`, `.git`) and custom prompt instructions that are appended to every request.\n\n---\n\n## 6. Output Format\n\nShotgun generates context optimized for LLM parsing:\n\n```xml\n\u003Cfile path=\"backend\u002Fmain.go\">\npackage main\n...\n\u003C\u002Ffile>\n\n\u003Cfile path=\"frontend\u002Fsrc\u002FApp.vue\">\n\u003Ctemplate>\n...\n\u003C\u002Ftemplate>\n\u003C\u002Ffile>\n```\n\nThis format allows models to understand file boundaries perfectly, enabling accurate multi-file refactoring suggestions.\n\n---\n\n## 7. ⚖️ License & Usage\n\nMy name is Gleb Curly, and I am an indie developer making software for a living.\n\nShotgun is developed and maintained by **Curly's Technology Tmi**. \n\nThis project uses a **Community License** model:\n\n### 1. Free for Small Teams & Non-Commercial Use\nYou can use Shotgun for free (including modification and internal use) if:\n- Your company\u002Fteam generates **less than $1M USD** in annual revenue.\n- You do **not** use the code to build a competing public product.\n\n### 2. Commercial License (Enterprise)\nIf your annual revenue exceeds **$1M USD**, you are required to purchase a commercial license with a pretty reasonable price.\n\nPlease contact me at **glebkudr@gmail.com** for pricing.\n\nSee [LICENSE.md](LICENSE.md) for the full legal text.\n\n---\n\n*Shotgun – Load, Aim, Blast your code into the future.*\n","Shotgun 是一个用于大型语言模型工作流的一键式代码库“爆炸”工具。它能够智能地打包项目上下文，并直接针对OpenAI（GPT-4o\u002FGPT-5）、Google Gemini或OpenRouter执行提示，从而为用户提供从本地代码库到强大LLM的桥梁。其核心功能包括基于AI的智能文件选择、直接API集成以及内置的提示工程模板等。适用于需要快速准备大量代码上下文供AI处理的场景，如代码审查、重构或文档生成等，极大地提高了开发者利用AI进行代码相关工作的效率和准确性。","2026-06-11 03:44:54","high_star"]