[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-81436":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":13,"stars30d":17,"stars90d":15,"forks30d":15,"starsTrendScore":17,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":15,"starSnapshotCount":15,"syncStatus":13,"lastSyncTime":27,"discoverSource":28},81436,"pi-piqo","piqoni\u002Fpi-piqo","piqoni","A good invisible interface to agents","",null,"TypeScript",36,2,33,0,1,3,44.73,"MIT License",false,"main",true,[],"2026-06-12 04:01:33","# Piqo — Pi Extension\n\nA chat-less way to collaborate with your favorite LLM models (remote or local), directly from your files and from any editor. The output is stored automatically into your files.\n\nIt is a simple file-watcher extension for [pi](https:\u002F\u002Fgithub.com\u002Fbadlogic\u002Fpi-mono) triggered on-save, which continously monitors directories for `@piqo` markers and uses the LLM to generate content inline.\n\nMight be useful for keeping notes, writing tasks, researching topics, etc. \n\nRandom Example: \nIf you write the following (highlighted line) and save the file:\n\u003Cimg width=\"719\" height=\"160\" alt=\"Image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F30eda1ca-34ad-468a-baef-52db15169573\" \u002F>\n\nYou will get something like (using gpt-5.4-mini): \n\n\u003Cimg width=\"718\" height=\"267\" alt=\"Image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F8f0c9a27-c366-4022-8e27-e188a0e19188\" \u002F>\n\n## How It Works\n\n1. You start pi with the piqo extension and specify directories to watch\n2. Piqo recursively watches those directories for file changes\n3. When a file contains one or more `@piqo \u003Cinstruction>` markers, it reads the file, gathers context around all markers, and sends them to pi's LLM in one request\n4. The LLM fulfills each prompt and removes the human prompt line\u002Ftag from the file\n\n## Usage\nIf you have [Pi](https:\u002F\u002Fpi.dev\u002F) installed, you are one command away from using it:\n\n```bash\n# Load it directly from npm (or alternatively a github repo url)\npi -e npm:pi-piqo --dir=\u002Fpath\u002Fto\u002Fyour\u002Fproject\n```\n\nOther options: \n```bash\n# Or if you want to reference a local checkout of this repo\npi -e . --dir=\u002Fpath\u002Fto\u002Fyour\u002Fproject\n\n# Watch multiple directories\npi -e . --dir=\u002Fpath\u002Fto\u002Fdir1,\u002Fpath\u002Fto\u002Fdir2\n\n# Headless mode (no TUI)\npi -e . --dir=\u002Fpath\u002Fto\u002Fproject -p \"Start piqo watcher\"\n```\n\nUse exactly one loading mode at a time:\n\n- If you use `pi -e ...`, do not also rely on a globally installed `pi-piqo`.\n- If you installed `pi-piqo` globally with `pi install npm:pi-piqo`, run `pi --dir=...` without `-e`.\n\n## Marker Format\n\nIn any text file within the watched directories, add:\n\n```\n@piqo \u003Cyour instruction here>\n```\n\nThe LLM will process it and replace\u002Fremove the prompt so the file becomes:\n\n```\n... generated content ...\n```\n\n### Examples\n\n**In a Python file:**\n```python\n# @piqo add a function to parse CSV files and return a list of dicts\n\n# Becomes generated code with the @piqo prompt removed\n```\n\n**In a Markdown file:**\n```markdown\n@piqo write a summary of REST API best practices\n\nBecomes generated content with the @piqo prompt removed\n```\n\n**In a config file:**\n```yaml\n# @piqo add sensible default nginx config for a Node.js app\n\n# Becomes generated config with the @piqo prompt removed\n```\n\n## Behavior Details\n\n- **Debounce**: File changes are debounced at 500ms per file to avoid duplicate processing\n- **Initial scan**: On startup, piqo scans all watched directories for existing markers\n- **Ignored paths**: Hidden files\u002Fdirs, `node_modules`, `.git` are automatically skipped\n- **Text files only**: Only processes common text file extensions (.ts, .js, .py, .md, .txt, etc.)\n\n## Installation\n\nTo install it for your Pi globally:\n```\npi install npm:pi-piqo\n```\n\nAfter that, run Pi with just `--dir` for the directory you want to monitor:\n\n```bash\npi --dir=\u002Fpath\u002Fof\u002Fyour\u002Fproject\n```\n","Piqo是一个用于与你喜欢的LLM模型（远程或本地）直接从文件和任何编辑器中协作的无聊天界面工具。其核心功能是通过文件监视扩展来检测带有`@piqo`标记的文件，并使用LLM生成内容并自动存储到文件中。该工具基于TypeScript开发，支持在保存文件时触发处理过程。适用于需要保持笔记、编写任务、研究主题等场景，特别适合那些希望在不离开编辑环境的情况下利用AI辅助完成工作的开发者或研究人员。","2026-06-11 04:05:03","CREATED_QUERY"]