# CodeIndexer
[](https://badge.fury.io/py/codeindexer)
A lightweight CLI tool for indexing codebases to provide context for LLMs.
## Why ?
Still doing some finger-hurting typing or copy-pasting just to update your LLM about code changes or set up context in new chats (the old way 😅, without copilots)?
I run this tool to generate a structured prompt with my project files, so all I have to do is copy, paste, and the model is ready to go! ⌛⏱️✨
## Installation ℹ️
```bash
pip install codeindexer
# Basic usage
codeindexer --index ./my_repo --format md index_file.md
# Filter by file extensions (create a txt prompt file index_file.txt)
codeindexer --index ./my_repo --only .py,.js,.md --format txt index_file.txt
# Skip specific directories or files (create a json prompt file index_file.json)
codeindexer --index ./my_repo --skip node_modules/,venv/,*.log --format json index_file.json
# Explicitly include files/paths (even if ignored by .gitignore)
codeindexer --index ./my_repo --include important.log,temp/config.json --format md index_file.md
# Add a custom prompt at the end
codeindexer --index ./my_repo --prompt "Analyze and suggest improvements." --format md index_file.md
# Disable .gitignore parsing
codeindexer --index ./my_repo --no-gitignore --format md index_file.md
# Split the prompt into multiple parts e.g 1000 lines max (place prompt parts in the index_file/... folder)
codeindexer --index ./my_repo --format md index_file.md --split 1000
````
Example of indexed output file (index_file.md) 📋
```tree
# Repo: my_repo
# Folder structure:
my_repo/
├── src/
│ ├── main.py
│ ├── utils.py
├── tests/
│ ├── test_main.py
├── README.md
├── requirements.txt
# Files
# my_repo/requirements.txt
{contents of my_repo/requirements.txt}
# my_repo/README.md
{contents of my_repo/README.md}
# my_repo/src/main.py
{contents of my_repo/src/main.py}
...
________________________________________
Acknowledge the project's description and files, do no provide additional explanation, wait for instructions
```
## Options 🔧
- `--index`: Directory to index (required)
- `--only`: Comma-separated list of file extensions to include (e.g., .py,.js,.md)
- `--skip`: Comma-separated list of patterns to skip (e.g., node_modules/,venv/,*.log)
- `--include`: Comma-separated list of patterns to explicitly include even if in .gitignore
- `--format`: Output format (md, txt, json) - default is md
- `--prompt`: Custom prompt to add at the end of the index
- `--no-skip-env`: Include .env files (by default they are skipped)
- `--no-gitignore`: Disable automatic parsing of .gitignore files (enabled by default)
- `--split`: Split output into chunks with specified max lines per file (default: 1000)
## Features ✨
- ✅ Generate a single file with your repo’s structure and files
- ✅ Automatically respects .gitignore rules 📋
- ✅ Filters files by extension and skips binaries 🔍
- ✅ Multiple output formats: Markdown, text, JSON 📝
- ✅ Add a custom prompt for LLM context 🤖
- ✅ Split output files into small parts
## Contributing 🤝
Contributions are welcome! Please check out our [Contributing Guide](CONTRIBUTING.md) for details on how to get started.
## License
MIT
Raw data
{
"_id": null,
"home_page": null,
"name": "codeindexer",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "productivity, open-source, code, prompt, indexing, gemini, codebase, llama, cursor, copilot, copy-paste, claude, groq, llm, prompt-engineering, llms, chatgpt, deepseek",
"author": null,
"author_email": "Franklin Kemta <hi@franklinkemta.com>",
"download_url": "https://files.pythonhosted.org/packages/3c/98/2fd5d79cb05d84164e7806303a2840bf0b7bb741e15d91baa49ae43fd004/codeindexer-0.1.2.tar.gz",
"platform": null,
"description": "# CodeIndexer\n\n[](https://badge.fury.io/py/codeindexer)\n\nA lightweight CLI tool for indexing codebases to provide context for LLMs.\n\n## Why ?\n\nStill doing some finger-hurting typing or copy-pasting just to update your LLM about code changes or set up context in new chats (the old way \ud83d\ude05, without copilots)?\n\nI run this tool to generate a structured prompt with my project files, so all I have to do is copy, paste, and the model is ready to go! \u231b\u23f1\ufe0f\u2728\n\n## Installation \u2139\ufe0f\n\n```bash\npip install codeindexer\n\n# Basic usage\ncodeindexer --index ./my_repo --format md index_file.md\n\n# Filter by file extensions (create a txt prompt file index_file.txt)\ncodeindexer --index ./my_repo --only .py,.js,.md --format txt index_file.txt\n\n# Skip specific directories or files (create a json prompt file index_file.json)\ncodeindexer --index ./my_repo --skip node_modules/,venv/,*.log --format json index_file.json\n\n# Explicitly include files/paths (even if ignored by .gitignore)\ncodeindexer --index ./my_repo --include important.log,temp/config.json --format md index_file.md\n\n# Add a custom prompt at the end\ncodeindexer --index ./my_repo --prompt \"Analyze and suggest improvements.\" --format md index_file.md\n\n# Disable .gitignore parsing\ncodeindexer --index ./my_repo --no-gitignore --format md index_file.md\n\n# Split the prompt into multiple parts e.g 1000 lines max (place prompt parts in the index_file/... folder)\ncodeindexer --index ./my_repo --format md index_file.md --split 1000\n````\n\nExample of indexed output file (index_file.md) \ud83d\udccb\n\n```tree\n# Repo: my_repo\n# Folder structure:\nmy_repo/\n\u251c\u2500\u2500 src/\n\u2502 \u251c\u2500\u2500 main.py\n\u2502 \u251c\u2500\u2500 utils.py\n\u251c\u2500\u2500 tests/\n\u2502 \u251c\u2500\u2500 test_main.py\n\u251c\u2500\u2500 README.md\n\u251c\u2500\u2500 requirements.txt\n\n# Files \n# my_repo/requirements.txt \n{contents of my_repo/requirements.txt} \n\n# my_repo/README.md \n{contents of my_repo/README.md} \n\n# my_repo/src/main.py \n{contents of my_repo/src/main.py} \n\n... \n________________________________________\n\nAcknowledge the project's description and files, do no provide additional explanation, wait for instructions\n\n```\n\n## Options \ud83d\udd27\n\n- `--index`: Directory to index (required)\n- `--only`: Comma-separated list of file extensions to include (e.g., .py,.js,.md)\n- `--skip`: Comma-separated list of patterns to skip (e.g., node_modules/,venv/,*.log)\n- `--include`: Comma-separated list of patterns to explicitly include even if in .gitignore\n- `--format`: Output format (md, txt, json) - default is md\n- `--prompt`: Custom prompt to add at the end of the index\n- `--no-skip-env`: Include .env files (by default they are skipped)\n- `--no-gitignore`: Disable automatic parsing of .gitignore files (enabled by default)\n- `--split`: Split output into chunks with specified max lines per file (default: 1000)\n\n\n## Features \u2728\n- \u2705 Generate a single file with your repo\u2019s structure and files\n- \u2705 Automatically respects .gitignore rules \ud83d\udccb\n- \u2705 Filters files by extension and skips binaries \ud83d\udd0d\n- \u2705 Multiple output formats: Markdown, text, JSON \ud83d\udcdd\n- \u2705 Add a custom prompt for LLM context \ud83e\udd16\n- \u2705 Split output files into small parts\n\n## Contributing \ud83e\udd1d\nContributions are welcome! Please check out our [Contributing Guide](CONTRIBUTING.md) for details on how to get started.\n\n## License\n\nMIT\n",
"bugtrack_url": null,
"license": null,
"summary": "A lightweight CLI to index a codebase and create a context-ready prompt file for LLM.",
"version": "0.1.2",
"project_urls": {
"Bug Tracker": "https://github.com/franklinkemta/codeindexer/issues",
"Homepage": "https://github.com/franklinkemta/codeindexer"
},
"split_keywords": [
"productivity",
" open-source",
" code",
" prompt",
" indexing",
" gemini",
" codebase",
" llama",
" cursor",
" copilot",
" copy-paste",
" claude",
" groq",
" llm",
" prompt-engineering",
" llms",
" chatgpt",
" deepseek"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "f01396357e58db5f48171c162d9b858666e0b419e7c9fdc6a593350431ee0132",
"md5": "92ffa151bce72fbcf935b2903b00eec3",
"sha256": "3f329e97695ce29b1d52b4b8faf80e1473746768cc54c21e5ca976e916044107"
},
"downloads": -1,
"filename": "codeindexer-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "92ffa151bce72fbcf935b2903b00eec3",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 14045,
"upload_time": "2025-07-13T01:55:08",
"upload_time_iso_8601": "2025-07-13T01:55:08.742580Z",
"url": "https://files.pythonhosted.org/packages/f0/13/96357e58db5f48171c162d9b858666e0b419e7c9fdc6a593350431ee0132/codeindexer-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "3c982fd5d79cb05d84164e7806303a2840bf0b7bb741e15d91baa49ae43fd004",
"md5": "98a078af8d813b9a835154728803804b",
"sha256": "36669cc665e52e1b85c687c989ac2137c107de3034b2c0a710673022ffd51c19"
},
"downloads": -1,
"filename": "codeindexer-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "98a078af8d813b9a835154728803804b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 13798,
"upload_time": "2025-07-13T01:55:09",
"upload_time_iso_8601": "2025-07-13T01:55:09.848207Z",
"url": "https://files.pythonhosted.org/packages/3c/98/2fd5d79cb05d84164e7806303a2840bf0b7bb741e15d91baa49ae43fd004/codeindexer-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-13 01:55:09",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "franklinkemta",
"github_project": "codeindexer",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "codeindexer"
}
JSON
