# passive-agent
A passive agent for prompt engineering experiments with instruction-based context building.
## Overview
Passive Agent is a flexible tool for building complex contexts by processing instructions that combine file content with AI completions. It's designed for prompt engineering experiments where you need to iteratively build context from multiple sources.
## Features
- 📄 Load content from files and directories
- 🤖 Integrate AI completions into context (supports OpenAI and OpenRouter)
- 🔄 Sequential processing with context accumulation
- 📊 Token usage tracking and reporting
- 🎯 Simple instruction-based workflow
## Installation
```bash
pip install passive-agent
```
Or install from source:
```bash
git clone https://github.com/yourusername/passive-agent
cd passive-agent
pip install -e .
```
## Quick Start
1. Create an `INSTRUCT.md` file with your instructions:
```
@header.md
@data/
/completion
@footer.md
```
2. Run passive-agent:
```bash
passive-agent
```
3. Check the generated files:
- `CONTEXT.md` - Complete context with all content
- `COMPLETION.json` - Raw API response
- `COMPLETION.md` - Completion text
## Example
See the `example/` directory for a complete working example:
```bash
cd example
passive-agent
```
## Configuration
### OpenAI
```bash
export OPENAI_API_KEY="your-key"
passive-agent
```
### OpenRouter
```bash
export OPENROUTER_API_KEY="your-key"
export OPENROUTER_MODEL="anthropic/claude-3-opus"
passive-agent
```
## Documentation
For detailed usage instructions, see [USAGE.md](USAGE.md).
## License
MIT License - see [LICENSE](LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "passive-agent",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "ai, context-building, llm, openai, openrouter, prompt-engineering",
"author": null,
"author_email": "Your Name <your.email@example.com>",
"download_url": "https://files.pythonhosted.org/packages/d2/b6/0f3d2cd767c4a185e2b47824789ef5098a1bda7a581931118929068a76ca/passive_agent-0.1.0.tar.gz",
"platform": null,
"description": "# passive-agent\n\nA passive agent for prompt engineering experiments with instruction-based context building.\n\n## Overview\n\nPassive Agent is a flexible tool for building complex contexts by processing instructions that combine file content with AI completions. It's designed for prompt engineering experiments where you need to iteratively build context from multiple sources.\n\n## Features\n\n- \ud83d\udcc4 Load content from files and directories\n- \ud83e\udd16 Integrate AI completions into context (supports OpenAI and OpenRouter)\n- \ud83d\udd04 Sequential processing with context accumulation\n- \ud83d\udcca Token usage tracking and reporting\n- \ud83c\udfaf Simple instruction-based workflow\n\n## Installation\n\n```bash\npip install passive-agent\n```\n\nOr install from source:\n```bash\ngit clone https://github.com/yourusername/passive-agent\ncd passive-agent\npip install -e .\n```\n\n## Quick Start\n\n1. Create an `INSTRUCT.md` file with your instructions:\n ```\n @header.md\n @data/\n /completion\n @footer.md\n ```\n\n2. Run passive-agent:\n ```bash\n passive-agent\n ```\n\n3. Check the generated files:\n - `CONTEXT.md` - Complete context with all content\n - `COMPLETION.json` - Raw API response\n - `COMPLETION.md` - Completion text\n\n## Example\n\nSee the `example/` directory for a complete working example:\n\n```bash\ncd example\npassive-agent\n```\n\n## Configuration\n\n### OpenAI\n```bash\nexport OPENAI_API_KEY=\"your-key\"\npassive-agent\n```\n\n### OpenRouter\n```bash\nexport OPENROUTER_API_KEY=\"your-key\"\nexport OPENROUTER_MODEL=\"anthropic/claude-3-opus\"\npassive-agent\n```\n\n## Documentation\n\nFor detailed usage instructions, see [USAGE.md](USAGE.md).\n\n## License\n\nMIT License - see [LICENSE](LICENSE) file for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A passive agent for prompt engineering experiments with instruction-based context building",
"version": "0.1.0",
"project_urls": {
"Documentation": "https://github.com/yourusername/passive-agent#readme",
"Homepage": "https://github.com/yourusername/passive-agent",
"Issues": "https://github.com/yourusername/passive-agent/issues",
"Repository": "https://github.com/yourusername/passive-agent"
},
"split_keywords": [
"ai",
" context-building",
" llm",
" openai",
" openrouter",
" prompt-engineering"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "efd8cd81ed71833822f94d2d758c9729ea10e2ee11aecb1a61e5736715892749",
"md5": "44592ee82be78e2a3c5c321281b2055b",
"sha256": "5b7c45e9b46b6aa974df50b559a950b9c8f271ff9fbf822ce3cdc135d46ce83a"
},
"downloads": -1,
"filename": "passive_agent-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "44592ee82be78e2a3c5c321281b2055b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 7648,
"upload_time": "2025-07-19T05:29:13",
"upload_time_iso_8601": "2025-07-19T05:29:13.978706Z",
"url": "https://files.pythonhosted.org/packages/ef/d8/cd81ed71833822f94d2d758c9729ea10e2ee11aecb1a61e5736715892749/passive_agent-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d2b60f3d2cd767c4a185e2b47824789ef5098a1bda7a581931118929068a76ca",
"md5": "b5d71031d24dd1b0eada7ec96d8c2cb7",
"sha256": "a5ea90c75b6e26497b79801f4605e377d928a5a4171762b4b2961d9070c81eb2"
},
"downloads": -1,
"filename": "passive_agent-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "b5d71031d24dd1b0eada7ec96d8c2cb7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 12633,
"upload_time": "2025-07-19T05:29:15",
"upload_time_iso_8601": "2025-07-19T05:29:15.673283Z",
"url": "https://files.pythonhosted.org/packages/d2/b6/0f3d2cd767c4a185e2b47824789ef5098a1bda7a581931118929068a76ca/passive_agent-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-19 05:29:15",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "yourusername",
"github_project": "passive-agent#readme",
"github_not_found": true,
"lcname": "passive-agent"
}
JSON
