| Name | agex JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | None |
| Summary | Library-friendly agents that work directly with your existing Python codebase. |
| upload_time | 2025-08-23 16:39:29 |
| maintainer | None |
| docs_url | None |
| author | ashenfad |
| requires_python | >=3.10 |
| license | None |
| keywords |
agents
ai
llm
python
runtime
sandbox
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# agex: Library-Friendly Agents
**`agex`** (a portmanteau of **age**nt **ex**ecution) is a Python-native agentic framework that enables AI agents to work directly with your existing libraries and codebase.
**This works because** `agex` agents can accept and return complex types like `pandas.DataFrame` and `plotly.Figure` objects without intermediate JSON serialization. For a deeper dive, check out the full **[agex101.ipynb tutorial](https://ashenfad.github.io/agex/examples/agex101/)** or see **[geospatial routing with OSMnx](https://ashenfad.github.io/agex/examples/routing/)** for advanced multi-library integration.
## What Makes This Different
`agex` uses a subset of Python as the agent action space, executing actions in a sandboxed environment within your process. This approach avoids the complexity of JSON serialization and allows complex objects to flow directly between your code and the agent. You control exactly what functions, classes, and modules are available, creating a safe and focused
environment for the agent.
- **Code-as-Action**: Secure, sandboxed Python execution for agents.
- **Library Integration**: Use your existing code directly, no tool-making required.
- **Workspace Persistence**: Git-like versioning for agent state and memory.
- **Multi-Agent**: Orchestrate agents with natural Python control flow.
- **Event Streams**: Real-time, notebook-friendly observability.
- **Benchmarking**: A framework for data-driven agent evaluation.
## Documentation
Complete documentation is hosted at **[ashenfad.github.io/agex](https://ashenfad.github.io/agex/)**.
Key sections:
- **[📚 Quick Start Guide](https://ashenfad.github.io/agex/quick-start/)**
- **[🔭 The Big Picture](https://ashenfad.github.io/agex/concepts/big-picture/)**
- **[💡 Examples](https://ashenfad.github.io/agex/examples/overview/)**
- **[📖 API Reference](https://ashenfad.github.io/agex/api/overview/)**
## Installation
Install agex with your preferred LLM provider:
```bash
# Install with a specific provider
pip install "agex[openai]" # For OpenAI models
pip install "agex[anthropic]" # For Anthropic Claude models
pip install "agex[gemini]" # For Google Gemini models
# Or install with all providers
pip install "agex[all-providers]"
```
## Project Status
> **⚠️** `agex` is a new framework in active development. While the core concepts are stabilizing, the API should be considered experimental and is subject to change.
For teams looking for a more battle-tested library built on the same "agents-that-think-in-code" philosophy, we highly recommend Hugging Face's excellent [`smolagents`](https://github.com/huggingface/smolagents) project. `agex` explores a different architectural path, focusing on deep runtime interoperability and a secure, sandboxed environment for direct integration with existing Python libraries.
## Contributing
We welcome contributions! See our [Contributing Guide](CONTRIBUTING.md) for details on our development workflow, code style, and how to submit pull requests. For bug reports and feature requests, please use [GitHub Issues](https://github.com/ashenfad/agex/issues).
Raw data
{
"_id": null,
"home_page": null,
"name": "agex",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "agents, ai, llm, python, runtime, sandbox",
"author": "ashenfad",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/9e/ce/f8a2ba4f31d944385ffd6a26333b831b1733c422860db58e9a6e133c8a3e/agex-0.1.2.tar.gz",
"platform": null,
"description": "# agex: Library-Friendly Agents\n\n**`agex`** (a portmanteau of **age**nt **ex**ecution) is a Python-native agentic framework that enables AI agents to work directly with your existing libraries and codebase.\n\n\n\n**This works because** `agex` agents can accept and return complex types like `pandas.DataFrame` and `plotly.Figure` objects without intermediate JSON serialization. For a deeper dive, check out the full **[agex101.ipynb tutorial](https://ashenfad.github.io/agex/examples/agex101/)** or see **[geospatial routing with OSMnx](https://ashenfad.github.io/agex/examples/routing/)** for advanced multi-library integration.\n\n## What Makes This Different\n\n`agex` uses a subset of Python as the agent action space, executing actions in a sandboxed environment within your process. This approach avoids the complexity of JSON serialization and allows complex objects to flow directly between your code and the agent. You control exactly what functions, classes, and modules are available, creating a safe and focused\nenvironment for the agent.\n\n- **Code-as-Action**: Secure, sandboxed Python execution for agents.\n- **Library Integration**: Use your existing code directly, no tool-making required.\n- **Workspace Persistence**: Git-like versioning for agent state and memory.\n- **Multi-Agent**: Orchestrate agents with natural Python control flow.\n- **Event Streams**: Real-time, notebook-friendly observability.\n- **Benchmarking**: A framework for data-driven agent evaluation.\n\n## Documentation\n\nComplete documentation is hosted at **[ashenfad.github.io/agex](https://ashenfad.github.io/agex/)**.\n\nKey sections:\n- **[\ud83d\udcda Quick Start Guide](https://ashenfad.github.io/agex/quick-start/)**\n- **[\ud83d\udd2d The Big Picture](https://ashenfad.github.io/agex/concepts/big-picture/)**\n- **[\ud83d\udca1 Examples](https://ashenfad.github.io/agex/examples/overview/)**\n- **[\ud83d\udcd6 API Reference](https://ashenfad.github.io/agex/api/overview/)**\n\n## Installation\n\nInstall agex with your preferred LLM provider:\n\n```bash\n# Install with a specific provider\npip install \"agex[openai]\" # For OpenAI models\npip install \"agex[anthropic]\" # For Anthropic Claude models\npip install \"agex[gemini]\" # For Google Gemini models\n\n# Or install with all providers\npip install \"agex[all-providers]\"\n```\n\n## Project Status\n\n> **\u26a0\ufe0f** `agex` is a new framework in active development. While the core concepts are stabilizing, the API should be considered experimental and is subject to change.\n\nFor teams looking for a more battle-tested library built on the same \"agents-that-think-in-code\" philosophy, we highly recommend Hugging Face's excellent [`smolagents`](https://github.com/huggingface/smolagents) project. `agex` explores a different architectural path, focusing on deep runtime interoperability and a secure, sandboxed environment for direct integration with existing Python libraries.\n\n## Contributing\n\nWe welcome contributions! See our [Contributing Guide](CONTRIBUTING.md) for details on our development workflow, code style, and how to submit pull requests. For bug reports and feature requests, please use [GitHub Issues](https://github.com/ashenfad/agex/issues).\n",
"bugtrack_url": null,
"license": null,
"summary": "Library-friendly agents that work directly with your existing Python codebase.",
"version": "0.1.2",
"project_urls": {
"Documentation": "https://ashenfad.github.io/agex/",
"Homepage": "https://ashenfad.github.io/agex/",
"Issues": "https://github.com/ashenfad/agex/issues",
"Repository": "https://github.com/ashenfad/agex"
},
"split_keywords": [
"agents",
" ai",
" llm",
" python",
" runtime",
" sandbox"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "1bcc23b061cd2b03b496c4725643ced63dd8bcd181cf8f101c596ebe07886179",
"md5": "d5f209ddcfa851cdd1f3b59644d184f7",
"sha256": "a069fa47c07470159183b62a7184f88f144cfcf03ce6413e21777bf907d66631"
},
"downloads": -1,
"filename": "agex-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "d5f209ddcfa851cdd1f3b59644d184f7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 147991,
"upload_time": "2025-08-23T16:39:28",
"upload_time_iso_8601": "2025-08-23T16:39:28.071400Z",
"url": "https://files.pythonhosted.org/packages/1b/cc/23b061cd2b03b496c4725643ced63dd8bcd181cf8f101c596ebe07886179/agex-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "9ecef8a2ba4f31d944385ffd6a26333b831b1733c422860db58e9a6e133c8a3e",
"md5": "8416f277ccc45869ff63d05544345654",
"sha256": "8e5f22e7b44ce83c6534512f43d7521a497fa8fe43d33ed14bf78baf8b19e9c3"
},
"downloads": -1,
"filename": "agex-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "8416f277ccc45869ff63d05544345654",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 121089,
"upload_time": "2025-08-23T16:39:29",
"upload_time_iso_8601": "2025-08-23T16:39:29.301086Z",
"url": "https://files.pythonhosted.org/packages/9e/ce/f8a2ba4f31d944385ffd6a26333b831b1733c422860db58e9a6e133c8a3e/agex-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-23 16:39:29",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ashenfad",
"github_project": "agex",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "agex"
}
