# Autonomous Agent for Kubernetes
Autonomous Agent for Kubernetes powered by OpenAI.
Features:
- Autonomous Kubernetes cluster operations using LLM Agents powered by ChatGPT (GPT-3.5, GPT-4 and future versions).
- Diagnose and analyze the potential issues for Kubernetes workloads.
- Generate the Kubernetes manifests based on the provided prompt instructions.
- Utilize native kubectl and trivy commands for Kubernetes cluster access and security vulnerability scanning.
## Install
### Install locally
Install the kube-agent with the commands below. It is highly recommended to use [pipx](https://pipx.pypa.io/stable/) or [venv](https://docs.python.org/3/library/venv.html) to install the copilot to avoid conflicts with other Python packages.
```sh
# Option 1: use pipx to install the copilot
pipx install kube-agent
# Option 2: use venv to install the copilot
python3 -m venv agentenv
source agentenv/bin/activate
pip install kube-agent
# Option 3: Use pip to install the copilot (not recommended)
pip install kube-agent
```
**Setup:**
- Ensure [`kubectl`](https://kubernetes.io/docs/tasks/tools/install-kubectl-linux/) is installed on the local machine and the kubeconfig file is configured for Kubernetes cluster access.
- Install [`trivy`](https://github.com/aquasecurity/trivy) to assess container image security issues (for the `audit` command).
- Set the OpenAI [API key](https://platform.openai.com/account/api-keys) as the `OPENAI_API_KEY` environment variable to enable ChatGPT functionality.
- For [Azure OpenAI service](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/quickstart?tabs=command-line&pivots=rest-api#retrieve-key-and-endpoint), please set `AZURE_OPENAI_API_KEY=<key>` and `AZURE_OPENAI_ENDPOINT=https://<replace-this>.openai.azure.com/`.
### Run in Kubernetes
```sh
kubectl run -it --rm copilot \
--env="OPENAI_API_KEY=$OPENAI_API_KEY" \
--restart=Never \
--image=ghcr.io/feiskyer/kube-agent \
-- execute --verbose 'What Pods are using max memory in the cluster'
kubectl run -it --rm copilot \
--env="AZURE_OPENAI_API_KEY=$AZURE_OPENAI_API_KEY" \
--env="AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" \
--restart=Never \
--image=ghcr.io/feiskyer/kube-agent \
-- execute --verbose 'What Pods are using max memory in the cluster'
```
Refer [kubernetes.md](kubernetes.md) for more detailed steps.
## How to use
Running directly in the terminal:
```sh
Usage: kube-agent [OPTIONS] COMMAND [ARGS]...
Kubernetes Copilot powered by OpenAI
Options:
--version Show the version and exit.
--help Show this message and exit.
Commands:
analyze analyze issues for a given resource
audit audit security issues for a Pod
diagnose diagnose problems for a Pod
execute execute operations based on prompt instructions
generate generate Kubernetes manifests
```
### Audit Security Issues for Pod
`kube-agent audit POD [NAMESPACE]` will audit security issues for a Pod:
```sh
Usage: kube-agent audit [OPTIONS] POD [NAMESPACE]
audit security issues for a Pod
Options:
--verbose Enable verbose information of copilot execution steps
--model MODEL OpenAI model to use for copilot execution, default is gpt-4
--help Show this message and exit.
```
### Diagnose Problems for Pod
`kube-agent diagnose POD [NAMESPACE]` will diagnose problems for a Pod:
```sh
Usage: kube-agent diagnose [OPTIONS] POD [NAMESPACE]
diagnose problems for a Pod
Options:
--verbose Enable verbose information of copilot execution steps
--model MODEL OpenAI model to use for copilot execution, default is gpt-4
--help Show this message and exit.
```
### Analyze Potential Issues for k8s Object
`kube-agent analyze RESOURCE NAME [NAMESPACE]` will analyze potential issues for the given resource object:
```sh
Usage: kube-agent analyze [OPTIONS] RESOURCE NAME [NAMESPACE]
analyze issues for a given resource
Options:
--verbose Enable verbose information of copilot execution steps
--model TEXT OpenAI model to use for copilot execution, default is gpt-4
--help Show this message and exit.
```
### Execute Operations Based on Prompt Instructions
`kube-agent execute INSTRUCTIONS` will execute operations based on prompt instructions.
It could also be used to ask any questions.
```sh
Usage: kube-agent execute [OPTIONS] INSTRUCTIONS
execute operations based on prompt instructions
Options:
--verbose Enable verbose information of copilot execution steps
--model MODEL OpenAI model to use for copilot execution, default is gpt-4
--help Show this message and exit.
```
### Generate Kubernetes Manifests
Use the `kube-agent generate` command to create Kubernetes manifests based on
the provided prompt instructions. After generating the manifests, you will be
prompted to confirm whether you want to apply them.
```sh
Usage: kube-agent generate [OPTIONS] INSTRUCTIONS
generate Kubernetes manifests
Options:
--verbose Enable verbose information of copilot execution steps
--model TEXT OpenAI model to use for copilot execution, default is gpt-4
--help Show this message and exit.
```
## Contribution
The project is opensource at github [feiskyer/kube-agent](https://github.com/feiskyer/kube-agent) with Apache License.
If you would like to contribute to the project, please follow these guidelines:
1. Fork the repository and clone it to your local machine.
2. Create a new branch for your changes.
3. Make your changes and commit them with a descriptive commit message.
4. Push your changes to your forked repository.
5. Open a pull request to the main repository.
Raw data
{
"_id": null,
"home_page": "https://github.com/feiskyer/kube-agent",
"name": "kube-agent",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": "kubernetes, copilot, openai, chatgpt, agent, ai, agentic",
"author": "Pengfei Ni",
"author_email": "feiskyer@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/77/7b/4af1df1bf29aca61faa048bfe69314ac075598a3d285be1389a7aa7b10de/kube_agent-0.2.0.tar.gz",
"platform": null,
"description": "# Autonomous Agent for Kubernetes\n\nAutonomous Agent for Kubernetes powered by OpenAI.\n\nFeatures:\n\n- Autonomous Kubernetes cluster operations using LLM Agents powered by ChatGPT (GPT-3.5, GPT-4 and future versions).\n- Diagnose and analyze the potential issues for Kubernetes workloads.\n- Generate the Kubernetes manifests based on the provided prompt instructions.\n- Utilize native kubectl and trivy commands for Kubernetes cluster access and security vulnerability scanning.\n\n## Install\n\n### Install locally\n\nInstall the kube-agent with the commands below. It is highly recommended to use [pipx](https://pipx.pypa.io/stable/) or [venv](https://docs.python.org/3/library/venv.html) to install the copilot to avoid conflicts with other Python packages.\n\n```sh\n# Option 1: use pipx to install the copilot\npipx install kube-agent\n\n# Option 2: use venv to install the copilot\npython3 -m venv agentenv\nsource agentenv/bin/activate\npip install kube-agent\n\n# Option 3: Use pip to install the copilot (not recommended)\npip install kube-agent\n```\n\n**Setup:**\n\n- Ensure [`kubectl`](https://kubernetes.io/docs/tasks/tools/install-kubectl-linux/) is installed on the local machine and the kubeconfig file is configured for Kubernetes cluster access.\n- Install [`trivy`](https://github.com/aquasecurity/trivy) to assess container image security issues (for the `audit` command).\n- Set the OpenAI [API key](https://platform.openai.com/account/api-keys) as the `OPENAI_API_KEY` environment variable to enable ChatGPT functionality.\n - For [Azure OpenAI service](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/quickstart?tabs=command-line&pivots=rest-api#retrieve-key-and-endpoint), please set `AZURE_OPENAI_API_KEY=<key>` and `AZURE_OPENAI_ENDPOINT=https://<replace-this>.openai.azure.com/`.\n\n### Run in Kubernetes\n\n```sh\nkubectl run -it --rm copilot \\\n --env=\"OPENAI_API_KEY=$OPENAI_API_KEY\" \\\n --restart=Never \\\n --image=ghcr.io/feiskyer/kube-agent \\\n -- execute --verbose 'What Pods are using max memory in the cluster'\n\nkubectl run -it --rm copilot \\\n --env=\"AZURE_OPENAI_API_KEY=$AZURE_OPENAI_API_KEY\" \\\n --env=\"AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT\" \\\n --restart=Never \\\n --image=ghcr.io/feiskyer/kube-agent \\\n -- execute --verbose 'What Pods are using max memory in the cluster'\n```\n\nRefer [kubernetes.md](kubernetes.md) for more detailed steps.\n\n## How to use\n\nRunning directly in the terminal:\n\n```sh\nUsage: kube-agent [OPTIONS] COMMAND [ARGS]...\n\n Kubernetes Copilot powered by OpenAI\n\nOptions:\n --version Show the version and exit.\n --help Show this message and exit.\n\nCommands:\n analyze analyze issues for a given resource\n audit audit security issues for a Pod\n diagnose diagnose problems for a Pod\n execute execute operations based on prompt instructions\n generate generate Kubernetes manifests\n```\n\n### Audit Security Issues for Pod\n\n`kube-agent audit POD [NAMESPACE]` will audit security issues for a Pod:\n\n```sh\nUsage: kube-agent audit [OPTIONS] POD [NAMESPACE]\n\n audit security issues for a Pod\n\nOptions:\n --verbose Enable verbose information of copilot execution steps\n --model MODEL OpenAI model to use for copilot execution, default is gpt-4\n --help Show this message and exit.\n```\n\n### Diagnose Problems for Pod\n\n`kube-agent diagnose POD [NAMESPACE]` will diagnose problems for a Pod:\n\n```sh\nUsage: kube-agent diagnose [OPTIONS] POD [NAMESPACE]\n\n diagnose problems for a Pod\n\nOptions:\n --verbose Enable verbose information of copilot execution steps\n --model MODEL OpenAI model to use for copilot execution, default is gpt-4\n --help Show this message and exit.\n```\n\n### Analyze Potential Issues for k8s Object\n\n`kube-agent analyze RESOURCE NAME [NAMESPACE]` will analyze potential issues for the given resource object:\n\n```sh\nUsage: kube-agent analyze [OPTIONS] RESOURCE NAME [NAMESPACE]\n\n analyze issues for a given resource\n\nOptions:\n --verbose Enable verbose information of copilot execution steps\n --model TEXT OpenAI model to use for copilot execution, default is gpt-4\n --help Show this message and exit.\n```\n\n### Execute Operations Based on Prompt Instructions\n\n`kube-agent execute INSTRUCTIONS` will execute operations based on prompt instructions.\nIt could also be used to ask any questions.\n\n```sh\nUsage: kube-agent execute [OPTIONS] INSTRUCTIONS\n\n execute operations based on prompt instructions\n\nOptions:\n --verbose Enable verbose information of copilot execution steps\n --model MODEL OpenAI model to use for copilot execution, default is gpt-4\n --help Show this message and exit.\n```\n\n### Generate Kubernetes Manifests\n\nUse the `kube-agent generate` command to create Kubernetes manifests based on\nthe provided prompt instructions. After generating the manifests, you will be\nprompted to confirm whether you want to apply them.\n\n```sh\nUsage: kube-agent generate [OPTIONS] INSTRUCTIONS\n\n generate Kubernetes manifests\n\nOptions:\n --verbose Enable verbose information of copilot execution steps\n --model TEXT OpenAI model to use for copilot execution, default is gpt-4\n --help Show this message and exit.\n```\n\n## Contribution\n\nThe project is opensource at github [feiskyer/kube-agent](https://github.com/feiskyer/kube-agent) with Apache License.\n\nIf you would like to contribute to the project, please follow these guidelines:\n\n1. Fork the repository and clone it to your local machine.\n2. Create a new branch for your changes.\n3. Make your changes and commit them with a descriptive commit message.\n4. Push your changes to your forked repository.\n5. Open a pull request to the main repository.\n",
"bugtrack_url": null,
"license": null,
"summary": "A Kubernetes copilot agent powered by OpenAI",
"version": "0.2.0",
"project_urls": {
"Homepage": "https://github.com/feiskyer/kube-agent",
"Repository": "https://github.com/feiskyer/kube-agent"
},
"split_keywords": [
"kubernetes",
" copilot",
" openai",
" chatgpt",
" agent",
" ai",
" agentic"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "c01336b0ec015157d77370da387c2e3fa1dae0b9661545d0bc99635780541971",
"md5": "02e539e59f239ef0208db4afb51128fb",
"sha256": "72c1c6d1bf1d146a30edd3e9453226335cc4ef5102590b82398d335a43265934"
},
"downloads": -1,
"filename": "kube_agent-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "02e539e59f239ef0208db4afb51128fb",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 31806,
"upload_time": "2024-11-13T13:00:44",
"upload_time_iso_8601": "2024-11-13T13:00:44.194495Z",
"url": "https://files.pythonhosted.org/packages/c0/13/36b0ec015157d77370da387c2e3fa1dae0b9661545d0bc99635780541971/kube_agent-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "777b4af1df1bf29aca61faa048bfe69314ac075598a3d285be1389a7aa7b10de",
"md5": "a2c3cb1d4291473d685077e5356d623d",
"sha256": "1342185c9e4e27e35ecff07c688292081845add12acd6908496e8d7d4360acfc"
},
"downloads": -1,
"filename": "kube_agent-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "a2c3cb1d4291473d685077e5356d623d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 29077,
"upload_time": "2024-11-13T13:00:45",
"upload_time_iso_8601": "2024-11-13T13:00:45.720499Z",
"url": "https://files.pythonhosted.org/packages/77/7b/4af1df1bf29aca61faa048bfe69314ac075598a3d285be1389a7aa7b10de/kube_agent-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-13 13:00:45",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "feiskyer",
"github_project": "kube-agent",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "kube-agent"
}
JSON
