https://github.com/kaikaikaifang/divine-agent

Creating Your Divine Agent 😇
https://github.com/kaikaikaifang/divine-agent

agent agents ai monorepo observability sdk-python

Last synced: 4 months ago
JSON representation

Creating Your Divine Agent 😇

• Host: GitHub
• URL: https://github.com/kaikaikaifang/divine-agent
• Owner: Kaikaikaifang
• License: mit
• Created: 2025-01-15T10:29:32.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2025-05-26T15:52:11.000Z (5 months ago)
• Last Synced: 2025-06-27T11:07:36.978Z (4 months ago)
• Topics: agent, agents, ai, monorepo, observability, sdk-python
• Language: TypeScript
• Homepage: https://docs.divine-agent.com
• Size: 3.69 MB
• Stars: 10
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Contributing: docs/CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: docs/CODE_OF_CONDUCT.md
  • Security: docs/SECURITY.md

Awesome Lists containing this project

README

          


  



Divine Agent – Fully open-source agent observability. Simple. Clear.






    







    中文 / English



divine-agent is an observability tool for LLM-based agents, offering tracing, evaluation, and usage statistics.

---

> [!IMPORTANT]

> **divine-agent is currently experimental** and may undergo significant changes at any time. This project is in active development, which means APIs and features might change without prior notice.

>

> We do not recommend using divine-agent in production environments until a stable release is available.

## Install

Requires Python 3.11+

```shell

pip install divi

```

## Trace

1. Get API Key from [Web](https://www.divine-agent.com/dashboard/api-keys).

2. Create a `.env` file and add the following line:

  ```env

  DIVI_API_KEY=your_api_key

  ```

3. Run the following code:

  ```python

  from divi import obs_openai, observable

  from dotenv import load_dotenv

  from openai import OpenAI

  load_dotenv()

  class Pirate:

      def __init__(self):

          self.client = obs_openai(

              OpenAI(),

              name="Pirate",

          )

      @observable(name="Talk with pirate")

      def talk(self, message: str):

          """Talk like a pirate."""

          res = self.client.chat.completions.create(

              model="gpt-4o",

              messages=[

                  {"role": "developer", "content": "Talk like a pirate."},

                  {

                      "role": "user",

                      "content": message,

                  },

              ],

          )

          return res.choices[0].message.content

  pirate = Pirate()

  pirate.talk("How do I check if a Python object is an instance of a class?")

  ```