open-taranis

# open-taranis

Python framework for AI agents logic-only coding with streaming, tool calls, and multi-LLM provider support.

Only the **"fairly stable"** versions are published on PyPi, but to get the latest experimental versions, clone this repository and install it !

## Installation

```bash
pip install open-taranis --upgrade
```
For package on **PyPi**


**or**
```bash
git clone https://github.com/SyntaxError4Life/open-taranis && cd open-taranis/ && pip install .
```
For last version

## Quick Start

<details><summary><b>Simplest</b></summary>

```python
import open_taranis as T

client = T.clients.openrouter() # API_KEY in env_var

messages = [
    T.create_user_prompt("Tell me about yourself")
]

stream = T.clients.openrouter_request(
    client=client,
    messages=messages,
    model="nvidia/nemotron-3-nano-30b-a3b:free", 
)

print("assistant : ",end="")
for token, tool, tool_bool in T.handle_streaming(stream) : 
    if token :
        print(token, end="")
```
</details> 

<details><summary><b>Make a simple agent with a context windows on the 6 last turns</b></summary>

```python
import open_taranis as T

class Agent(T.agent_base):
    def __init__(self):
        super().__init__()

        self.client = T.clients.openrouter()
        self._system_prompt = [T.create_system_prompt(
            "You're an agent nammed **Taranis** !"
        )]


    def create_stream(self):
        return T.clients.openrouter_request(
            client=self.client,
            messages=self._system_prompt+self.messages,
            model="nvidia/nemotron-3-nano-30b-a3b:free"
        )

    def manage_messages(self):
        self.messages = self.messages[-12:] # Each turn have 1 user and 1 assistant

My_agent = Agent()

while True :
    prompt = input("user : ")

    print("\n\nagent : ", end="")

    for t in My_agent(prompt):
        print(t, end="", flush=True)
    
    print("\n\n","="*60,"\n")
```
</details>

<details><summary><b>To create a simple display using gradio a