clovis 0.2.0

cloooooo — personal LLM client, prompt/context/thinking interface over local Ollama

clovis

OpenAI-compatible Python client over a local Ollama instance.

Install

pip install clovis

Usage

from clovis import cloooooo

client = cloooooo()  # connects to localhost:11434 by default

# Chat
resp = client.chat.completions.create(
    model="qwen3-72b",
    messages=[{"role": "user", "content": "Bonjour !"}]
)
print(resp.choices[0].message.content)

# Streaming
for chunk in client.chat.completions.create(
    messages=[{"role": "user", "content": "Écris un poème"}],
    stream=True,
):
    print(chunk.choices[0].delta.get("content", ""), end="", flush=True)

# Conversation with auto history
with client.conversation(system="Tu es un expert en finance.") as conv:
    print(conv.chat("Explique le CAPM"))
    print(conv.chat("Et ses limites ?"))  # remembers context

# Start API server
cloooooo.serve(port=8000, api_key="sk-...")

CLI

clovis "Explique les trous noirs"   # direct question
clovis repl                          # interactive conversation
clovis serve --port 8000             # start API server

Config

export CLOVIS_MODEL="qwen3-72b"
export CLOVIS_OLLAMA_URL="http://localhost:11434"
export CLOVIS_API_KEY="sk-..."