Integrations

Since Koda speaks both the Ollama and OpenAI protocols, most compatible tools work out of the box. Just point them at http://localhost:11434.

Open WebUI

Open WebUI is a popular chat frontend for local models.

1. Start Koda's API server: koda serve
2. In Open WebUI settings, set the Ollama URL to http://localhost:11434
3. Your Koda models will appear automatically

Continue.dev

Continue is a VS Code AI coding assistant with built-in Ollama support.

1. Start Koda's API server: koda serve
2. In Continue's config, add an Ollama provider pointing to http://localhost:11434
3. Select your Koda model and start coding

LangChain

Use Koda as a local LLM backend in LangChain via the Ollama or OpenAI provider.

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="http://localhost:11434/v1",
    api_key="koda",
    model="llama3.2",
)

response = llm.invoke("What is the meaning of life?")
print(response.content)

LlamaIndex

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    api_base="http://localhost:11434/v1",
    api_key="koda",
    model="llama3.2",
)

Any OpenAI-Compatible Client

Any tool or library that supports a custom OpenAI base URL works with Koda:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:11434/v1",
    api_key="koda"
)