OpenAI Codex with Ollama Integration

Ollama has integrated with the OpenAI Codex CLI, allowing users to run open-weight models locally to read, modify, and execute code within a working directory. This integration enables developers to leverage the Codex CLI's capabilities while maintaining control over their models and data through Ollama.

Local Code Execution with Open Models

Open-weight models can now be used with the OpenAI Codex CLI via Ollama. This allows the CLI to perform actions such as reading and modifying code in the local working directory and executing that code. Supported models include gpt-oss:20b and gpt-oss:120b, as well as other open-weight alternatives available through Ollama.

Setup and Configuration

To use open models with the Codex CLI, users must first install the CLI via npm:

npm install -g @openai/codex

To activate the integration, the CLI is started with the --oss flag:

codex --oss

By default, the system uses the gpt-oss:20b model. Users can specify a different model using the -m flag, for example:

codex --oss -m gpt-oss:120b

Context Window Requirements

Because Codex requires a large context window to operate effectively, Ollama recommends a minimum of 32K tokens. Users can adjust the context length settings within Ollama to meet this requirement.

Cloud Model Support

In addition to local models, all models hosted on Ollama Cloud are compatible with the Codex CLI using the --oss flag. For example, users can access cloud-hosted versions of the models:

codex --oss -m gpt-oss:120b-cloud

Sources

Related

  • Dispatch
    OpenAI gpt-oss Release on Ollama

    Ollama has partnered with OpenAI to integrate the gpt-oss open weight models, offering 20B and 120B parameter versions optimized for local execution via the MXFP4 quantization format.

  • Dispatch
    Run Code Llama locally with Ollama

    Meta's Code Llama models are now runnable locally via Ollama, offering 7B, 13B, and 34B parameter versions plus code and Python specializations for programming tasks.

  • Project
    ollama/ollama

    Ollama is a cross‑platform runtime that lets you download and run open‑source large language models locally. It offers a CLI, a REST API (localhost:11434), and official Python/JS SDKs, plus many community integrations (web UIs, LangChain, AutoGPT, etc.). Install with a one‑line script or Docker, then launch models like `ollama run gemma4` or use `ollama launch` to connect to coding assistants or personal bots.

  • Dispatch
    Ollama Tool Support Release

    Ollama has introduced tool calling support for models like Llama 3.1, allowing local LLMs to interact with external APIs, functions, and code interpreters.

  • Dispatch
    Ollama OpenAI Compatibility Update

    Ollama has introduced built-in compatibility with the OpenAI Chat Completions API, allowing users to run local models using existing OpenAI-compatible tools and libraries.