←back to thread

106 points codingmoh | 3 comments | | HN request time: 0s | source

Hey HN,

I’ve built Open Codex, a fully local, open-source alternative to OpenAI’s Codex CLI.

My initial plan was to fork their project and extend it. I even started doing that. But it turned out their code has several leaky abstractions, which made it hard to override core behavior cleanly. Shortly after, OpenAI introduced breaking changes. Maintaining my customizations on top became increasingly difficult.

So I rewrote the whole thing from scratch using Python. My version is designed to support local LLMs.

Right now, it only works with phi-4-mini (GGUF) via lmstudio-community/Phi-4-mini-instruct-GGUF, but I plan to support more models. Everything is structured to be extendable.

At the moment I only support single-shot mode, but I intend to add interactive (chat mode), function calling, and more.

You can install it using Homebrew:

   brew tap codingmoh/open-codex
   brew install open-codex

It's also published on PyPI:

   pip install open-codex

Source: https://github.com/codingmoh/open-codex
1. submeta ◴[] No.43760333[source]
Sounds great! Although I would prefer Claude Code to be open sourced as it’s a tool that works best for Vibe coding. Albeit expensive using Anthropic‘s models via API. There is an inofficial clone though („Anon Kode“), but it’s not legitimate.
replies(1): >>43760966 #
2. Philpax ◴[] No.43760966[source]
I believe anon-kode is a decompiled Claude Code, so it should work identically when paired with Claude.
replies(1): >>43761261 #
3. submeta ◴[] No.43761261[source]
Unfortunately it does not. Where I can feed Claude Code with a file larger than 256k, Anon Code (like Roo) will complain that the file is too large, using Gemini 2.5 Pro.