What is code-forge?

muuchan0279/code-forge — explained in plain English

Analysis updated 2026-05-18

★ 0PythonAudience · researcherComplexity · 4/5Setup · hard

Mindmap

mindmap
  root((code-forge))
    What it does
      Decomposes coding goals
      Test first workflow
      Red to green build loop
    Tech stack
      Python
      PySide6
      pytest
      llama.cpp
    Use cases
      Build small programs locally
      Automate coding with a small model
      Optional cloud assist for planning
    Audience
      Local LLM tinkerers
      Researchers
    Notes
      Research grade MVP
      Comments in Japanese

mindmap root((code-forge)) What it does Decomposes coding goals Test first workflow Red to green build loop Tech stack Python PySide6 pytest llama.cpp Use cases Build small programs locally Automate coding with a small model Optional cloud assist for planning Audience Local LLM tinkerers Researchers Notes Research grade MVP Comments in Japanese

What do people build with it?

USE CASE 1

Have a small local AI model build a complete small program from a one line goal.

USE CASE 2

Test whether a local 27B model can do agentic coding without a bigger GPU or more context.

USE CASE 3

Run coding tasks as an automated HTTP service instead of the GUI.

USE CASE 4

Optionally route only planning and test generation to a stronger cloud model while keeping coding local.

What is it built with?

PythonPySide6pytestllama.cpp

How does it compare?

	muuchan0279/code-forge	0xallam/my-recipe	0xhassaan/nn-from-scratch
Stars	0	—	0
Language	Python	Python	Python
Last pushed	—	2022-11-22	—
Maintenance	—	Dormant	—
Setup difficulty	hard	moderate	moderate
Complexity	4/5	2/5	4/5
Audience	researcher	general	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1h+

Requires running a local OpenAI-compatible model server, ideally a 27B model on a 24GB GPU.

So what is it?

Code Forge is a Python tool that lets a small, locally run AI model write working code on its own, without needing a bigger computer, a longer context window, or a paid API. The project's argument is that the usual fixes people reach for when a local coding model struggles, giving it more context or buying a bigger GPU, are not actually the problem. Instead, Code Forge focuses on structuring the work so a smaller model can succeed. It does this by breaking a goal into smaller subtasks, writing down a clear interface for each piece of code before anything is implemented, generating tests first, and then having the model write code in a loop until those tests pass. The plan, the tests, and the final code all refer to the exact same declared names, which is meant to stop the model from getting confused between similarly named functions. The model that writes the code is not allowed to edit the tests it is being checked against, so passing the tests actually means something. The workflow has a clear split between what the machine can check automatically, such as whether code compiles, launches, and passes its tests, and what only a human can judge, such as whether the finished program actually behaves and feels right. Code Forge is upfront that it will not falsely claim something works if a human still needs to try it out and confirm. To use it, you need a local server that speaks the OpenAI style chat API, such as one built with llama.cpp, running a capable local model. The project was tested with a 27 billion parameter model on a 24 gigabyte graphics card, using it to build a playable Tetris game. Code Forge ships with a graphical interface built in PySide6, as well as a simpler command line style HTTP service for automation. It can optionally send a few specific planning and test writing steps to a stronger cloud model from Anthropic if an API key is provided, but everything works fully locally by default. Comments inside the code are written in Japanese, since this began as a personal research project before being cleaned up and shared publicly. No license is stated in the README.

Copy-paste prompts

Prompt 1

Help me set up llama.cpp's llama-server so Code Forge can talk to my local model.

Prompt 2

Explain how Code Forge's decompose, contract, test-first, and red-green loop works together.

Prompt 3

Show me how to run forge_service.py as a headless HTTP build service.

Prompt 4

Walk me through configuring FORGE_ROLE_PLAN to route planning to a stronger model while staying local otherwise.

Frequently asked questions