gitwtfhub

wtf is learning-pi-through-force?

muellerzr/learning-pi-through-force — explained in plain English

Analysis updated 2026-05-18

8PythonAudience · developer

TL;DR

A shared personal configuration for the pi AI coding agent, including custom model routing, research skills, and writing subagents.

Mindmap

mindmap
  root((learning pi through force))
    What it does
      Shares pi agent config
      Routes tasks to models
      Adds custom skills
    Tech stack
      Python
      pi agent
      Self hosted models
    Use cases
      Copy a working pi setup
      Run research pipelines
      Automate model research
    Audience
      Developers
      AI agent users
    Setup
      Copy config files
      Add API keys
      Fill in secrets

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Copy a ready-made pi agent configuration to route tasks between multiple self-hosted models.

REASON 2

Reuse a research pipeline skill that retrieves, checks, and summarizes sources with citations.

REASON 3

Automatically generate a report on a newly released HuggingFace model.

REASON 4

Set up a dedicated writing subagent for drafts, outlines, and edits.

What's in the stack?

Pythonpi agentGLM-5.2Kimi K2.7DeepSeek V4

How it stacks up

muellerzr/learning-pi-through-force100/awesome-machine-learningadam-s/car-diagnosis
Stars888
LanguagePythonPythonPython
Last pushed2024-08-07
MaintenanceStale
Setup difficultyeasymoderate
Complexity1/53/5
Audiencedeveloperdeveloperresearcher

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

Wtf does this do

This repository is a personal setup shared by the author of a blog about learning to use an AI coding agent called pi. It packages up the configuration files, custom skills, and custom subagents that the author built on top of a standard pi install, so anyone else who uses pi can copy the same setup into their own machine and get the same behavior. At the center of it is a model routing configuration that decides which AI model handles which kind of task. The author runs three self-hosted models: one used for strong reasoning and planning, one used as a fast coding assistant, and one used as a cheap model for quick lookups and retrieval. A settings file assigns each type of subagent role, such as scout, planner, or worker, to one of these models along with how much the model is allowed to think before answering. On top of the models, the repository includes two custom subagents. One is a fast retriever built for pulling together research sources in parallel, deliberately using the cheaper model so the stronger model is saved for harder synthesis work. The other is an editorial agent meant for writing tasks like outlines, drafts, and rewrites. It also includes four custom skills. One is a multi-step research pipeline that scopes a question, plans research, retrieves sources, checks them against each other, and produces a final written report with citations. Another safely fetches academic papers from arXiv. A third pulls model information from HuggingFace. The last one researches a newly released HuggingFace model and produces a full report, which can optionally be emailed or sent to a Kindle device. Every credential in the repository has been replaced with a placeholder, so before using any of this, a person needs to fill in their own API keys and endpoint addresses. The install instructions are simple copy commands that drop the files into the standard pi configuration folder. This is aimed squarely at people who already use the pi agent and want to see or reuse someone else's working configuration.

Yoink these prompts

Prompt 1
Help me set up this pi agent configuration by filling in my own API keys in models.json.
Prompt 2
Explain how the settings.json file routes different subagent roles to different models.
Prompt 3
Walk me through installing the deep-research skill into my own pi agent setup.
Prompt 4
Show me how the hf-model-researcher skill generates a report on a new HuggingFace model.

Frequently asked questions

wtf is learning-pi-through-force?

A shared personal configuration for the pi AI coding agent, including custom model routing, research skills, and writing subagents.

What language is learning-pi-through-force written in?

Mainly Python. The stack also includes Python, pi agent, GLM-5.2.

Who is learning-pi-through-force for?

Mainly developer.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.