Cheasee-Pi: Build Your Own PI. Cheap. Easy. Secure.

Token-saving agent harness with security guardrails and a Kanban git-oriented sub-agent framework. Docker + Pi AI — autonomous Kanban pipeline, sandboxed execution, real-time feedback via git worktrees for parallel development.

Cheasee-Pi TUI — multi-agent Kanban pipeline

What is Cheasee-Pi?

Cheasee-Pi is a Pi agent harness built on the Pi coding agent — engineered to save tokens, enforce security boundaries, and drive sub-agents through a Kanban git-oriented workflow. It uses a GitHub Project board to orchestrate an autonomous multi-agent pipeline — Researcher → Architect → TestDesigner → Developer → Auditor — with tools that minimise token waste, enforce security boundaries, and streamline development inside isolated git worktrees.

All components run locally. No code leaves your machine (except LLM API calls to your provider).

Extensions overview

Extension	Purpose
Structural Analyzer	AST-aware code search via ast-grep
Ripgrep Search	Fast literal/regex code search
Supervisor	Kanban-driven multi-agent pipeline
Web Crawler	Web crawling with Scrapling + Cloudflare bypass
Web Search	DuckDuckGo search via ddgs Python lib
Context Info	Rich TUI status bar (branch, model, tokens, TPS, cache)
Session Logger	Session logging to JSONL with Markdown reports
Agent Harness	Runtime tool call validation (blocks dangerous patterns)
Caveman Protocol	Token-efficient communication
Ponytail	Lazy senior dev mode — YAGNI, stdlib-first, minimal code
Ask User	Interactive MC dialogs + CSV logging
Format on Save	Auto Prettier + ESLint after write/edit
PiIgnore	Path blocking via `.piignore` patterns
TSC Checkpoint	`/check` command: `tsc --noEmit`
Worktree Sandbox	Worktree path enforcement
RTK	Token-saving bash rewrite — 60-90% less output per command
LSP Auditor	LSP diagnostics pre-audit for pipeline

Quick start

Install in one line

curl -fsL https://raw.githubusercontent.com/SchneiderDaniel/cheasee-pi/main/scripts/install.sh | bash

Or manually from the latest release.

Using the CLI (auto)

cheasee-pi init           # interactive setup: auth, fork, clone, env
cheasee-pi                # start container + inject keys + launch pi (default)
cheasee-pi down           # stop and remove container
cheasee-pi clean          # kill orphaned pi sessions + prune Docker garbage
cheasee-pi build          # rebuild container image (Dockerfile/entrypoint changes)
cheasee-pi auth add       # add API key for a provider
cheasee-pi auth list      # list configured providers/keys
cheasee-pi auth remove    # remove a provider key

See Installation guide for prerequisites and step-by-step setup.

Documentation

Full documentation is at schneiderdaniel.github.io/cheasee-pi.

Section	What’s there
Installation	Prerequisites, step-by-step setup, verification
Daily Usage	Docker workflow, parallel sessions, troubleshooting
Architecture	System design, extensions vs MCP, git worktrees, pipeline
Extensions	All 18 extensions, agent definitions, published packages
Skills	20 skill definitions (10 auto-loaded, 10 manual)
Methodology	Kanban pipeline, security, token efficiency, daily use
Prompts	Internal-only prompts (all Cheasee-Pi prompts converted to skills)
SBOM	Software Bill of Materials
Acknowledgements	Credits and licenses

Daily workflow

Typical session

Start with pi
Select or create a GitHub issue
Run /supervisor <issue-number> to start the Kanban pipeline
Monitor progress via TUI status bar
Review results when pipeline completes

Update pi

Pi auto-updates to the latest version on every container start (entrypoint checks npm registry). No action needed.

For Dockerfile / entrypoint changes (new tools, config), rebuild:

cheasee-pi start --build

CodeFlow (code-structure visualization)

The stack ships a local CodeFlow service (browser-based dependency/architecture visualizer, tree-sitter AST, 18 languages). It starts with docker compose up -d and serves on port 8470. See Daily usage > CodeFlow for configuration (docker/codeflow/config.json).

Contributing

Fork the repository
Create a feature worktree: git worktree add -b my-feature ../my-feature main
cd ../my-feature and make your changes
Run tests: npm test
Push and submit a PR
Clean up: git worktree remove --force ../my-feature

Philosophy

Everyone should build their own Pi. This repo is my personal Pi agent harness. Fork it as a starting point, but the real power comes from shaping it into your own — your preferred tools, your workflows, your guardrails.

Customize ruthlessly. Make it yours.