@grainulation/grainulation
v1.0.1
Published
Structured research for decisions that satisfice
Maintainers
Readme
Most decisions fail not because the team lacked data, but because they lacked a process for turning data into evidence and evidence into conviction. Grainulation is that process.
You start with a question. You grow evidence: claims with types, confidence levels, and evidence tiers. You challenge what you find. You look for blind spots. And only when the evidence compiles -- when conflicts are resolved and gaps are acknowledged -- do you write the brief.
Install
npm install -g @grainulation/grainulationOr start a research sprint directly:
npx @grainulation/wheat initQuick start
grainulation # Ecosystem overview
grainulation doctor # Health check: which tools, which versions
grainulation setup # Install the right tools for your role
grainulation wheat init # Delegate to any tool
grainulation farmer startThe ecosystem
Eight tools. Each does one thing. Use what you need.
| Tool | What it does | Install |
| ------------------------------------------------------------ | ----------------------------------------------------------------------------- | ------------------------------------- |
| wheat | Research engine. Grow structured evidence. | npx @grainulation/wheat init |
| farmer | Permission dashboard. Approve AI actions in real time (admin + viewer roles). | npm i -g @grainulation/farmer |
| barn | Shared tools. Templates, validators, sprint detection. | npm i -g @grainulation/barn |
| mill | Format conversion. Export to PDF, CSV, slides, 24 formats. | npm i -g @grainulation/mill |
| silo | Knowledge storage. Reusable claim libraries and packs. | npm i -g @grainulation/silo |
| harvest | Analytics. Cross-sprint patterns and prediction scoring. | npm i -g @grainulation/harvest |
| orchard | Orchestration. Multi-sprint coordination and dependencies. | npm i -g @grainulation/orchard |
| grainulation | Unified CLI. Single entry point to the ecosystem. | npm i -g @grainulation/grainulation |
You don't need all eight. Start with wheat. That's it. One command. Everything else is optional -- add tools when you feel the friction.
The journey
Question --> Seed Claims --> Grow Evidence --> Compile Brief
/init /research /challenge /brief
/blind-spot
/witnessEvery step is tracked. Every claim has provenance. Every decision is reproducible.
Philosophy
Satisficing over maximizing. You will never have perfect information. The goal is enough evidence to make a defensible decision, not a perfect one.
Claims over opinions. Every finding is a typed claim with an evidence tier. "I think" becomes "r003: factual, tested -- measured 340ms p95 latency under load."
Adversarial pressure over consensus. The /challenge command exists because comfortable agreement is the enemy of good decisions.
Process over heroics. A reproducible sprint that anyone can pick up beats a brilliant analysis that lives in one person's head.
Zero dependencies
Every grainulation tool runs on Node built-ins only. No npm install waterfall. No left-pad. No supply chain anxiety.
The name
You build the crop (wheat), the steward (farmer), the barn, the mill, the silo, the harvest, the orchard -- and only then do you name the machine that connects them all.
Grainulation: the machine that processes the grain.
License
MIT
