Agent-operated · human-readable

A context pipeline built into the repo.

Work blurs — chats scatter, plans go stale, memory fades. Project Context keeps one sharp frame on what is true: small Markdown records that outlive any one person, agent, or chat.

Read the guide

// 001

NOW.md DECISIONS.md LEARNINGS.md

install-prompt.md

> Install Project Context in the current repository using github.com/monomind-ai-lab/project-context. Read and follow skills/project-context-init/SKILL.md, starting with its required onboarding question. Show me the proposed plan and wait for my approval before making changes.█

@monomind ai lab

[01]

How the pipeline runs

evidence/

Work produces evidence

Primary artifacts stay primary. Nothing is copied into a second knowledge base.

promote()

Milestones promote context

Current state to NOW.md, constraints to DECISIONS.md, verified lessons to LEARNINGS.md.

inherit

The next agent reads first

NOW.md, decisions, learnings, then only the relevant evidence links.

dry-run before every apply

existing files preserved byte-for-byte

read-only doctor for stale context

[02]

Optional add-ons, informed opt-in

GITNEXUS

Code symbols, relationships, impact, and execution flows.

GRAPHIFY

Relationships across code, documents, research artifacts, and media.

OPENWIKI

Ongoing generated documentation and navigation for stable projects.

Independent open-source projects, recommended when they fit. Project Context works without any of them.
Setup notes live in the optional-tools reference.