Skip to content

Lore

Your code knows what. Lore knows why.

Lore

Demo

The Problem

You are 50 commits in. Six months later, someone asks: "Why did we build it this way?"

git blame shows who changed what and when — but not why. The reasoning is gone: buried in a Slack thread, a PR comment, or the memory of a developer who left.

The Solution

Three quick questions. Ninety seconds. Done.

$ git commit -m "feat: add JWT auth middleware"
  [1/3] Type [feature]:
  [2/3] What [add JWT auth middleware]:
  [3/3] Why? Stateless auth scales better than sessions
  ✓ Captured: feature-add-jwt-auth-2026-03-16.md

Lore hooks into your Git workflow and asks 3 essential questions after every commit — Type, What, Why — plus 2 optional ones (Alternatives, Impact) that auto-skip when you answer the first three quickly, or stay in for higher-stakes commits. The answers become a Markdown file in your repo — searchable, versionable, portable. No wiki. No SaaS. No friction.

How it works

graph LR
    A[git commit] --> B[lore hook triggers]
    B --> C[3 questions: Type, What, Why]
    C --> D[Markdown document created]
    D --> E[Searchable with lore show]
  1. Commit your code as usual
  2. Answer 3 essential questions — Type, What, Why — plus 2 optional (Alternatives, Impact) that auto-skip when you go fast (~90 seconds median)
  3. Done — A Markdown document captures the decision forever
  4. Search anytime with lore show "auth" to find past decisions

Get Started

  • Installation

    Homebrew, Chocolatey, Go, curl, deb, rpm — ways to install on macOS, Linux, Windows

  • Quickstart

    From zero to your first captured "why" in 5 minutes

  • Commands

    Full reference for all 19 commands

  • Philosophy

    Why Lore exists and the principles behind it

Built for

  • Solo developers who revisit their own code months later and wonder "why did I do this?"
  • Teams that lose institutional knowledge when people leave or rotate projects
  • Open-source maintainers who want contributors to understand design choices
  • Anyone tired of decisions buried in Slack, PR comments, or someone's memory

What makes Lore different

Lore Swimm Confluence GitBook
When Commit-time After the fact After the fact After the fact
Where Local (.lore/) SaaS SaaS SaaS
Friction 90 seconds 30 minutes 30 minutes 15 minutes
AI Angela (opt-in) Generic Generic Generic
Lock-in Markdown Proprietary Proprietary Mixed
Price Free (AGPL) $28/seat $5.75/user $8/user

Angela — Your AI Documentation Companion

Angela is Lore's embedded reviewer — a colleague who has read every document your team ever wrote, knows the project's style, and proofreads your docs before you publish them.

She doesn't work alone. She leans on a system of expert personas — Affoué (the storyteller, who keeps the why clearer than the what), Ouattara (the API designer, for Postman contracts and technical specs), and others. Not a generic AI — a team that knows your project.

  • lore angela draft — Free, offline analysis: missing sections, style issues, related documents
  • lore angela polish — AI-assisted rewrite with interactive diff review
  • lore angela review — Corpus-wide coherence check: contradictions, isolated docs, coverage gaps

Angela is opt-in. Respectful of resources. No automatic decision without your consent. She works with Anthropic (Claude), OpenAI (GPT), or Ollama (local). draft mode requires no API key.

Angela also works as a standalone CI quality gate on any Markdown directory — no lore init required. Add 3 lines to your GitHub Actions, GitLab CI, or Jenkins pipeline: Angela in CI →

Learn about Angela's story →

Learn More