# Lore: Repurposing Git Commit Messages as a Structured Knowledge Protocol for AI Coding Agents

arXiv: https://arxiv.org/abs/2603.15566 · HTML: https://mlsanity.com/paper/2603.15566/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 3 of its 15 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 3 of 3)

- [The Future of AI-Driven Software Engineering](https://mlsanity.com/paper/2406.07737/) (2024)
- [Git Context Controller: Manage the Context of LLM-based Agents like Git](https://mlsanity.com/paper/2508.00031/) (2025)
- [Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development](https://mlsanity.com/paper/2510.16395/) (2025)

## Built on by (most cited first, 1 of 1)

- [AtomicCommitBench: Can Coding Agents Reconstruct Commit Histories from Squashed Patches?](https://mlsanity.com/paper/2607.03332/) (2026)

## Abstract (arXiv)

As AI coding agents become both primary producers and consumers of source code, the software industry faces an accelerating loss of institutional knowledge. Each commit captures a code diff but discards the reasoning behind it - the constraints, rejected alternatives, and forward-looking context that shaped the decision. I term this discarded reasoning the Decision Shadow. This paper proposes Lore, a lightweight protocol that restructures commit messages - using native git trailers - into self-contained decision records carrying constraints, rejected alternatives, agent directives, and verification metadata. Lore requires no infrastructure beyond git, is queryable via a standalone CLI tool, and is discoverable by any agent capable of running shell commands. The paper formalizes the protocol, compares it against five competing approaches, stress-tests it against its strongest objections, and outlines an empirical validation path.