CommitLore – Git memory for decisions coding agents keep forgetting
Source
github.com
Author
weplay0628
Date
Context
CommitLore preserves reasons for engineering decisions alongside a repository's Git history, then supplies relevant, still-active decisions before an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → edits a file. This gives a new session access to constraints and rejected alternatives that the code alone may not explain. Superseded or expired records are excluded from the active context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →. The README describes this delivery mechanism.
Creating those records remains a separate step. A supported integration can deliver existing decisions automatically, but an agent must initiate capture of a new rationale; the commit agent hookA script the harness runs automatically at a fixed point in an agent's loop — before a tool call, after an edit, on session start.Full definition → validates a supplied record rather than inventing one. Its usefulness therefore depends on recording the reasons worth carrying into future sessions.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
agent hook — A script the harness runs automatically at a fixed point in an agent's loop — before a tool call, after an edit, on session start.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.