Elephant
Persistent memory + auto changelogs for Claude Code
Start new thread
Fatih Unver

Elephant - Persistent memory + auto changelogs for Claude Code

by
Trendoline
ā€¢
Claude Code forgets everything between sessions. You burn tokens re-explaining your stack every time. Elephant fixes that: šŸ§  Persistent memory ā€” auto-loaded at session start. šŸ‘„ Team memory ā€” ELEPHANT.md lives in your repo, committed, author-tagged. šŸŒ Cross-repo ā€” switch projects, keep the thread. šŸ“ Auto changelogs ā€” /elephant changelog reads git log, suggests semver bump. šŸ“– Auto READMEs ā€” badges and commands stay in sync. One-line install. MIT. Just a file, no cloud.

Add a comment

Replies

Best
Fatih Unver
Maker
šŸ“Œ
Hey PH šŸ‘‹ I built Elephant because I got tired of starting every Claude Code session with the same 200-token preamble: "we use Bun not Node, auth moved to packages/core, don't touch the stripe webhook it's mid-migration..." Elephant is three files doing boring work well: ā€¢ ELEPHANT.md ā€” repo-local, committed, team-shared memory. Every entry tagged with author. ā€¢ ~/.claude/elephant/memory.md ā€” personal cross-repo memory. ā€¢ CHANGELOG.md ā€” auto-generated from git log with semver-aware bumps. A SessionStart hook loads memory automatically. A Stop hook nudges Claude to save important decisions when topics shift. Caveman-compressed entries keep a week of history at ~150 tokens. Bonus: /elephant takeover reads your last 60 commits and seeds memory on a fresh clone ā€” new teammates get briefed before their first session. MIT. No cloud. Works today on Claude Code. Would love feedback! What's the most painful context you lose between AI coding sessions?