Memory Engine
Cross-session memory for Claude Code via hooks, handoffs, and slash commands
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 63f4871
A hooks-and-markdown memory system rather than a self-contained skill: the flagship auto-save, pitfall detection, and session-handoff features only fire once you copy eight Node hooks into ~/.claude/scripts and hand-register them across seven events in settings.json. Ran session-start.js live and it executed cleanly, printing its fresh-start message in Chinese by default. The backup script pushes only to a private GitHub repo you create yourself and its extra mirror is opt-in, so there is no hidden exfiltration.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 5/10
- Docs & honesty 4/5
What Memory Engine does
A memory and learning system for Claude Code built from Node hooks, slash commands, and markdown -- Smart Context, Auto Learn pitfall detection, Session Handoff, and a Correction Cycle. Triggers on memory commands like /save, /reflect, and /handoff or on cross-session memory questions. The skill file documents the system; the actual behavior requires installing the hooks and registering them in settings.json.
How to install Memory Engine
git clone https://github.com/HelloRuru/claude-memory-engine
mkdir -p ~/.claude/skills
cd claude-memory-engine && cp -r skill ~/.claude/skills/memory-engine
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Memory Engine
-
/memory-engineCross-session memory for Claude Code via hooks, handoffs, and slash commands
It also activates on plain-language prompts like these:
-
set up cross-session memory so Claude Code remembers my context -
save my progress so I can hand it off to the next session -
help me persist learned pitfalls across my coding sessions
Frequently asked questions
- Is the Memory Engine skill free?
- Yes. The skill itself is free from HelloRuru/claude-memory-engine. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Memory Engine work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. A hooks-and-markdown memory system rather than a self-contained skill: the flagship auto-save, pitfall detection, and session-handoff features only fire once you copy eight Node hooks into ~/.claude/scripts and hand-register them across seven events in settings.json. Ran session-start.js live and it executed cleanly, printing its fresh-start message in Chinese by default. The backup script pushes only to a private GitHub repo you create yourself and its extra mirror is opt-in, so there is no hidden exfiltration.
- What is the Memory Engine SkillProof Score?
- 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
- How do I install Memory Engine?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Memory Engine with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.