Starter template for Claude Code memory system with modular rules, persistent memory, and session handover.
claude-memory-template is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo clone lukasz-fedor/claude-memory-templateOpen or clone the template repository.
Move the relevant AGENTS.md content into your project root.
Update project-specific commands, environment rules, and sensitive areas.
This template gives Claude Code a memory system so it remembers your project across sessions. It organizes rules into modular files that load only when needed, saves decisions and bug fixes, and automatically hands off context when a session runs out of space. You just copy the template into your project and start using Claude more efficiently.
Claude Code Memory Template is a ready-to-use system that makes Claude Code remember your project across sessions — rules, preferences, decisions, and context. It solves the problem that every new Claude Code session starts from zero, forcing you to repeat yourself and lose time. The template provides: - **Modular rules**: Claude loads only relevant instructions based on glob patterns, keeping CLAUDE.md short. - **Persistent memory**: Decisions, bug fixes, and gotchas survive across sessions in a memory/ directory. - **Session handover**: A pre-compact hook saves context before it's lost, so the next session picks up where you left off. - **Skills**: Reusable modes for specific tasks like code review, copywriting, or deployment. - **Anti-hallucination rules**: Built-in instructions that stop Claude from making up facts, stats, or URLs. The template is organized with a clear directory structure: .claude/rules/ for detailed rules, .claude/skills/ for specialized modes, .claude/hooks/ for automation, memory/ for persistent notes, and local/ for working notes. Setup involves copying files, renaming templates, and editing CLAUDE.md and rule files to match your project.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 144 days ago.
29 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
Set up persistent memory for a long-running software project to avoid repeating context to Claude.
Organize Claude Code rules by file type so it only loads relevant instructions when editing specific files.
Use session handover to continue work seamlessly after Claude runs out of context mid-conversation.
Create reusable skill modes for tasks like code review, copywriting, or deployment automation.
Prevent hallucination by enforcing rules that require Claude to cite sources and avoid made-up facts.
Memory files may contain sensitive project information; ensure .gitignore excludes local/ and memory/ if needed.
The handover hook executes Python code; review it before use to avoid unintended behavior.
Over-reliance on memory may cause Claude to use outdated context if not regularly cleaned.
29
Stars
2
Forks
0
Issues
MIT
License
A drop-in AGENTS.md file that makes coding agents behave like senior engineers, eliminating sycophancy and forcing verification.
Convert and sync AI coding-agent rule files between formats with zero dependencies.
Generate AGENTS.md from your codebase in one command. Free, instant, no API key.
Starter template for Claude Code memory system with modular rules, persistent memory, and session handover.
Developers using Claude Code for daily development who want to reduce repetitive instructions., Tech leads setting up a standardized AI-assisted workflow for their team., Prompt engineers looking for a structured way to manage Claude's behavior across sessions.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Memory files may contain sensitive project information; ensure .gitignore excludes local/ and memory/ if needed. The handover hook executes Python code; review it before use to avoid unintended behavior.
Similar or complementary options to evaluate include agents-md, agentsync, agentseed.
Jun 7, 2026
3 security/trust notes recorded.
Setup difficulty is 2/5.