davegoldblatt

Persistent memory plugin for Claude Code. Tiered memory system with write gates, correction propagation, and slash commands.

185
10
100% credibility
Found Feb 07, 2026 at 25 stars 7x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Shell
AI Summary

Total Recall is a curated memory system for Claude Code that filters important coding session insights into organized daily logs and permanent notes to enhance AI recall without context bloat.

How It Works

1
🔍 Discover Total Recall

You learn about a smart memory helper for your AI coding partner Claude that only saves the truly important stuff from your chats.

2
📥 Add it to your project

You easily install the memory tool into your coding folder using a quick marketplace command or a simple setup script.

3
📁 Set up your memory notebooks

It creates organized notebooks in your project for daily notes, key facts, and long-term memories, all kept private.

4
💭 Save meaningful moments

As you code and chat, you use simple commands to jot down decisions, corrections, or commitments that matter for later.

5
Review and promote highlights

You check your daily notes and move the best ones to permanent memory spots so they stick around.

6
🔄 Start a new session

Next time you open your project, Claude automatically pulls in the right memories to pick up right where you left off.

🎉 Smarter coding forever

Your AI buddy now remembers key insights without getting overwhelmed, making every session more productive and reliable.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 25 to 185 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is total-recall?

Total Recall is a Shell-based plugin for Claude Code that adds persistent memory across sessions, solving the amnesia problem where AI forgets preferences, decisions, and project details like client names or auth boundaries. It uses a tiered system—quick-access counter, categorized registers, daily logs, and archives—with slash commands like /recall-write, /recall-search, and /recall-promote to log, search, and curate notes. Hooks auto-inject session summaries and compaction markers, keeping Claude primed without bloating context.

Why is it gaining traction?

It stands out with a "write gate" that filters noise, only promoting behavior-changing facts or explicit notes to permanent github persistent storage, unlike auto-ingest tools that hoard everything and spike token costs. Developers notice lean, searchable persistent memory for LLMs—think ram vs persistent memory but for code chats—plus instant correction propagation across tiers. The user-controlled promotion and privacy (all local markdown, no telemetry) hook those tired of repeating instructions.

Who should use this?

Claude Code users on long projects, like backend devs tracking iptables-persistent github configs or frontend teams remembering UI decisions. Solo hackers building persistent memory llm apps, or teams mimicking Total Recall 1990's unbreakable recall for commitments and open loops. Avoid if you're not in Claude Code ecosystems.

Verdict

Grab it for Claude Code if persistent memory programming matters—docs are solid, install is one script—but with 27 stars and 1.0% credibility score, treat as early alpha: test thoroughly before production reliance. Solid concept, immature execution.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.