TotalRecall: Persistent Memory for Your ProductiveBot

Your AI forgets everything between conversations. TotalRecall fixes that with persistent memory that works across sessions, days, and months.

PB
ProductiveBot Team· · 5 min read
Enhanced OpenClaw technology, free for ProductiveBot customers. TotalRecall is built on top of OpenClaw's memory framework and is available exclusively through the ProductiveBot Skill Store. Installation and setup details are available to ProductiveBot owners after logging in.

The Problem With Standard OpenClaw

ProductiveBot is built on OpenClaw, an open-source AI agent framework. Out of the box, OpenClaw's memory system requires significant technical configuration to work at all. Most installations ship with it silently broken. The workspace is misconfigured, hybrid search is off, and the bot forgets everything between sessions.

There is no error message. It just does not remember.

TotalRecall is ProductiveBot's fix for this. It properly configures OpenClaw's memory system, enables features that are off by default, and ensures everything runs correctly from the start.

What TotalRecall Adds to OpenClaw

Standard OpenClaw memory has several features that are disabled by default. TotalRecall turns them on and configures them correctly:

Hybrid Search

Standard OpenClaw uses basic keyword matching. TotalRecall enables hybrid search, combining meaning-based search with exact keyword matching. If you wrote "prefers Slack over email," asking "how should I contact them?" will find it.

Persistent Sessions

Standard OpenClaw starts fresh every conversation. TotalRecall ensures information persists across sessions. Tell your bot something on Monday and it will know it on Friday.

100% Local and Private

All memory files stay on your Mac Mini. Nothing is sent to the cloud. No one else can access your memories. This is how OpenClaw is designed to work, and TotalRecall keeps it that way.

Real-Time File Sync

Standard OpenClaw may not detect file changes immediately. TotalRecall configures the file watcher with proper debounce settings so edits are indexed right away.

See It In Action

Here is what a conversation looks like with TotalRecall installed:

Week 1

You: "Remember that our fiscal year starts in April, not January."

Bot: "Got it. I have noted that your fiscal year starts in April."

3 Weeks Later, New Conversation

You: "Can you put together a Q1 revenue summary?"

Bot: "Sure. Since your fiscal year starts in April, Q1 would be April through June. Let me pull that together..."

Without TotalRecall, the bot in the second conversation would assume January. With TotalRecall, it automatically recalls your fiscal year preference and gets it right.

How OpenClaw Memory Works

OpenClaw stores memories in simple markdown files that both you and your bot can read and write:

MEMORY.md is for curated, long-term memories: preferences, key decisions, lessons learned. Think of it as your bot's cheat sheet.

Daily files (like 2026-03-17.md) are raw notes from each day. Your bot writes these automatically as it works. Over time, the important stuff gets distilled into MEMORY.md.

TotalRecall ensures OpenClaw indexes these files correctly and searches them before every response.

What It Does Not Do

It does not record your conversations verbatim. It stores what you and your bot explicitly write to the memory files.

It does not send data anywhere. There is no cloud sync, no analytics, no telemetry. The memory files are plain text files on your Mac Mini.

It is not AI training. Your memories are never used to train any AI model.


Common Questions

How do I install TotalRecall?
Visit the Skill Store and click Install on the TotalRecall card.
Does it slow down my OpenClaw bot?
No. The memory search runs locally on your Mac Mini using a lightweight model called EmbeddingGemma. It typically takes less than a second.
Can I read and edit the memory files myself?
Yes. They are plain markdown files. You can open them in any text editor, add notes, correct mistakes, or delete things. OpenClaw picks up changes automatically.
How much storage does it use?
Very little. Memory files are plain text. Even after months of daily use, the total size is typically under a few megabytes.
What if I want my bot to forget something?
Open the memory file and delete the line. Or tell your bot "forget that" and it will remove it. Changes take effect immediately.
Does it work with ChatGPT OAuth?
Yes. TotalRecall works with any AI provider your OpenClaw bot uses, including Anthropic (Claude), OpenAI (ChatGPT via OAuth), or any other supported provider.
Is this different from standard OpenClaw memory?
Yes. Standard OpenClaw has memory capabilities but they require manual configuration and several features are off by default. TotalRecall configures everything correctly, enables hybrid search, and ensures the file watcher works properly. It is what OpenClaw memory should be out of the box.

Related

Get TotalRecall

TotalRecall is available for free on the ProductiveBot Skill Store. Log in with your ProductiveBot account to install it in under a minute.

Visit the Skill Store

Need help? Talk to Scout

Scout can help you install TotalRecall, troubleshoot memory issues, or answer any questions about your OpenClaw setup.

Chat with Scout

Reading next

Leave a comment

This site is protected by hCaptcha and the hCaptcha Privacy Policy and Terms of Service apply.