Skill Details

Support Skills Help Center Partners
Free Update

TotalRecall™

Your AI forgets everything between conversations. TotalRecall fixes that. It gives your ProductiveBot persistent memory that works across sessions, plus full transcript search, document and PDF search, a 7-step Deep Recall protocol for surfacing buried context, and automatic session summarization.

Install time
Under 1 minute
Privacy
100% local
Extra cost
None

The Problem

Without TotalRecall, your ProductiveBot starts fresh every conversation. It does not remember your name, your preferences, your past decisions, or what you talked about yesterday. Every session is a blank slate.

This is not a bug. It is how most AI assistants work by default. The AI model processes your message, responds, and moves on. There is no built-in system to carry information forward.

TotalRecall changes that. It adds a persistent memory layer that runs entirely on your Mac Mini. Your bot remembers what matters and brings it back when it is relevant.

How It Works

TotalRecall creates a set of memory files on your Mac Mini and watches them in real time. When your bot learns something important, it writes it down. When you ask a question, TotalRecall searches those files and surfaces the most relevant context before the bot responds.

TotalRecall also searches every past conversation transcript, shared documents, PDFs, and channel history — so your bot can recall what you discussed weeks or months ago, even if it was never explicitly saved. The 7-step Deep Recall protocol digs through memory files, session transcripts, shared documents, PDFs, Google Docs, and channel history to surface buried information. Session summarization automatically captures key decisions and details after every work session.

Hybrid Search

Finds memories by meaning and keywords. If you wrote "prefers Slack over email," asking "how should I contact them?" will find it.

Full Transcript Search

Search every past conversation transcript on your Mac Mini. Your bot can recall what you discussed weeks or months ago, even conversations that were never saved to memory files.

Deep Recall Protocol (7-step)

When a simple search is not enough, Deep Recall searches memory files, session transcripts, shared documents, PDFs, Google Docs, and channel history — leaving no stone unturned.

Session Summarization

Long conversations are automatically distilled into key takeaways. Your bot captures decisions, action items, and important details without you asking.

Completely Private

All memory files stay on your Mac Mini. Nothing is sent to the cloud. No one else can access your memories.

Real-Time Sync

Edit a memory file and the changes are indexed immediately. No manual re-indexing or restarts needed.

See It In Action

Here is what a conversation looks like with TotalRecall installed:

Week 1
"Remember that our fiscal year starts in April, not January."
"Got it. I've noted that your fiscal year starts in April."
3 Weeks Later, New Conversation
"Can you put together a Q1 revenue summary?"
"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.

Memory File Structure

TotalRecall uses simple markdown files that you and your bot both read and write:

workspace/
  ├── MEMORY.md       # Long-term: key decisions, preferences
  └── memory/
      ├── 2026-03-15.md  # Daily notes
      ├── 2026-03-16.md
      └── 2026-03-17.md

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

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

What It Does Not Do

Transparency matters. Here is what TotalRecall is not:

It does not record your conversations verbatim. It stores what you and your bot explicitly write to the memory files. If you say "remember this," your bot writes it down. Casual conversation that is not flagged for memory does not get stored.

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's hard drive.

It is not AI training. Your memories are never used to train any AI model. They are only used to give your bot context in your conversations.


Common Questions

How do I install TotalRecall?
Visit the Skill Store and click Install on the TotalRecall card. You can install it through Terminal or by telling your bot.
Does it slow down my bot?
No. The memory search runs locally on your Mac Mini and typically takes less than a second. It uses a lightweight model (EmbeddingGemma) that is optimized for the Mac Mini's hardware.
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 you do not want remembered. Changes are picked up 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. The search index adds a small amount on top of that.
What if I want my bot to forget something?
Open the memory file and delete the line. Or tell your bot "forget that my favorite color is blue" and it will remove it from MEMORY.md. Changes take effect immediately.
Is TotalRecall included with every ProductiveBot?
TotalRecall ships pre-installed on newer units. If your unit does not have it, you can install it for free from the Skill Store. It is a free update for all ProductiveBot owners.
Does it work with ChatGPT OAuth?
Yes. TotalRecall works with any AI provider your bot uses, including Anthropic (Claude), OpenAI (ChatGPT), or any other supported provider. The memory system is independent of which AI model you use.

Update Log

v1.8.0 March 27, 2026

Full session transcript search (searches all past conversations on disk), document and PDF search (shared files, workspace docs), Google Docs integration, recency-weighted results, 7-step Deep Recall protocol, mandatory session summarization. Includes pdftotext for PDF content extraction.

v1.6.0 March 24, 2026

Session & channel history search, Deep Recall protocol, session summarization, improved installer with native module rebuild.

v1.0.0 March 11, 2026

Initial release — local memory file search, BM25 keyword matching.

Need help? Talk to Scout

Scout can help you install TotalRecall, troubleshoot memory issues, or answer any questions.

Chat with Scout Help Center

You can also email us at support@productivebot.ai