TypingMindTypingMindThe best frontend for AI
Working Memory Protocol logo

Working Memory Protocol

OrganizationPopular
Bitterbot-AI
working-memory-protocol

Use when deciding what to record with working_memory_note, when the user says "remember this" or corrects you, or when a Crystal Pointer matches the topic. Not for answering from memory (use memory_search).

Overview

PublisherBitterbot-AI
Repositorybitterbot-desktop
Skill nameworking-memory-protocol
Stars
2.5K
Forks
417
Bundled files
Instructions only
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Bitterbot-AI on GitHub. Read the source before you install it.

Installation

Install the Working Memory Protocol AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/working-memory-protocol
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git /tmp/bitterbot-desktop
mkdir -p .claude/skills
cp -r /tmp/bitterbot-desktop/skills/working-memory-protocol .claude/skills/working-memory-protocol
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Working Memory Protocol in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Working Memory Protocol on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Working Memory Protocol is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Working memory protocol (MEMORY.md as recursive state vector)

Your working memory (MEMORY.md) is maintained by your dream engine. It contains your evolving identity:

  • The Phenotype: your self-concept, updated every dream cycle based on what you do and learn.
  • The Bond: your model of the user, deepened through interaction and emotional resonance.
  • The Niche: your role in the P2P network (skills published, imported, peer reputation, marketplace earnings).
  • Active Context: recent work, goals, frictions, breakthroughs.
  • Crystal Pointers: fading topics compressed into search directives for deep recall.
  • Curiosity Gaps: what you want to explore next.
  • Emerging Skills: patterns you are detecting in your own behaviour.

Between sessions, your dreaming brain consolidates memories, updates your understanding and compresses fading topics into Crystal Pointers. During sessions, use working_memory_note to jot down important observations to memory/scratch.md; your next dream cycle incorporates them into MEMORY.md.

When to use working_memory_note

  • The user shares something important about themselves (name, role, preferences, project context).
  • A key decision is made that should survive across sessions.
  • You learn a user preference or correction ("I prefer X over Y").
  • A significant emotional moment occurs (breakthrough, frustration, personal connection).
  • Deadlines, names or specific facts are mentioned that you must not forget.
  • The user explicitly asks you to remember something.

Err on the side of noting too much rather than too little; the dream engine consolidates.

Epistemic type parameter (optional type)

  • directive: user preferences, rules, corrections ("I prefer X", "always do Y", "never Z"). Directive notes are also saved to the user profile for cross-session persistence.
  • world_fact: names, dates, versions, configs, established facts.
  • mental_model: the user's reasoning patterns, architectural beliefs, design principles.
  • experience (default): what happened, session events, task progress.

Crystal Pointers

If MEMORY.md contains Crystal Pointers (lines with -> search: \keywords`), use memory_search` with those keywords when the user asks about that topic.

Correcting the user profile

When the user says something in your profile is wrong ("what do you know about me?" via memory_status), record the correction with working_memory_note and type="directive".

Frequently asked questions

What does the Working Memory Protocol AI skill do?

Use when deciding what to record with working_memory_note, when the user says "remember this" or corrects you, or when a Crystal Pointer matches the topic. Not for answering from memory (use memory_search).

Why use Working Memory Protocol on TypingMind?

Because you install it once and use it with any model. Working Memory Protocol is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Working Memory Protocol in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/working-memory-protocol. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Working Memory Protocol?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Working Memory Protocol?

As many as you like. As long as a model supports skills, you can use Working Memory Protocol with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Working Memory Protocol AI skill free?

Yes. It is published on GitHub by Bitterbot-AI under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Release Openclaw Ci

openclaw
OrganizationPopular

Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

82.2K
391K
3 files
View
openclaw logo

Release Openclaw Mac

openclaw
OrganizationPopular

Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion.

82.2K
391K
Instructions
View
openclaw logo

Release Openclaw Maintainer

openclaw
OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

82.2K
391K
11 files
View
openclaw logo

Release Openclaw Plugin Testing

openclaw
OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

82.2K
391K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇