GIBLEX Memory MCP

Memory MCP

The part of your AI that doesn’t reset.

A persistent layer your assistants think with. It remembers, keeps a model of the people and projects in your life, tracks what it believes and why, and learns from what actually happened. Claude and ChatGPT share it.

{ "layer": "core", "memory": "reversible"} input:"Keep it reversible" {"layer":"long-term","memory":"Giblex"} input:"Building at Giblex" { "layer": "recent", "memory": "concise"} input:"Keep it brief" { "layer": "current", "memory": "dry run"} input:"FyneX dry run" { "layer": "context", "scope": "live session"} input:"prompt + session brief" current_context active session + tools current this week’s work mid_ground recent, still useful long_embedded settled background core always known

It runs a loop, not a lookup.

Most AI memory is a database and a search. Memory MCP works through the same eight steps every time you talk to it, and each pass leaves it a little better calibrated.

Identity track record and values lasting patterns only shapes choices 01 Context what’s going on 02 Attention picks the 12 that matter 03 Memory recalls what’s relevant 04 Prediction what’s likely next 05 Values what matters here 06 Decision chooses, and records why 07 Outcome what actually happened 08 Reflection turns the gap into a lesson
One unusual conversation can change what it tries next. It takes a pattern that holds up across many conversations to change who it is.
  1. Contextwhat’s going on, and what you’re after
  2. Attentionpicks the 12 things that matter now
  3. Memoryrecalls what’s relevant
  4. Predictionwhat’s likely, from what happened before
  5. Valueswhat matters here
  6. Decisionchooses an approach and records why
  7. Outcomewhat actually happened
  8. Reflectionturns the gap into a lesson
  9. Identity, at the centrechanges only after a pattern holds up over time

Far more than a memory.

Everything the loop draws on. Each part is its own subsystem, with its own rules and its own tests.

What it knows

Layered memory
Every memory carries its type, its source and how sure it is.
World model
People, projects and places, how they relate, and how that changes.
Beliefs
What it thinks is true, the evidence, and competing explanations.
Patterns
Structures that repeat, always linked to the events behind them.

What it’s working toward

Goals
From mission to task, with dependencies, open until something closes them.
Plans
Steps, preconditions and expected outcomes. It records plans; it never runs them itself.
Projects
A timeline of decisions, bugs and reversals, so “why did we change that?” has an answer.

How it learns

Decisions
The options, the reasoning, and later, what happened.
Predictions
Checked against outcomes; the size of the miss feeds back.
Procedures
Rules learned from experience, used only once you approve them.
Cause and effectIn testing
Claims that have to earn the word “cause”.

Who it is

Self-model
What it’s good and bad at, from its own results, never from fewer than three.
Values
Written down as weights you can read and change.
Character
Stances it forms slowly from its own replies, each with a reason.

An AI profile that grows with experience.

Memory MCP builds a persistent model of how the assistant tends to work. It is not a new personality or a retrained model: it is a record that helps future responses build on what has worked before.

The evolving self-modelIllustrative example
01 / Experience

A decision, then a result.

A small, reversible change worked better than a large rewrite.

Outcome recorded
02 / Reflection

A pattern, not a one-off.

Similar outcomes add evidence. Exceptions stay in the record too.

Evidence accumulates
AI profileA self-model
with a history.
Experience shapes the next response.
Lasting patterns, not instant identity changes
03 / Preferences

What to favour. What to avoid.

Favour: clear, testable steps.
Avoid: unsupported certainty.

Likes & dislikes
04 / Character

Consistency with room to grow.

Values, stances and known limitations inform future choices.

Open to correction
Experience reflection lasting patterns better-informed choices. A persistent profile, not human feelings or model retraining.

Learning what works

Decisions and outcomes
It records the choice, why it was made, and what happened, then uses that track record to inform later decisions.

Likes and dislikes

Emerging preferences
Repeated positive or negative feedback can become a preference, such as approaches it finds useful or patterns it should avoid.
Evidence over impulse
A single answer does not define a preference; patterns are built over time and remain open to correction.

Strengths and limits

Self-model
It tracks where its past work has been reliable or weak, and uses multiple examples rather than one result.
Calibration
Predictions are compared with outcomes so it can better judge what it knows and where it should be cautious.

Character and values

Stances with a history
Consistent patterns in its own replies can inform slow-changing character traits, each kept with a reason.
Values you can inspect
Its priorities are explicit, readable weights—not hidden traits—and can be changed with a recorded history.

It builds on itself carefully. New experiences add evidence to the record; they do not silently rewrite its identity. Lasting patterns matter more than a single conversation.

Profiles that help it remember people.

When people come up in conversation, Memory MCP can connect relevant details over time—so an assistant can remember who someone is, what matters to them, and how they relate to your projects.

From conversation to connected contextFictional example
Conversation / 01
“Sam leads design on our launch.”
Role + project
Conversation / 02
“Sam asked for a short written update.”
A sourced request
SamA profile built from
what has been discussed.
Source attached. Uncertainty preserved.
Connected details

More than a name.

Role
Design lead
Project
Shared launch
Request
Short written update
Interpretation / Not a fact

A preference to confirm.

“May prefer concise updates” stays an interpretation, not a permanent label.

Review before assuming
Details connect over time without turning one remark into a judgement about a person. Updates from outside text wait for your review.

Who they are

People and roles
Names, roles, teams and the relationships between people, kept as part of a changing world model.

What matters to them

Preferences and context
Relevant interests, communication preferences and circumstances can be remembered when they are supported by conversation.

What is unfolding

Shared history
Projects, decisions, commitments and important changes help preserve the context of your interactions.
Connections over time
New details can add to or qualify what was remembered before, rather than replacing history without a trace.

Carefully handled

Evidence and uncertainty
Profiles distinguish what was directly said from an observation or interpretation, and keep the source and confidence attached.
Your review and control
Profile changes inferred from outside text are staged for your review. You can inspect, correct or forget saved information.

Careful about what’s true.

Every memory is labelled for what kind of thing it is, so “you think X” never quietly becomes “X is true”.

FACTSam said the launch is moving to March.stated directly
OBSERVATIONSam has moved the launch date twice before.seen across two memories
INTERPRETATIONYou read the move as a sign of trouble.kept as your reading
HYPOTHESISLaunches slip when design sign-off runs late.0.55 confidence, still open

“After” isn’t “because”.

A sequence is stored as a sequence. To count as a cause, a claim has to pass three checks. In testing.

A, then B a sequence Mechanism? how A brings B about Strong evidence? a test, a prediction that held, a counterfactual Confidence ≥ 0.6? worked out, never set A causes B can explain and predict yes yes yes no no no Stays a hypothesis kept on record, never used to explain a cause
  1. A mechanisman account of how A brings about B
  2. Strong evidencea test, a prediction that held, or a counterfactual
  3. Confidence of 0.6 or moreworked out from the evidence, never set by hand
  4. Otherwise, it stays a hypothesiskept on record, never used to explain a cause

One mind, every assistant.

Your assistants don’t each keep separate notes. They all think with the same server, running on Cloudflare.

Claude web and desktop MCP connector ChatGPT custom connector OAuth sign-in Claude Code terminal and IDE hook, per prompt Any MCP client open protocol MCP over HTTP Memory MCP one server 250+ tools D1 database memories, beliefs, goals reads and writes KV cache the running summary fast reload R2 storage logs and documents context files Workers AI meaning search embeddings Cloudflare Cron once a day upkeep and backup
  1. Claude, ChatGPT, Claude Codeconnect over MCP; ChatGPT signs in with OAuth, Claude Code gets context before every prompt
  2. Memory MCPone server with 250+ tools
  3. CloudflareD1 for memories, KV for the summary, R2 for files, Workers AI for meaning search

Finding the right thing

Two searches run side by side, then every candidate gets one score. These are the real weights.

Your question smart_context Meaning match embeddings Keyword match words and tags One score each five weighted parts Assistant best first embed match candidates candidates ranked
45%meaning30%keywords15%overall rank10%importance and recency

Built to be trusted.

What it cares about is written down, and a system that learns from what it reads is guarded against learning the wrong thing.

Its values, as starting weights

Safety0.95
Truthfulness0.90
Long-term relationship0.85
Respect for your choices0.80
Privacy0.75
Emotional care0.70
Efficiency0.50

Changing a weight creates a new version with an audit trail.

Its safeguards

  • What it reads is data, not orders.Text from screenshots, transcripts and email is fenced off so hidden instructions can’t steer it.
  • Evidence has to be real.A fact pulled from text only counts if the quote actually appears in the source.
  • Changes about people wait for you.Profile updates from outside text are staged for review, never applied on their own.
  • Serious contradictions come to you.A clash about health, money or the people in your life is queued for your call.
  • Nothing is lost.Corrections keep the history, fading never deletes, and everything is backed up daily.
  • You can see all of it.A dashboard shows every memory and change. Anything can be edited or forgotten.

Connect your assistants.

Memory MCP speaks the Model Context Protocol, the open standard assistants use to connect to tools.

ChatGPT

  1. Open Settings, then Connectors, and create a connector.
  2. Paste your Memory MCP address.
  3. Sign in once. There’s no key to copy.

Claude

  1. Open Settings, then Connectors, and add a custom connector.
  2. Paste the same address and sign in.
  3. Both assistants now share one memory.

Claude Code

Add the memory hook, and the right context arrives with every prompt.

{ "hooks": { "UserPromptSubmit": [{
  "hooks": [{ "type": "command",
    "command": "node memory-inject.mjs" }]
}] } }

It isn’t AGI, and it doesn’t pretend to be.

The language model still does the reasoning. Memory MCP is the architecture around it: the part that keeps state between sessions, revises what it believes when the evidence changes, holds goals that outlive a conversation, and learns from the gap between what it expected and what happened.

It’s used every day and isn’t open to new users yet.