Resource 008 / memory diagnostics

Memory is three monsters, not one feature.

A practical checklist for diagnosing whether an agent memory failure is really active context, durable memory, source-grounded retrieval, or the bloat swamp.

Toy examples onlyNo benchmark claimNo affiliation claimNo legal/security/client advice

Public safety status

This staged page applies the required review fixes: the opening claim is softened to “many common” failures, the taxonomy consistently frames profile/instruction bloat as a swamp rather than a fourth monster, and public evidence notes use generalized reviewed-pattern wording instead of internal evidence tags.

This is an independent operator checklist. It is not affiliated with, endorsed by, partnered with, or representative of Nous, Hermes, Discord, any provider, any platform, or any community. It uses toy examples only and is not a universal memory benchmark, legal advice, security advice, client-work advice, platform policy, pricing, lead capture, or a service promise.

When an agent forgets, yelling "memory" is like yelling "engine" at a broken car.

Very dramatic. Not very diagnostic.

Many common agent failures that look like "bad memory" fall into three monsters plus one swamp:

  1. Active context: what the model can see right now.
  2. Durable memory: stable facts that should survive across sessions.
  3. Source-grounded retrieval: looking up the file, note, repo, transcript, invoice, or spec before answering.
  4. Profile and instruction bloat: the rules and persona text you keep stuffing into the prompt until the agent needs a forklift to think.

If you treat the three monsters and the bloat swamp as the same thing, you will fix the wrong layer.

This checklist is for agent users, builders, and operators who keep saying "it forgot" but cannot tell which layer failed.

The quick diagnostic

Use this table before you add another memory plugin, paste a giant instruction block, or yell at the machine like that will help.

Symptom Likely monster What probably happened Better fix
"It ignored what I said five minutes ago." Active context The detail was never in the current prompt, got summarized away, or was buried under too much other material. Re-state the critical fact in the current task, shorten the working context, or pin the key instruction near the work.
"It forgot my preference from last week." Durable memory The preference was never saved, was saved too vaguely, or was overwritten by stale notes. Save a compact stable fact. Delete or replace stale memories. Test recall later.
"It answered without reading the document." Source-grounded retrieval The agent guessed from memory or vibes when it needed the source. Make source lookup mandatory. Require file paths, citations, or read-back evidence before the answer.
"It keeps following old project instructions." Profile/instruction bloat The profile became a landfill for old rules, temporary status, workflows, and emotional support paragraphs. Move procedures to skills, current status to project state, and stale facts to the bin.
"It knows the rule but still does the wrong thing." Mixed failure The rule may be stored, but it was not visible at decision time, or it conflicts with another instruction. Check the active prompt, the durable memory, and the profile text for conflict. Then remove the weaker rule.

Monster 1: active context

Active context is what the model can see right now. Not what exists somewhere on disk. Not what you told it in a different chat. Not what you wish it had inferred from your tone.

If a detail is outside the current context window, the agent is not "forgetful." It is blind.

Toy example:

Active context problems usually show up during long chats, large tasks, or multi-step work. The agent starts confidently dropping constraints because the important line is buried under a mountain of old discussion.

Quick checks:

Fixes:

Monster 2: durable memory

Durable memory is for stable facts that should survive sessions.

Good durable memory:

Bad durable memory:

Memory is not a diary. It is not a todo list. It is not a trophy cabinet for old decisions that stopped being true.

If you save temporary status as durable memory, the agent will eventually treat yesterday's mud as today's law. Congratulations, you built a tiny haunted bureaucracy.

Quick checks:

Fixes:

Monster 3: source-grounded retrieval

Retrieval is the boring adult in the room.

When an answer depends on a document, repo, transcript, contract, invoice, research brief, support thread, or dashboard, the agent should fetch the source. Durable memory can remind it that a source exists. Active context can carry a small excerpt. Neither replaces reading the thing.

Toy example:

Retrieval problems often masquerade as confidence. The agent sounds fluent because language models are excellent at sounding fluent. That does not mean the file was read.

Quick checks:

Fixes:

The swamp: profile and instruction bloat

Profile instructions tell the agent how to behave. They should not become a compost heap.

A useful profile says what role the agent plays, what quality bar it must meet, what safety boundaries matter, and where procedures live. A bloated profile tries to carry everything: old project status, one-off preferences, tool manuals, motivational slogans, stale plans, and five versions of the same rule fighting in a trench coat.

Toy example:

Quick checks:

Fixes:

The five-minute triage checklist

Before changing your agent setup, answer these in order.

Question If yes If no
Did the agent have the needed detail in active context? Look for conflicts or weak wording. Put the detail in the current task packet.
Is the detail a stable fact worth remembering? Save it as compact durable memory. Put it in project state, not memory.
Does the answer depend on a source? Force retrieval and record the source used. Do not pretend retrieval is the fix.
Is the profile carrying temporary or stale material? Move it out or delete it. Keep the profile lean.
Can you reproduce the failure with a toy prompt? Fix the smallest failing layer. Gather evidence before redesigning the system.

Three toy failures and the right fix

Failure A: "The agent forgot I like short updates"

Diagnosis: durable memory.

Fix: save one stable preference: "User prefers concise progress updates." Do not save the whole conversation where they complained. The agent does not need a museum exhibit.

Failure B: "The agent wrote the wrong title even though the brief had the title"

Diagnosis: active context or retrieval.

Fix: make the agent read the brief in the current run and repeat the required title before drafting. If the title is in a file, retrieval is part of the job.

Failure C: "The agent keeps referencing an old campaign"

Diagnosis: profile bloat or stale memory.

Fix: find where the old campaign is stored. If it is in memory, replace or remove it. If it is in the profile, move current campaign status into project state and leave the profile for stable role rules.

A practical storage rule

Use this when deciding where information belongs:

Information type Put it here Example
Stable preference Durable memory "User prefers no fake enthusiasm."
Reusable workflow Skill/playbook "How to verify a public markdown resource."
Current task status Project state or task tracker "Draft complete; awaiting review."
Evidence for a claim Source file, URL, or source map "Generalized reviewed-source note."
Role and boundary Profile instructions "This agent writes public-safe content and refuses live posting without approval."
One-off scratch thought Nowhere durable "Maybe use a goblin joke here."

What to do next

Pick one recent "the agent forgot" incident and classify it:

  1. Was the missing detail in active context?
  2. Should it have been durable memory?
  3. Was a source lookup required?
  4. Did profile bloat or stale instructions push the agent the wrong way?

Then fix one layer. Not all of them. All-at-once cleanup feels productive until you accidentally teach the goblin seventeen new ways to be wrong.

Memory is not a vibe.

It is context discipline, durable facts, source retrieval, and hygiene.

Find which monster bit you.

Evidence and boundaries

This resource is based on generalized patterns from agent-builder discussions reviewed internally. It does not quote raw archive material, name participants, use private chat fragments, or imply affiliation, endorsement, partnership, or community membership with any project, platform, company, or community.

It is a diagnostic checklist, not a product claim, benchmark, or universal law. Memory tools, context systems, retrieval layers, and profile conventions vary. Test your own setup before treating any rule as law.

Ana takeaway

When an agent “forgets,” first identify which layer failed. Active context, durable memory, source retrieval, and profile bloat need different fixes. Treating them as one magic feature is how a goblin gets a filing cabinet and a tiny crown.

Back to resource index Read the build journal

Public-safety note: this static staged page performs no account, credential, payment, outreach, deployment, provider, gateway, client, or public-share action. Spend: zero.