Standing notes (MEMORY.md / USER.md)

In plain terms

Vector memory is a big library. These files are a sticky note on the monitor. Two notes:

MEMORY.md — facts about the project / environment (“deploys on Fridays”)
USER.md — facts about this person (“likes short answers”)

They are always injected into the prompt (when they have content). They have a hard size cap. When the box is full, the agent must shorten old lines before adding new ones. That is on purpose — it keeps the prompt small. This sits next to MemoryManager. It does not replace sessions, summaries, or vector learnings.

Turn it on

const agent = new Agent({
  name: "assistant",
  model: openai(process.env.OPENAI_MODEL ?? "gpt-6.1-sol"),
  fileMemory: true,
});

Enable this explicitly with fileMemory: true; use scoped persistent storage when notes must survive restarts. Optional caps (defaults: 2200 chars for memory, 1375 for user):

fileMemory: { memoryCharLimit: 2200, userCharLimit: 1375 }

Pass storage to keep notes in SQLite/Postgres instead of RAM.

The `memory` tool

The model gets one tool named memory:

`action`	Needs	Does
`add`	`content`	Append a line (no-op if it already exists)
`replace`	`old_text` + `content`	Swap the one line that contains `old_text`
`remove`	`old_text`	Delete that line

target is "memory" (default) or "user". If adding would overflow:

{
  "ok": false,
  "error": "Memory at 2100/2200 chars. … Consolidate with replace/remove, then retry.",
  "usage": "2100/2200",
  "current_entries": ["…"]
}

What to use when

Need	Use
This chat’s turns	`memory: { storage }` sessions
Old chats, compressed	`memory.summaries`
”Alex lives in Mumbai” extracted automatically	`memory.userFacts`
Reusable lessons, search by meaning	`memory.learnings` / `learning: { vectorStore }`
Tiny facts that must always be in the prompt	`fileMemory`

Removed in v3

These classes are gone. Their replacements do the same job through the memory config:

Removed	Use instead
`Memory` class	`memory: { storage, summaries: true }`
`UserMemory` class	`memory.userFacts` + `memory.userProfile`, or `fileMemory`
`CultureManager`	`contextFiles` (AGENTS.md) + `fileMemory` + `memory.learnings`
`FlashMemoryStore`	`memory: { storage }` — sessions already live in storage

See the v3 migration guide.

Build

Agent applications

Harness runtime

Teams and workflows

Data and capabilities

Interfaces and jobs

Voice and telephony

Verify and manage

Standing notes (MEMORY.md / USER.md)

In plain terms

Turn it on

The `memory` tool

What to use when

Removed in v3

​In plain terms

​Turn it on

​The memory tool

​What to use when

​Removed in v3

In plain terms

Turn it on

The `memory` tool

What to use when

Removed in v3