> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orcapods.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# orca memory

> List, search, show, and delete an agent's memories, and read the cross-profile memory bank.

> **Last updated: 2026-09-06**

`orca memory` inspects agent memories and the [memory bank](/concepts/memory-bank) that spans every profile in the tenant. Memories are written by agents as they run (or extracted in the dashboard), so the CLI is read, search, and delete only; there is no create or update.

Every subcommand accepts the [global flags](/cli/reference/overview#global-flags). `delete` prompts for confirmation in a terminal; in a script `--yes` is required or the command refuses (exit code 2).

## orca memory list

```bash theme={"dark"}
orca memory list <agent> [--limit <n>] [--offset <n>]
```

Lists an agent's memories. These are the command's own paging flags, not the shared page flags: there is no `--all`, and neither flag has a CLI default. When omitted they are not sent and the server pages with its own values.

| Flag           | Type    | Default                | Description |
| -------------- | ------- | ---------------------- | ----------- |
| `--limit <n>`  | integer | server default (`100`) | Page size   |
| `--offset <n>` | integer | server default (`0`)   | Page offset |

When the server holds more memories than the page returned, the terminal view prints a `Showing X of Y` hint on stderr.

```bash theme={"dark"}
orca memory list researcher --limit 50 --json
```

Plain (piped) output is one tab-separated row per memory: `id`, `category`, `source`, `confidence`, `createdAt`, `summary`. The `--json` output is the array of memory records only, without the page totals.

## orca memory search

```bash theme={"dark"}
orca memory search <agent> <query> [--limit <n>] [--min-score <n>]
```

Searches an agent's memories by relevance. Both flags are forwarded only when set; the defaults shown are applied by the server.

| Flag              | Type    | Default                 | Description             |
| ----------------- | ------- | ----------------------- | ----------------------- |
| `--limit <n>`     | integer | server default (`8`)    | Maximum results         |
| `--min-score <n>` | number  | server default (`0.05`) | Minimum relevance score |

```bash theme={"dark"}
orca memory search researcher "preferred citation style" --min-score 0.2 --json
```

Plain (piped) output is one tab-separated row per hit: `id`, `score`, `category`, `summary`. The `--json` output is the array of scored results; each has `memory` (the full record) and `relevance` (`score`, `recency`, `usage`, `topic`).

## orca memory show

```bash theme={"dark"}
orca memory show <agent> <id>
```

Shows one memory in full: category, source, confidence, staleness, access count, active flag, version, timestamps, the summary, the processed content, and the raw input when it differs from the processed content.

```bash theme={"dark"}
orca memory show researcher mem_01J... --json
```

Plain (piped) output is one `field`, `value` row per field: `id`, `profile`, `category`, `source`, `confidence`, `staleness`, `accessCount`, `isActive`, `version`, `createdAt`, `lastAccessedAt`, `summary`, `processedContent`. With `--json` the full memory record is printed.

## orca memory delete

```bash theme={"dark"}
orca memory delete <agent> <id> [--yes]
```

Deletes one memory.

| Flag    | Type    | Default | Description                  |
| ------- | ------- | ------- | ---------------------------- |
| `--yes` | boolean | `false` | Skip the confirmation prompt |

```bash theme={"dark"}
orca memory delete researcher mem_01J... --yes --json
```

```json theme={"dark"}
{ "id": "mem_01J...", "deleted": true }
```

## orca memory bank

```bash theme={"dark"}
orca memory bank
```

Prints a snapshot of the whole memory bank across every profile. The terminal and plain views flatten the snapshot into one list sorted by profile name, newest memory first within each profile, with a header that counts memories and profiles. With `--json` the snapshot is printed as the server returns it: `total`, `profilesWithMemory`, and `memories`, a map from profile name to that profile's memory records.

```bash theme={"dark"}
orca memory bank --json | jq '.memories | keys'
```

Plain (piped) output is one tab-separated row per memory: `profile`, `id`, `category`, `summary`, `createdAt`.

### orca memory bank stats

```bash theme={"dark"}
orca memory bank stats
```

Shows bank-wide totals and a per-profile count, sorted by count descending.

```bash theme={"dark"}
orca memory bank stats --json
```

Plain (piped) output is one tab-separated `profile`, `count` row per profile. The `--json` output is the stats record: `totalMemories`, `profilesWithMemory`, and `perProfile`, a map from profile name to count.

<Note>
  Verified against orca-cli `cli-v0.5.0`.
</Note>