# io.github.jyswee/agenticmemory (npm · agmry)

Persistent memory for AI agents — history, context, semantic search, queues. 17 tools, stdio/SSE.

- Trust score: 48/100 (low)
- Change this week: −12
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

> **Malware flagged**: A supply-chain scanner flagged a high-severity malware risk in this package. Treat it as unsafe to install until the finding is cleared.

## Components

- remote · `mcp.agenticmemory.ai`: 60/100, [markdown](https://verifymcp.io/servers/jyswee-agenticmemory/mcp.md), [page](https://verifymcp.io/servers/jyswee-agenticmemory/mcp)
- npm · `agmry`: 48/100 (this document), [markdown](https://verifymcp.io/servers/jyswee-agenticmemory/agmry.md), [page](https://verifymcp.io/servers/jyswee-agenticmemory/agmry)

## Channel facts

- Registry: `npm`
- Package: `agmry`
- Version: `1.8.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 55/100
  - Malware check failed: a supply-chain vendor flagged a high-severity malware risk.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (SEE LICENSE IN LICENSE) isn't a recognized OSI-approved license.
  - Actively maintained (last published 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 895 tokens (~52/item across 17 items; 17 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add jyswee-agenticmemory -- npx -y agmry
```

### Codex

```bash
codex mcp add jyswee-agenticmemory -- npx -y agmry
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jyswee-agenticmemory": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agmry"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jyswee-agenticmemory --command npx --arg -y --arg agmry
```

### Hermes

```yaml
mcp_servers:
  jyswee-agenticmemory:
    command: "npx"
    args: ["-y", "agmry"]
```

### Other

```json
{
  "mcpServers": {
    "jyswee-agenticmemory": {
      "command": "npx",
      "args": [
        "-y",
        "agmry"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 48, +1)

- [security regression] Malware scan: unverified → fail

### 2026-07-31 (score 47, −11)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 58, −2)

- [security regression] Malware scan: fail → unverified
- [security improvement] Malware indicator gptMalware:QgESvOPDHF_L2DproytMWfrVYYre12tuIKkPe6bglQFU cleared
- [security improvement] Malware indicator gptMalware:QpemHmEw_G-J-q22oWn5Xy1F75GijPQDpPznTpqefbTk cleared
- [security improvement] Malware indicator gptMalware:QrgejRIxLENrpbANYiUQyf7u7xHA9xmFxEwnbdonFKqg cleared

### 2026-07-27 (score 60, +33)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: good
- [functional] First check of Schema quality: fail

### 2026-07-26 (score 27)

First indexed and scored.

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (17)

### `memory_store` (~62 tokens)

Store a message in conversation history. Use for remembering what just happened.

Input parameters:

- `content` (string, required): Message content
- `role` (string): Role: user, assistant, system, tool (default: user)
- `spaceId` (string, required): Memory space ID

Output parameters:

- `_id` (string): Message ID
- `content` (string): Message text
- `createdAt` (string): ISO 8601 creation timestamp
- `metadata` (object): Optional caller-supplied metadata
- `role` (string): Message role: user, assistant, system, or tool
- `seq` (number): Monotonic sequence number within the space
- `spaceId` (string): Owning memory space ID

### `memory_store_batch` (~41 tokens)

Store multiple messages at once.

Input parameters:

- `messages` (array, required): Array of {role, content} messages
- `spaceId` (string, required): Memory space ID

Output parameters:

- `messages` (array): The stored messages

### `memory_recall` (~48 tokens)

Recall recent messages from conversation history. Returns newest first.

Input parameters:

- `limit` (number): Number of messages to return (default: 20)
- `spaceId` (string, required): Memory space ID

Output parameters:

- `encrypted` (boolean): True if the space is end-to-end encrypted (content is ciphertext)
- `messages` (array): Recalled messages, newest first

### `memory_clear` (~27 tokens)

Clear all messages in a memory space.

Input parameters:

- `spaceId` (string, required): Memory space ID

Output parameters:

- `cleared` (boolean): True when messages were cleared

### `memory_search` (~67 tokens)

Semantic search across past conversations. Finds by meaning, not keywords.

Input parameters:

- `limit` (number): Max results (default: 10)
- `query` (string, required): Natural language search query
- `spaceId` (string, required): Memory space ID
- `tags` (array): Filter by tags

Output parameters:

- `count` (number): Number of results returned
- `results` (array): Matching entries ranked by semantic relevance

### `context_set` (~60 tokens)

Set a key-value context entry. Stores structured data (JSON or string).

Input parameters:

- `key` (string, required): Context key name
- `spaceId` (string, required): Memory space ID
- `value` (required): Value to store (string, number, object, array)

Output parameters:

- `key` (string): The key that was set
- `value`: The stored value (string, number, object, or array)

### `context_get` (~36 tokens)

Get a context value by key.

Input parameters:

- `key` (string, required): Context key name
- `spaceId` (string, required): Memory space ID

Output parameters:

- `encrypted` (boolean): True if the space is end-to-end encrypted (value is ciphertext)
- `key` (string): The requested key
- `value`: The stored value (string, number, object, or array)

### `context_list` (~29 tokens)

List all context keys and values in a space.

Input parameters:

- `spaceId` (string, required): Memory space ID

Output parameters:

- `context` (object): Map of every context key to its stored value
- `encrypted` (boolean): True if the space is end-to-end encrypted (values are ciphertext)

### `context_delete` (~35 tokens)

Delete a context key.

Input parameters:

- `key` (string, required): Context key to delete
- `spaceId` (string, required): Memory space ID

Output parameters:

- `deleted` (boolean): True when the key was deleted

### `entry_add` (~82 tokens)

Add a long-term memory entry (summary, decision, extraction, artifact).

Input parameters:

- `content` (string): Entry content
- `spaceId` (string, required): Memory space ID
- `tags` (array): Tags for filtering
- `title` (string, required): Entry title
- `type` (string): Type: extraction, summary, decision, artifact (default: extraction)

Output parameters:

- `entry` (object)

### `entries_list` (~57 tokens)

List long-term memory entries. Filter by tags.

Input parameters:

- `limit` (number): Max entries (default: 20)
- `spaceId` (string, required): Memory space ID
- `tags` (string): Comma-separated tags to filter by

Output parameters:

- `encrypted` (boolean): True if the space is end-to-end encrypted (content is ciphertext)
- `entries` (array): Matching long-term entries

### `spaces_list` (~18 tokens)

List all memory spaces owned by this API key.

Output parameters:

- `spaces` (array): Every memory space owned by the caller

### `spaces_create` (~33 tokens)

Create a new memory space.

Input parameters:

- `name` (string, required): Space name
- `slug` (string, required): URL-safe slug

Output parameters:

- `space` (object)

### `queue_push` (~84 tokens)

Enqueue a JSON envelope onto a FIFO queue in a memory space. Use to send work/events to other agents sharing the space.

Input parameters:

- `envelope` (object, required): JSON envelope to enqueue (opaque to the server)
- `queue` (string, required): Queue name (lowercase alphanumeric plus . _ : -, max 64 chars)
- `spaceId` (string, required): Memory space ID

Output parameters:

- `length` (number): Queue length after the push
- `queue` (string): Queue name
- `queued` (boolean): True when the envelope was enqueued

### `queue_pop` (~84 tokens)

Dequeue the oldest envelope from a FIFO queue (returns null if empty). Set wait (max 25s) to long-poll for the next envelope.

Input parameters:

- `queue` (string, required): Queue name
- `spaceId` (string, required): Memory space ID
- `wait` (number): Long-poll seconds, 0-25 (default: 0 = return immediately)

Output parameters:

- `empty` (boolean): True when the queue was empty
- `encrypted` (boolean): True if the space is end-to-end encrypted (item is ciphertext)
- `item` (object|null): The dequeued envelope, or null if the queue was empty
- `queue` (string): Queue name

### `queue_peek` (~43 tokens)

Peek at a queue without consuming: returns length and the head envelope.

Input parameters:

- `queue` (string, required): Queue name
- `spaceId` (string, required): Memory space ID

Output parameters:

- `head` (object|null): The head envelope without consuming it, or null if empty
- `length` (number): Current queue length
- `queue` (string): Queue name

### `memory_bootstrap` (~89 tokens)

Load full context in one call: recent messages, entries, context, scratchpad. Run this at session start.

Input parameters:

- `entries` (number): Number of entries to include (default: 10)
- `messages` (number): Number of messages to include (default: 20)
- `query` (string): Semantic query for relevant entries
- `spaceId` (string, required): Memory space ID

Output parameters:

- `activeThreads` (array): Active conversation threads
- `contextEncoding` (string): Context encoding mode (json or lln)
- `encryption` (string): Encryption mode: none, managed, or e2e
- `entities` (array): Known entities in the space
- `llnPrimer` (string): LLN primer mode (inline, system, or none)
- `recentEntries` (array): Most recent long-term entries
- `recentMessages` (array): Most recent messages
- `semanticEntries` (array): Entries matched by the optional semantic query
- `shared` (object): Shared world context visible to all agents in the space
- `state` (object): Current working state for the space

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/jyswee-agenticmemory/agmry#diagnostics

## Score history

- 2026-08-03: 48
- 2026-08-02: 48
- 2026-08-01: 47
- 2026-07-31: 47
- 2026-07-30: 58
- 2026-07-28: 60
- 2026-07-27: 60
- 2026-07-26: 27

## Links

- npm package: https://www.npmjs.com/package/agmry
- Socket report: https://socket.dev/npm/package/agmry
- Repository: https://github.com/jyswee/agenticmemory
- Website: https://agenticmemory.ai/
- Changelog RSS feed: https://verifymcp.io/servers/jyswee-agenticmemory/agmry/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/jyswee-agenticmemory/agmry/changelog.json
- HTML version of this page: https://verifymcp.io/servers/jyswee-agenticmemory/agmry