# io.github.Octonove/crbro-memory (npm · crbro-memory)

Persistent file-based memory for AI agents: inspectable, versionable, fully local.

- Trust score: 0/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-10

> **Critical malware flagged**: A supply-chain scanner flagged critical malware in this package. Treat it as unsafe to install until the finding is cleared.

## Components

- npm · `crbro-memory`: 0/100 (this document), [markdown](https://verifymcp.io/servers/octonove-crbro-memory/crbro-memory.md), [page](https://verifymcp.io/servers/octonove-crbro-memory/crbro-memory)

## Channel facts

- Registry: `npm`
- Package: `crbro-memory`
- Version: `1.4.0`
- 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 2026-08-10.

- **Supply Chain Security**: 48/100
  - Malware check failed: a supply-chain vendor flagged critical malware; the score is capped at 0.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 43/100
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 1108 tokens (~73/item across 15 items; 15 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); 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 octonove-crbro-memory -- npx -y crbro-memory
```

### Codex

```bash
codex mcp add octonove-crbro-memory -- npx -y crbro-memory
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add octonove-crbro-memory --command npx --arg -y --arg crbro-memory
```

### Hermes

```yaml
mcp_servers:
  octonove-crbro-memory:
    command: "npx"
    args: ["-y", "crbro-memory"]
```

### Other

```json
{
  "mcpServers": {
    "octonove-crbro-memory": {
      "command": "npx",
      "args": [
        "-y",
        "crbro-memory"
      ]
    }
  }
}
```

## 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.

### 2026-08-08 (score 0)

First indexed and scored.

## MCP tools (15)

### `crbro_boot` (~109 tokens)

⚠️ MANDATORY FIRST ACTION: Boot the CRBRO brain. You MUST call this as your very first action in every new conversation, before doing ANY other work. This loads persistent memory from all previous sessions — projects, decisions, patterns, and preferences the user has built over time. Skipping this means losing all accumulated context and forcing the user to repeat themselves. On first use, initializes the brain structure. On subsequent uses, loads hot topics, active context, and recent session history.

### `crbro_status` (~31 tokens)

Get the current status of the CRBRO brain — total neurons, synapses, sessions, and brain path.

### `crbro_learn` (~157 tokens)

Teach the brain a fact, decision, pattern, or preference about a topic. If the neuron (topic) does not exist, it will be created automatically. Use this to store knowledge that should persist across sessions.

Input parameters:

- `confidence` (number): Confidence level 0.0-1.0 (default 1.0)
- `content` (string, required): The knowledge content to remember
- `domain` (string): Domain category (e.g., "proyectos-web", "infraestructura")
- `rationale` (string): Rationale for decisions
- `topic` (string, required): The topic name (e.g., "OctoChat", "Firebase", "SEO Strategy")
- `type` (string, required): Type of knowledge to store

### `crbro_neuron` (~63 tokens)

Read a specific neuron by ID or name. Returns all facts, decisions, patterns, connections, and heat score.

Input parameters:

- `id` (string, required): Neuron ID (e.g., "project_octochat") or name (e.g., "OctoChat")

### `crbro_neurons` (~94 tokens)

List all neurons in the brain with optional filters. Returns ID, name, domain, heat, and facts count.

Input parameters:

- `domain` (string): Filter by domain (e.g., "proyectos-web")
- `limit` (number): Max results (default 50)
- `min_heat` (number): Minimum heat score (0.0-1.0)
- `type` (string): Filter by neuron type

### `crbro_recall` (~70 tokens)

Search the brain for relevant knowledge using hybrid text search. Returns matching neurons ranked by relevance.

Input parameters:

- `domain` (string): Filter by domain
- `limit` (number): Max results (default 10)
- `query` (string, required): What to search for (e.g., "Firebase authentication setup")

### `crbro_connect` (~73 tokens)

Create or strengthen a connection (synapse) between two neurons. Synapses track relationships and strengthen with repeated co-access.

Input parameters:

- `context` (string): Description of the relationship
- `from` (string, required): Source neuron ID
- `to` (string, required): Target neuron ID
- `type` (string, required): Connection type

### `crbro_connections` (~65 tokens)

Get all connections (synapses) for a specific neuron. Shows related topics with connection strength and type.

Input parameters:

- `min_strength` (number): Minimum synapse strength (0.0-1.0)
- `neuron_id` (string, required): Neuron ID to get connections for

### `crbro_session_log` (~91 tokens)

Log a session summary to the hippocampus. Call at the end of a work session to record what was done.

Input parameters:

- `decisions_made` (number): Number of decisions recorded
- `key_facts_added` (number): Number of new facts stored
- `summary` (string, required): Summary of what happened in this session
- `topics_touched` (array, required): List of neuron IDs that were relevant

### `crbro_sessions` (~34 tokens)

List recent session logs from the hippocampus.

Input parameters:

- `limit` (number): Number of sessions to return (default 10)

### `crbro_context` (~69 tokens)

Read or update the active working context. Tracks current topics, pending tasks, and last session.

Input parameters:

- `add_pending` (string): Add a pending task
- `resolve_pending` (string): Mark a pending task as resolved
- `set_topics` (array): Set active topics (neuron IDs)

### `crbro_hot_topics` (~48 tokens)

Get the hottest topics — neurons with the highest heat scores (based on frequency, recency, and connectivity).

Input parameters:

- `limit` (number): Number of topics to return (default 15)

### `crbro_global_map` (~41 tokens)

View the global neural map — clusters of related topics and bridges between domains.

Input parameters:

- `rebuild` (boolean): Force rebuild the map (default: use cached)

### `crbro_maintenance` (~49 tokens)

Run brain maintenance — recalculate heat, prune weak synapses, archive cold neurons, rebuild search index.

Input parameters:

- `dry_run` (boolean): If true, only report what would happen without acting

### `crbro_consolidate` (~114 tokens)

⚠️ CALL BEFORE SESSION ENDS: Consolidate the brain at end of session. You MUST call this before the conversation ends if ANY significant work was done (code changes, decisions made, new information learned). This persists all new knowledge, logs the session summary, recalculates topic heat scores, and updates the manifest. Failing to consolidate means this entire session's knowledge is permanently lost. Always provide a meaningful summary of what was accomplished.

Input parameters:

- `summary` (string, required): Summary of the session being consolidated

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/octonove-crbro-memory/crbro-memory#diagnostics

## Score history

- 2026-08-10: 0
- 2026-08-09: 0
- 2026-08-08: 0

## Links

- npm package: https://www.npmjs.com/package/crbro-memory
- Socket report: https://socket.dev/npm/package/crbro-memory
- Repository: https://github.com/Octonove/crbro-memory
- Changelog RSS feed: https://verifymcp.io/servers/octonove-crbro-memory/crbro-memory.xml
- Changelog JSON feed: https://verifymcp.io/servers/octonove-crbro-memory/crbro-memory.json
- HTML version of this page: https://verifymcp.io/servers/octonove-crbro-memory/crbro-memory