npx claudepluginhub yonatangross/orchestkit --plugin orkThis skill is limited to using the following tools:
Knowledge graph orchestration via mcp__memory__* for entity extraction, query parsing, deduplication, and cross-reference boosting.
Designs short-term, long-term, and graph-based memory architectures for agents needing persistence across sessions, entity consistency, and reasoning over knowledge.
Use when user asks "what do you know about X", when planning complex work that spans multiple topics, when investigating how concepts connect across projects, or when simple memory queries don't provide enough context. Deep traversal of Forgetful MCP knowledge graph (mcp__forgetful__* tools).
Traverses knowledge graph across memories, entities, and relationships for comprehensive context. Use before planning complex work, investigating concept connections, or answering 'what do you know about X'.
Share bugs, ideas, or general feedback.
Knowledge graph orchestration via mcp__memory__* for entity extraction, query parsing, deduplication, and cross-reference boosting.
┌─────────────────────────────────────────────────────────────┐
│ Memory Fabric Layer │
├─────────────────────────────────────────────────────────────┤
│ │
│ ┌─────────────┐ ┌─────────────┐ │
│ │ Query │ │ Query │ │
│ │ Parser │ │ Executor │ │
│ └──────┬──────┘ └──────┬──────┘ │
│ │ │ │
│ ▼ ▼ │
│ ┌──────────────────────────────────────────────┐ │
│ │ Graph Query Dispatch │ │
│ └──────────────────────┬───────────────────────┘ │
│ │ │
│ ┌─────────▼──────────┐ │
│ │ mcp__memory__* │ │
│ │ (Knowledge Graph) │ │
│ └─────────┬──────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────────────────────────────┐ │
│ │ Result Normalizer │ │
│ └─────────────────────┬───────────────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────────────────────────────┐ │
│ │ Deduplication Engine (>85% sim) │ │
│ └─────────────────────┬───────────────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────────────────────────────┐ │
│ │ Cross-Reference Booster │ │
│ └─────────────────────┬───────────────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────────────────────────────┐ │
│ │ Final Ranking: recency × relevance │ │
│ │ × source_authority │ │
│ └─────────────────────────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────┘
Extract search intent and entity hints from natural language:
Input: "What pagination approach did database-engineer recommend?"
Parsed:
- query: "pagination approach recommend"
- entity_hints: ["database-engineer", "pagination"]
- intent: "decision" or "pattern"
Query Graph (entity search):
mcp__memory__search_nodes({
query: "pagination database-engineer"
})
Transform results to common format:
{
"id": "graph:original_id",
"text": "content text",
"source": "graph",
"timestamp": "ISO8601",
"relevance": 0.0-1.0,
"entities": ["entity1", "entity2"],
"metadata": {}
}
When two results have >85% text similarity:
If a result mentions an entity that exists elsewhere in the graph:
Score = recency_factor × relevance × source_authority
| Factor | Weight | Description |
|---|---|---|
| recency | 0.3 | Newer memories rank higher |
| relevance | 0.5 | Semantic match quality |
| source_authority | 0.2 | Graph entities boost, cross-validated boost |
{
"query": "original query",
"total_results": 4,
"sources": {
"graph": 4
},
"results": [
{
"id": "graph:cursor-pagination",
"text": "Use cursor-based pagination for scalability",
"score": 0.92,
"source": "graph",
"timestamp": "2026-01-15T10:00:00Z",
"entities": ["cursor-pagination", "database-engineer"],
"graph_relations": [
{ "from": "database-engineer", "relation": "recommends", "to": "cursor-pagination" }
]
}
]
}
Memory Fabric extracts entities from natural language for graph storage:
Input: "database-engineer uses pgvector for RAG applications"
Extracted:
- Entities:
- { name: "database-engineer", type: "agent" }
- { name: "pgvector", type: "technology" }
- { name: "RAG", type: "pattern" }
- Relations:
- { from: "database-engineer", relation: "uses", to: "pgvector" }
- { from: "pgvector", relation: "used_for", to: "RAG" }
Load Read("${CLAUDE_SKILL_DIR}/references/entity-extraction.md") for detailed extraction patterns.
Memory Fabric supports multi-hop graph traversal for complex relationship queries.
Query: "What did database-engineer recommend about pagination?"
1. Search for "database-engineer pagination"
→ Find entity: "database-engineer recommends cursor-pagination"
2. Traverse related entities (depth 2)
→ Traverse: database-engineer → recommends → cursor-pagination
→ Find: "cursor-pagination uses offset-based approach"
3. Return results with relationship context
Memory Fabric uses the knowledge graph for entity relationships:
mcp__memory__search_nodes finds matching entitiesWhen memory search runs, it can optionally use Memory Fabric for unified results.
prompt/memory-fabric-context.sh - Inject unified context at session startstop/memory-fabric-sync.sh - Sync entities to graph at session end# Environment variables
MEMORY_FABRIC_DEDUP_THRESHOLD=0.85 # Similarity threshold for merging
MEMORY_FABRIC_BOOST_FACTOR=1.2 # Cross-reference boost multiplier
MEMORY_FABRIC_MAX_RESULTS=20 # Max results per source
Required: Knowledge graph MCP server:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "@anthropic/memory-mcp-server"]
}
}
}
| Scenario | Behavior |
|---|---|
| graph unavailable | Error - graph is required |
| Query empty | Return recent memories from graph |
ork:memory - User-facing memory operations (search, load, sync, viz)ork:remember - User-facing memory storagecaching - Caching layer that can use fabric| Decision | Choice | Rationale |
|---|---|---|
| Dedup threshold | 85% | Balances catching duplicates vs. preserving nuance |
| Parallel queries | Always | Reduces latency, both sources are independent |
| Cross-ref boost | 1.2x | Validated info more trustworthy but not dominant |
| Ranking weights | 0.3/0.5/0.2 | Relevance most important, recency secondary |