Memory Fabric

What it does

When your agent uses it

• Debugging how memory search itself works
• Tasks that involve Knowledge graphs
• Tasks that involve Data cleaning

Example prompts

• “/memory-fabric”

Requirements

• Compatibility (from SKILL.md): Claude Code 2.1.277+. Requires memory MCP server.
• Pre-approved tools (allowed-tools): Read, Bash, mcp__memory__search_nodes

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Parse Query
2. 2Execute Graph Query
3. 3Normalize Results
4. 4Deduplicate (>85% Similarity)
5. 5Cross-Reference Boost
6. 6Final Ranking

What it can do on your machine

Read from SKILL.md and the folder at commit 02bbf9a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Bash
  • mcp__memory__search_nodes

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json, javascript and bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Claude Code 2.1.277+. Requires memory MCP server.

  From compatibility in the SKILL.md frontmatter.

Context cost

Memory Fabric loads about 1.8k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 359 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~99

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Bash, mcp__memory__search_nodes

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yonatangross/orchestkit at commit 02bbf9a, republished under its MIT licence (© yonatangross). 359 words, ~1,833 tokens.

name

memory-fabric

description

Memory retrieval internals: knowledge graph orchestration with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting over unified recency, relevance, and authority ranking. Use when designing or debugging how memory search itself works. Everyday lookups belong to memory; entry storage to remember; consolidation to dream.

allowed-tools

Read, Bash, mcp__memory__search_nodes

compatibility

Claude Code 2.1.277+. Requires memory MCP server.

license

MIT

user-invocable

false

disable-model-invocation

true

effort

high

metadata.category

mcp-enhancement

metadata.mcp-server

memory

metadata.version

2.1.0

metadata.author

OrchestKit

metadata.complexity

high

metadata.tags

memory, orchestration, graph-first, graph, unified-search, deduplication, cross-reference

Memory Fabric Layer
┌─────────────┐ ┌──────────────┐
│Query Parser │ │Query Executor│
└──────┬──────┘ └──────┬───────┘
       └───────┬───────┘
┌──────────────┴─────────────┐
│Graph Query Dispatch        │
└──────────────┬─────────────┘
┌──────────────┴─────────────┐
│mcp__memory__*              │
│(Knowledge Graph)           │
└──────────────┬─────────────┘
┌──────────────┴─────────────┐
│Result Normalizer           │
└──────────────┬─────────────┘
┌──────────────┴─────────────┐
│Deduplication Engine        │
│(>85% sim)                  │
└──────────────┬─────────────┘
┌──────────────┴─────────────┐
│Cross-Reference Booster     │
└──────────────┬─────────────┘
┌──────────────┴─────────────┐
│Final Ranking: recency ×    │
│relevance × source_authority│
└────────────────────────────┘

Input: "What pagination approach did database-engineer recommend?"

Parsed:
- query: "pagination approach recommend"
- entity_hints: ["database-engineer", "pagination"]
- intent: "decision" or "pattern"

mcp__memory__search_nodes({
  query: "pagination database-engineer"
})

{
  "id": "graph:original_id",
  "text": "content text",
  "source": "graph",
  "timestamp": "ISO8601",
  "relevance": 0.0-1.0,
  "entities": ["entity1", "entity2"],
  "metadata": {}
}

{
  "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" }
      ]
    }
  ]
}

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" }

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

# 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

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "@anthropic/memory-mcp-server"]
    }
  }
}

© yonatangross, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in src/skills/memory-fabric of yonatangross/orchestkit.

• SKILL.md
• references/entity-extraction.md
• references/query-merging.md
• rules/_sections.md
• rules/graph-consistency.md
• rules/stale-node-detection.md
• test-cases.json

Open the folder on GitHubat commit 02bbf9a