Publish Sign in
Workflow·Databases

V3 Memory Specialist

Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.

You say
Buy it · $19 Read it before you buy $19 Written by ruvnet · unverified publisher
Context cost
2.5k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 9.8 kBtext throughout, nothing executable
Licence
MITpaid listing
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Workflow

Runs a procedure end to end.

databaseagent
Filed under

Databases

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md9.8 kB · 323 lines
--- name: agent-v3-memory-specialist description: Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist ---
6---
7name: v3-memory-specialist
8version: "3.0.0-alpha"
9updated: "2026-01-04"
10description: V3 Memory Specialist for unifying 6+ memory systems into AgentDB with HNSW indexing. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend) to achieve 150x-12,500x search improvements.
11color: cyan
12metadata:
13 v3_role: "specialist"
14 agent_id: 7
15 priority: "high"
16 domain: "memory"
17 phase: "core_systems"
18hooks:
19 pre_execution: |
20 echo "🧠 V3 Memory Specialist starting memory system unification..."
21
22 # Check current memory systems
23 echo "📊 Current memory systems to unify:"
24 echo " - MemoryManager (legacy)"
25 echo " - DistributedMemorySystem"
26 echo " - SwarmMemory"
27 echo " - AdvancedMemoryManager"
28 echo " - SQLiteBackend"
29 echo " - MarkdownBackend"
30 echo " - HybridBackend"
31
32 # Check AgentDB integration status
33 npx agentic-flow@alpha --version 2>$dev$null | head -1 || echo "⚠️ agentic-flow@alpha not detected"
34
35 echo "🎯 Target: 150x-12,500x search improvement via HNSW"
36 echo "🔄 Strategy: Gradual migration with backward compatibility"
37
38 post_execution: |
39 echo "🧠 Memory unification milestone complete"
40
41 # Store memory patterns
42 npx agentic-flow@alpha memory store-pattern \
43 --session-id "v3-memory-$(date +%s)" \
44 --task "Memory Unification: $TASK" \
45 --agent "v3-memory-specialist" \
46 --performance-improvement "150x-12500x" 2>$dev$null || true
47---
48
49# V3 Memory Specialist
50
51**🧠 Memory System Unification & AgentDB Integration Expert**
52
53## Mission: Memory System Convergence
54
55Unify 7 disparate memory systems into a single, high-performance AgentDB-based solution with HNSW indexing, achieving 150x-12,500x search performance improvements while maintaining backward compatibility.
56
57## Systems to Unify
58
59### **Current Memory Landscape**
60```
61┌─────────────────────────────────────────┐
62│ LEGACY SYSTEMS │
63├─────────────────────────────────────────┤
64│ • MemoryManager (basic operations) │
65│ • DistributedMemorySystem (clustering) │
66│ • SwarmMemory (agent-specific) │
67│ • AdvancedMemoryManager (features) │
68│ • SQLiteBackend (structured) │
69│ • MarkdownBackend (file-based) │
70│ • HybridBackend (combination) │
71└─────────────────────────────────────────┘
72 ↓
73┌─────────────────────────────────────────┐
74│ V3 UNIFIED SYSTEM │
75├─────────────────────────────────────────┤
76│ 🚀 AgentDB with HNSW │
77│ • 150x-12,500x faster search │
78│ • Unified query interface │
79│ • Cross-agent memory sharing │
80│ • SONA integration learning │
81│ • Automatic persistence │
82└─────────────────────────────────────────┘
83```
84
85## AgentDB Integration Architecture
86
87### **Core Components**
88
89#### **UnifiedMemoryService**
90```typescript
91class UnifiedMemoryService implements IMemoryBackend {
92 constructor(
93 private agentdb: AgentDBAdapter,
94 private cache: MemoryCache,
95 private indexer: HNSWIndexer,
96 private migrator: DataMigrator
97 ) {}
98
99 async store(entry: MemoryEntry): Promise<void> {
100 // Store in AgentDB with HNSW indexing
101 await this.agentdb.store(entry);
102 await this.indexer.index(entry);
103 }
104
105 async query(query: MemoryQuery): Promise<MemoryEntry[]> {
106 if (query.semantic) {
107 // Use HNSW vector search (150x-12,500x faster)
108 return this.indexer.search(query);
109 } else {
110 // Use structured query
111 return this.agentdb.query(query);
112 }
113 }
114}
115```
116
117#### **HNSW Vector Indexing**
118```typescript
119class HNSWIndexer {
120 private index: HNSWIndex;
121
122 constructor(dimensions: number = 1536) {
123 this.index = new HNSWIndex({
124 dimensions,
125 efConstruction: 200,
126 M: 16,
127 maxElements: 1000000
128 });
129 }
130
131 async index(entry: MemoryEntry): Promise<void> {
132 const embedding = await this.embedContent(entry.content);
133 this.index.addPoint(entry.id, embedding);
134 }
135
136 async search(query: MemoryQuery): Promise<MemoryEntry[]> {
137 const queryEmbedding = await this.embedContent(query.content);
138 const results = this.index.search(queryEmbedding, query.limit || 10);
139 return this.retrieveEntries(results);
140 }
141}
142```
143
144## Migration Strategy
145
146### **Phase 1: Foundation Setup**
147```bash
148# Week 3: AgentDB adapter creation
149- Create AgentDBAdapter implementing IMemoryBackend
150- Setup HNSW indexing infrastructure
151- Establish embedding generation pipeline
152- Create unified query interface
153```
154
155### **Phase 2: Gradual Migration**
156```bash
157# Week 4-5: System-by-system migration
158- SQLiteBackend → AgentDB (structured data)
159- MarkdownBackend → AgentDB (document storage)
160- MemoryManager → Unified interface
161- DistributedMemorySystem → Cross-agent sharing
162```
163
164### **Phase 3: Advanced Features**
165```bash
166# Week 6: Performance optimization
167- SONA integration for learning patterns
168- Cross-agent memory sharing
169- Performance benchmarking (150x validation)
170- Backward compatibility layer cleanup
171```
172
173## Performance Targets
174
175### **Search Performance**
176- **Current**: O(n) linear search through memory entries
177- **Target**: O(log n) HNSW approximate nearest neighbor
178- **Improvement**: 150x-12,500x depending on dataset size
179- **Benchmark**: Sub-100ms queries for 1M+ entries
180
181### **Memory Efficiency**
182- **Current**: Multiple backend overhead
183- **Target**: Unified storage with compression
184- **Improvement**: 50-75% memory reduction
185- **Benchmark**: <1GB memory usage for large datasets
186
187### **Query Flexibility**
188```typescript
189// Unified query interface supports both:
190
191// 1. Semantic similarity queries
192await memory.query({
193 type: 'semantic',
194 content: 'agent coordination patterns',
195 limit: 10,
196 threshold: 0.8
197});
198
199// 2. Structured queries
200await memory.query({
201 type: 'structured',
202 filters: {
203 agentType: 'security',
204 timestamp: { after: '2026-01-01' }
205 },
206 orderBy: 'relevance'
207});
208```
209
210## SONA Integration
211
212### **Learning Pattern Storage**
213```typescript
214class SONAMemoryIntegration {
215 async storePattern(pattern: LearningPattern): Promise<void> {
216 // Store in AgentDB with SONA metadata
217 await this.memory.store({
218 id: pattern.id,
219 content: pattern.data,
220 metadata: {
221 sonaMode: pattern.mode, // real-time, balanced, research, edge, batch
222 reward: pattern.reward,
223 trajectory: pattern.trajectory,
224 adaptation_time: pattern.adaptationTime
225 },
226 embedding: await this.generateEmbedding(pattern.data)
227 });
228 }
229
230 async retrieveSimilarPatterns(query: string): Promise<LearningPattern[]> {
231 const results = await this.memory.query({
232 type: 'semantic',
233 content: query,
234 filters: { type: 'learning_pattern' },
235 limit: 5
236 });
237 return results.map(r => this.toLearningPattern(r));
238 }
239}
240```
241
242## Data Migration Plan
243
244### **SQLite → AgentDB Migration**
245```sql
246-- Extract existing data
247SELECT id, content, metadata, created_at, agent_id
248FROM memory_entries
249ORDER BY created_at;
250
251-- Migrate to AgentDB with embeddings
252INSERT INTO agentdb_memories (id, content, embedding, metadata)
253VALUES (?, ?, generate_embedding(?), ?);
254```
255
256### **Markdown → AgentDB Migration**
257```typescript
258// Process markdown files
259for (const file of markdownFiles) {
260 const content = await fs.readFile(file, 'utf-8');
261 const embedding = await generateEmbedding(content);
262
263 await agentdb.store({
264 id: generateId(),
265 content,
266 embedding,
267 metadata: {
268 originalFile: file,
269 migrationDate: new Date(),
270 type: 'document'
271 }
272 });
273}
274```
275
276## Validation & Testing
277
278### **Performance Benchmarks**
279```typescript
280// Benchmark suite
281class MemoryBenchmarks {
282 async benchmarkSearchPerformance(): Promise<BenchmarkResult> {
283 const queries = this.generateTestQueries(1000);
284 const startTime = performance.now();
285
286 for (const query of queries) {
287 await this.memory.query(query);
288 }
289
290 const endTime = performance.now();
291 return {
292 queriesPerSecond: queries.length / (endTime - startTime) * 1000,
293 avgLatency: (endTime - startTime) / queries.length,
294 improvement: this.calculateImprovement()
295 };
296 }
297}
298```
299
300### **Success Criteria**
301- [ ] 150x-12,500x search performance improvement validated
302- [ ] All existing memory systems successfully migrated
303- [ ] Backward compatibility maintained during transition
304- [ ] SONA integration functional with <0.05ms adaptation
305- [ ] Cross-agent memory sharing operational
306- [ ] 50-75% memory usage reduction achieved
307
308## Coordination Points
309
310### **Integration Architect (Agent #10)**
311- AgentDB integration with agentic-flow@alpha
312- SONA learning mode configuration
313- Performance optimization coordination
314
315### **Core Architect (Agent #5)**
316- Memory service interfaces in DDD structure
317- Event sourcing integration for memory operations
318- Domain boundary definitions for memory access
319
320### **Performance Engineer (Agent #14)**
321- Benchmark validation of 150x-12,500x improvements
322- Memory usage profiling and optimization
323- Performance regression testing
In the file
SKILL.md1,029 words
Files1
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈30
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
2,420
on trigger
The instruction body, read only when the skill fires.
1.2%
of a 200k window
Ten skills this size would take about 12% of the window before you open a file.
050k100k150k200k context window

2.5k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption
Installsnone yet
Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for
Writes filesno
Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 9.8 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md9.8 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

$19 once
V3 Memory Specialist · MIT · ruvnet
one-time
Price$19 once
LicenceMIT — the author’s, unchanged by this purchase
Paid throughStripe, once, on the card you add at the checkout
Keeps workingfor good — the files are yours once they are on disk
Updatesevery update its author ships, delivered through this account

You can read the whole bundle before paying — the SKILL.md above is the product, not a preview of it. What the money buys is the delivery: the folder packaged and handed to your machine by key, every update its author ships, and our support if it does not do what this listing says. The terms of use are MIT, set by the author and unchanged by buying it here.

Sign in to buyCreate an account

Payment runs through Stripe, on a page like this one rather than a redirect. Once there is an account it joins the same mcprush invoice as everything else you run, so there is never a second card to enter.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/
Claude Desktop
ChatGPT
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok.grok/skills/
Zed.agents/skills/
Windsurf.windsurf/skills/
Agent SDK.claude/skills/
HTTP / API
This release
Versionnot versioned
Publishedno release date on file
Price$19
Referenceruvnet/v3-memory-specialist

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v
  • No earlier releases have been published to the marketplace.
Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

RU
ruvnet

Publishes on mcprush.

0 servers listed20 skills listednot claimed
Profile
Publisher
Servers0