V3 Memory Unification

V3 Memory Unification is a skill for Claude Code, Codex from ayushcodes10/echo-mem. It costs 51 tokens per session (1,172 once invoked), scanned A, a copy of V3 Memory Unification, Apache-2.0.

A migration guide for combining several memory stores into AgentDB, using HNSW indexing for fast similarity search. Similarity search finds stored items that are close in meaning or representation.

In plain words
What is it for?
Use it to configure AgentDB, set up HNSW indexes, and migrate SQLite and Markdown data from existing memory backends.
Why use it?
It helps replace separate memory systems with one backend while preserving compatibility and supporting searches across stored agent information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to configure AgentDB, set up HNSW indexes, and migrate SQLite and Markdown data from existing memory backends.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ayushcodes10/echo-mem/v3-memory-unification
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ayushcodes10/echo-mem --skill v3-memory-unification
Clone the repo
git clone --depth 1 https://github.com/ayushcodes10/echo-mem

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for V3 Memory Unification

README.md
[![agentmods](https://agentmods.dev/badge/skills/ayushcodes10/echo-mem/v3-memory-unification/github.svg)](https://agentmods.dev/skills/ayushcodes10/echo-mem/v3-memory-unification)
Your own site
<a href="https://agentmods.dev/skills/ayushcodes10/echo-mem/v3-memory-unification"><img src="https://agentmods.dev/badge/skills/ayushcodes10/echo-mem/v3-memory-unification/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for V3 Memory Unification

Your own site · 80×15
<a href="https://agentmods.dev/skills/ayushcodes10/echo-mem/v3-memory-unification"><img src="https://agentmods.dev/badge/skills/ayushcodes10/echo-mem/v3-memory-unification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,172 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01172
Opus 5.5 $0.00020 $0.00469
Sonnet 5.5 $0.00010 $0.00234
Haiku 4.5 $0.00005 $0.00117

Measured 1mo ago against content hash 4853ec2fec84, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

V3 Memory Unification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to V3 Memory Unification — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/v3-memory-unification/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

V3 Memory Unification

What This Skill Does

Consolidates disparate memory systems into unified AgentDB backend with HNSW vector search, achieving 150x-12,500x search performance improvements while maintaining backward compatibility.

Quick Start

# Initialize memory unification
Task("Memory architecture", "Design AgentDB unification strategy", "v3-memory-specialist")

# AgentDB integration
Task("AgentDB setup", "Configure HNSW indexing and vector search", "v3-memory-specialist")

# Data migration
Task("Memory migration", "Migrate SQLite/Markdown to AgentDB", "v3-memory-specialist")

Systems to Unify

Legacy Systems → AgentDB

┌─────────────────────────────────────────┐
│  • MemoryManager (basic operations)     │
│  • DistributedMemorySystem (clustering) │
│  • SwarmMemory (agent-specific)         │
│  • AdvancedMemoryManager (features)     │
│  • SQLiteBackend (structured)           │
│  • MarkdownBackend (file-based)         │
│  • HybridBackend (combination)          │
└─────────────────────────────────────────┘
                    ↓
┌─────────────────────────────────────────┐
│       🚀 AgentDB with HNSW             │
│  • 150x-12,500x faster search          │
│  • Unified query interface             │
│  • Cross-agent memory sharing          │
│  • SONA learning integration           │
└─────────────────────────────────────────┘

Implementation Architecture

Unified Memory Service

class UnifiedMemoryService implements IMemoryBackend {
  constructor(
    private agentdb: AgentDBAdapter,
    private indexer: HNSWIndexer,
    private migrator: DataMigrator
  ) {}

  async store(entry: MemoryEntry): Promise<void> {
    await this.agentdb.store(entry);
    await this.indexer.index(entry);
  }

  async query(query: MemoryQuery): Promise<MemoryEntry[]> {
    if (query.semantic) {
      return this.indexer.search(query); // 150x-12,500x faster
    }
    return this.agentdb.query(query);
  }
}

HNSW Vector Search

class HNSWIndexer {
  constructor(dimensions: number = 1536) {
    this.index = new HNSWIndex({
      dimensions,
      efConstruction: 200,
      M: 16,
      speedupTarget: '150x-12500x'
    });
  }

  async search(query: MemoryQuery): Promise<MemoryEntry[]> {
    const embedding = await this.embedContent(query.content);
    const results = this.index.search(embedding, query.limit || 10);
    return this.retrieveEntries(results);
  }
}

Read the full file on GitHub · 174 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 174 lines · 51 tokens per session scan A 4853ec2fec84

Subscribe to this mod's changes

V3 Memory Unification is a skill published in the GitHub repository ayushcodes10/echo-mem (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,172 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to V3 Memory Unification, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

omnigraph

Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…

ModernRelay/omnigraph · 94 tokens

mesh-memory

Self-hosted semantic memory for AI agents via MCP. Save worklogs, decisions, and notes, then recall them across sessions by meaning, not keyword. Postgres + pgvector with auto-tagging.

skillmds/skillmd · 44 tokens

setup

Set up memex with provisioned Postgres (RDS + pgvector), AGENTS.md injection, first import.

timurgaleev/memex · 25 tokens

databases

Use when creating, changing, or reviewing MongoDB/PostgreSQL/SQLite database work in a real repository, including schema, models, migrations, queries, indexes, transactions, connection config, backup/restore assumptions, dual-database desktop sync, or performance; follow repo-native tooling and meet the production…

tamnguyendinh/Anvien · 74 tokens

squish

ALWAYS use this skill when working with agents, memory, context, persistence, or AI agent state. Use when the user mentions: 'the agent forgot', 'save this', 'remember that', 'context is lost', 'memory', 'MCP server', 'agent memory', 'persistent memory', 'session context', 'project context', 'recall', 'remember'…

michielhdoteth/squish-memory · 157 tokens

squish-memory

Persistent memory system for Claude Code. Use when you need to store, recall, or search project memories, facts, decisions, and learnings across sessions. Triggers on: remember, recall, memory, forget, search memories, store context, project knowledge, what did we decide, previous conversation.

michielhdoteth/squish-memory · 0 tokens