Vizra ADK Memory System

Vizra ADK Memory System is a skill for Claude Code, Codex from vizra-ai/vizra-adk. It costs 24 tokens per session (2,519 once invoked), scanned A, original, MIT.

A memory system for Vizra ADK agents, the PHP toolkit described here. It keeps conversation context for a session, user information across sessions, and searchable stored knowledge using vector search, a method for finding text by meaning.

In plain words
What is it for?
Use it to retain chat history, remember user-specific details, and retrieve related information for retrieval-augmented generation (RAG), where an agent answers using stored documents or data.
Why use it?
It prevents agents from forgetting earlier messages, user preferences, or relevant stored information when answering later questions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to retain chat history, remember user-specific details, and retrieve related information for retrieval-augmented generation (RAG), where an agent answers using stored documents or data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vizra-ai/vizra-adk/vizra-memory
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 vizra-ai/vizra-adk --skill vizra-memory
Clone the repo
git clone --depth 1 https://github.com/vizra-ai/vizra-adk

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 Vizra ADK Memory System

README.md
[![agentmods](https://agentmods.dev/badge/skills/vizra-ai/vizra-adk/vizra-memory/github.svg)](https://agentmods.dev/skills/vizra-ai/vizra-adk/vizra-memory)
Your own site
<a href="https://agentmods.dev/skills/vizra-ai/vizra-adk/vizra-memory"><img src="https://agentmods.dev/badge/skills/vizra-ai/vizra-adk/vizra-memory/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 Vizra ADK Memory System

Your own site · 80×15
<a href="https://agentmods.dev/skills/vizra-ai/vizra-adk/vizra-memory"><img src="https://agentmods.dev/badge/skills/vizra-ai/vizra-adk/vizra-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,519 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found 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 $0.00024 $0.02519
Opus 5 $0.00012 $0.01260
Sonnet 5 $0.00005 $0.00504
Haiku 4.5 $0.00002 $0.00252

Measured 12d ago against content hash b70dfcbed7ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Vizra ADK Memory System 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 12d 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.

resources/boost/skills/vizra-memory/SKILL.md · 433 lines

How it starts

The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vizra ADK Memory System

Vizra ADK provides multiple memory types for agents to maintain context across conversations and sessions.

Memory Types

Type Purpose Persistence
Session Memory Conversation history within a session Session lifetime
User Memory Information tied to a specific user Permanent
Vector Memory Semantic search and RAG Permanent

Basic Memory Usage

Session-Based Memory

Conversation history persists within a session:

use App\Agents\MyAgent;

$sessionId = 'conversation-123';

// First message in session
$response1 = MyAgent::run('My name is John')
    ->forUser($user)
    ->withSession($sessionId)
    ->go();

// Later in the same session - agent remembers context
$response2 = MyAgent::run('What is my name?')
    ->forUser($user)
    ->withSession($sessionId)
    ->go(); // Will remember "John"

User-Based Memory

Memory persists across all sessions for a user:

// First conversation
$response1 = MyAgent::run('I prefer dark mode and short responses')
    ->forUser($user)
    ->go();

// New conversation - user preferences are remembered
$response2 = MyAgent::run('Help me with my project')
    ->forUser($user)
    ->go(); // Agent remembers preferences

Memory Tools

MemoryTool

Allow agents to explicitly store and retrieve memories:

use Vizra\VizraADK\Tools\MemoryTool;

class PersonalAssistantAgent extends BaseLlmAgent
{
    protected string $name = 'personal_assistant';
    protected string $instructions = <<<'INSTRUCTIONS'
        You are a personal assistant. Use the memory tool to:
        - Remember important facts the user tells you
        - Recall information when asked
        - Update memories when information changes
        INSTRUCTIONS;

    protected array $tools = [
        MemoryTool::class,
    ];
}

The agent can then use commands like:

  • remember: User's birthday is March 15
  • recall: birthday
  • forget: old address

Read the full file on GitHub · 433 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. 12d ago First seen · 433 lines · 24 tokens per session scan A b70dfcbed7ac

Subscribe to this mod's changes

Vizra ADK Memory System is a skill published in the GitHub repository vizra-ai/vizra-adk (295 stars, last pushed 18d ago), licensed MIT. It adds 24 tokens to every session and 2,519 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

knowledge-graph-builder

Activates KnowledgeGraph — an expert in building, querying, and reasoning over knowledge graphs. Use when you need entity extraction, relationship mapping, ontology design, Neo4j/RDF graph construction, graph-RAG pipelines, or complex multi-hop reasoning over structured knowledge.

vignesh2027/Claude-Agentic-Skills2.0-version · 58 tokens

rag-architect

Activates the RAG-Architect agent for designing and building Retrieval-Augmented Generation systems. Use this skill when you need to build a document Q&A system, design a knowledge base with semantic search, set up vector stores (Chroma, Pinecone, pgvector), implement hybrid retrieval (dense + BM25 sparse), add…

vignesh2027/Claude-Agentic-Skills2.0-version · 95 tokens

vector-db

Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.

ginkida/rustyhand · 19 tokens

pinecone-research

Agent RAG and long-term memory with Pinecone.

NousResearch/hermes-agent · 16 tokens

langchain

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…

davila7/claude-code-templates · 79 tokens

hive.context-preservation

Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.

aden-hive/hive · 24 tokens