Skill

Official

Review

Audit score 70

iris-development

redis/agent-skills

Persistent memory layer for AI agents on Redis Cloud with session and long-term memory tiers.

What is iris-development?

Iris Redis Agent Memory (RAM) is a managed service on Redis Cloud that provides append-only session memory and semantically searchable long-term memory for AI agents. Use this skill when integrating agent memory persistence, recording session events, searching memories, or configuring memory promotion.

Record session events as append-only conversation history per agent session
Create and search long-term memories with semantic filtering and metadata organization
Configure memory stores on Redis Cloud with authentication tokens
Tune background promotion workers that extract facts from sessions into long-term memory
Organize memories by namespace, owner ID, topics, and memory type

How to install iris-development

npx skills add https://github.com/redis/agent-skills --skill iris-development

Prerequisites

Redis Cloud account with Agent Memory service provisioned
AGENT_MEMORY_API_KEY environment variable set
AGENT_MEMORY_STORE_ID environment variable set
Python `redis-agent-memory` package or TypeScript `@redis-iris/agent-memory` package installed

Claude Code

Cursor

Windsurf

Cline

How to use iris-development

1.Create a Memory service on Redis Cloud at https://cloud.redis.io/#/agent-memory
2.Retrieve your API key and store ID from the Cloud console
3.Set AGENT_MEMORY_API_KEY and AGENT_MEMORY_STORE_ID environment variables
4.Initialize AgentMemory client with the official SDK for your language
5.Call addSessionEvent() or add_session_event() to record conversation turns
6.Use searchLongTermMemory() or search_long_term_memory() to retrieve memories with filters
7.Monitor background promotion to verify facts are extracted into long-term memory

Use cases

Good for

Building a chatbot that retains conversation history and learns user preferences over time
Extracting key facts from multi-turn conversations and storing them for future retrieval
Implementing semantic search across an agent's accumulated knowledge base
Setting up a managed memory service for a multi-agent system on Redis Cloud
Automating memory promotion from session events to persistent long-term records

Who it's for

AI agent developers integrating persistent memory
Backend engineers building conversational systems
Teams deploying agents on Redis Cloud
Developers using Python or TypeScript SDKs

iris-development FAQ

What is the difference between session memory and long-term memory?

Session memory is append-only conversation history per session (working memory). Long-term memory is semantically searchable records extracted from sessions or created directly, persisted across sessions.

Do I need to manually promote session events to long-term memory?

No. A background promotion worker managed by Redis Cloud automatically extracts durable facts from session events and writes them into long-term memory.

Which languages are supported?

Python (via `redis-agent-memory` package) and TypeScript (via `@redis-iris/agent-memory` package) are officially supported with dedicated SDKs.

What is the production data-plane URL?

The default production URL is `https://gcp-us-east4.memory.redis.io`, but your exact URL is shown in the Redis Cloud console after provisioning.

How do I authenticate with the Agent Memory API?

Set the AGENT_MEMORY_API_KEY environment variable with your store API key. The SDK reads it automatically.

Full instructions (SKILL.md)

Source of truth, from redis/agent-skills.

name: iris-development description: Iris is Redis's umbrella for AI-focused products. Use this skill when integrating with the Iris Redis Agent Memory (RAM) data plane on Redis Cloud — recording session events for an AI agent, creating or searching long-term memories, configuring a memory store, or tuning background memory promotion. Code examples use the official `redis-agent-memory` (Python) and `@redis-iris/agent-memory` (TypeScript) SDKs. license: MIT metadata: author: redis version: "1.0.0"

Iris: Redis Agent Memory

Iris is the umbrella brand for Redis's AI-focused products. This skill currently covers one product in that family: Redis Agent Memory (RAM) — the persistent memory layer for AI agents, delivered as a managed service on Redis Cloud. Additional Iris products will be added as separate sections when they ship.

Redis Agent Memory exposes a REST/JSON data-plane API with two memory tiers:

Session memory — append-only conversation history per session (working memory).
Long-term memory — semantically searchable records extracted from sessions (or created directly).

A background promotion worker — managed by Redis Cloud — extracts durable facts from session events and writes them into long-term memory.

Official SDKs

All code samples use the official SDKs:

Language	Package	Class	Install
Python	`redis-agent-memory`	`AgentMemory`	`pip install redis-agent-memory`
TypeScript	`@redis-iris/agent-memory`	`AgentMemory`	`npm add @redis-iris/agent-memory`

Both SDKs read the bearer token from AGENT_MEMORY_API_KEY and the default store ID from AGENT_MEMORY_STORE_ID. The production data-plane URL is https://gcp-us-east4.memory.redis.io; the exact URL for your service is also shown in the Cloud console after provisioning.

When to Apply

Reference these guidelines when:

Creating a memory service on Redis Cloud (https://cloud.redis.io/#/agent-memory)
Wiring an agent to call AgentMemory.add_session_event(...) / addSessionEvent(...)
Searching long-term memory with search_long_term_memory(...) / searchLongTermMemory(...)
Choosing between session events and direct long-term memory writes

Rule Categories by Priority

Priority	Category	Impact	Prefix
1	Setup & Cloud Service	HIGH	`setup-`
2	Session Memory / Events	HIGH	`session-`
3	Long-Term Memory	HIGH	`ltm-`
4	Memory Promotion	MEDIUM	`promotion-`

Quick Reference

1. Setup & Cloud Service (HIGH)

setup-cloud-service - Create a Memory service on Redis Cloud
setup-auth-token - Authenticate the SDK with a store API key

2. Session Memory / Events (HIGH)

session-when-to-use - Choose session events vs direct long-term memory
session-add-event - Append a session event correctly
session-retrieval - Retrieve session memory and individual events

3. Long-Term Memory (HIGH)

ltm-bulk-create - Create long-term memories in bulk with idempotent IDs
ltm-search - Search long-term memory semantically with filters
ltm-organize - Organize records with namespace, ownerId, topics, and memoryType

4. Memory Promotion (MEDIUM)

promotion-overview - How background promotion works

How to Use

Read individual rule files under references/ for detailed explanations and code examples:

references/setup-cloud-service.md
references/session-add-event.md
references/promotion-overview.md

Each rule file contains:

Brief explanation of why it matters
Correct example(s) with Python and TypeScript SDK code
Either an "Incorrect" example or "When to use / When NOT needed" guidance
Additional context and references

Related skills

More from redis/agent-skills and the wider catalog.

redis-clustering

Official

redis/agent-skills

Design Redis Cluster keys with hash tags and route reads to replicas to avoid CROSSSLOT errors and scale read-heavy workloads.

1.6k installsAudited

redis-connections

Official

redis/agent-skills

Configure Redis clients efficiently with pooling, pipelining, and client-side caching.

2.4k installsAudited

redis-core

Official

redis/agent-skills

Choose the right Redis data structure and key-naming convention for your access pattern.

3.3k installsAudited

redis-development

Official

redis/agent-skills

Redis performance optimization and best practices for data structures, query engines, vector search, and semantic caching.

3.3k installs

redis-observability

Official

redis/agent-skills

Monitor Redis health and diagnose performance issues with key metrics and built-in commands.

2.0k installsAudited

redis-search

redis/agent-skills

Redis Search guidance for schema design, vector indexing, and hybrid retrieval queries.

1.3k installsAudited