iris-development

작성자: redis

Iris는 AI 중심 제품을 위한 Redis의 포괄적인 브랜드입니다. Redis Cloud에서 Iris Redis Agent Memory (RAM) 데이터 플레인과 통합할 때 이 스킬을 사용하세요 — 기록…

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

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:

LanguagePackageClassInstall
Pythonredis-agent-memoryAgentMemorypip install redis-agent-memory
TypeScript@redis-iris/agent-memoryAgentMemorynpm 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

PriorityCategoryImpactPrefix
1Setup & Cloud ServiceHIGHsetup-
2Session Memory / EventsHIGHsession-
3Long-Term MemoryHIGHltm-
4Memory PromotionMEDIUMpromotion-

Quick Reference

1. Setup & Cloud Service (HIGH)

2. Session Memory / Events (HIGH)

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)

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

redis의 다른 스킬

docs-sync
redis
마스터 브랜치의 구현 및 구성을 분석하여 docs/, README.md, 패키지별 README에서 누락되거나, 부정확하거나, 오래된 문서를 찾습니다.
redis-query-engine
redis
Redis Query Engine (RQE) 가이드: FT.CREATE 스키마 설계, 필드 유형 선택(TEXT, TAG, NUMERIC, GEO, GEOSHAPE, VECTOR), DIALECT 2 쿼리 구문,…
redis-search
redis
Redis Search 가이드: FT.CREATE 스키마 설계, 필드 유형 선택(TEXT, TAG, NUMERIC, GEO, GEOSHAPE, VECTOR, JSON 경로), DIALECT 2 쿼리 구문,…
redis-security
redis
Redis 보안 가이드로 인증(requirepass 및 ACL 사용자), TLS, ACL 기반 최소 권한 접근 제어, 네트워크 노출 제한 등을 다룹니다.
redis-semantic-cache
redis
Redis LangCache를 사용하여 Redis Cloud에서 LLM 응답의 시맨틱 캐싱을 수행하는 방법 — SDK 또는 REST API를 통한 검색/설정 호출, 유사도 임계값 조정,…
redis-vector-search
redis
Redis 벡터 검색 가이드: HNSW vs FLAT 알고리즘 선택, 벡터 인덱스 구성(차원, 거리 메트릭, 데이터 타입), 필터링된 하이브리드 검색…
bump-test-image
redis
공유 DEFAULT_DOCKER_CONFIG 및 CI 매트릭스에서 기본 Redis docker 테스트 이미지(redislabs/client-libs-test)를 범프한 다음 강제 푸시합니다…
i18n
redis
RedisInsight UI(i18next)의 국제화 규칙입니다. redisinsight/ui/** 아래의 사용자 표시 문자열을 추가하거나 변경할 때, ...를 편집할 때 사용합니다.