tanstack-ai-memory-hindsight
GitHub用于集成 @tanstack/ai-memory/hindsight 的托管记忆适配器。它将记忆按会话分桶，通过 recall/recall/reflect 工具让模型自主管理长期记忆，支持配置用户ID、预算及回调。
触发场景
安装
npx skills add TanStack/ai --skill tanstack-ai-memory-hindsight -g -y
SKILL.md
Frontmatter
{
"name": "tanstack-ai-memory-hindsight",
"description": "Use when wiring hindsight() from @tanstack\/ai-memory\/hindsight — a hosted memory adapter that buckets memory per conversation and exposes retain\/recall\/reflect tools to the model. Requires the optional @vectorize-io\/hindsight-client peer."
}
Hindsight Memory Adapter
Hosted recall/save adapter backed by Hindsight. Hindsight owns extraction and
ranking server-side, buckets memory into per-conversation "banks"
({tenantId|_}__{user}__{threadId}), and — uniquely — exposes LLM tools through recall so the
model can retain/recall/reflect directly.
Setup
import { memoryMiddleware } from '@tanstack/ai-memory'
import { hindsight } from '@tanstack/ai-memory/hindsight'
const memory = hindsight({ user: currentUserId }) // baseUrl defaults to HINDSIGHT_URL
memoryMiddleware({ adapter: memory, scope })
@vectorize-io/hindsight-client is an optional peer dependency, loaded lazily on
first use — install it where you use hindsight().
Options
user— durable user id for the bank key (falls back toscope.userId).baseUrl— Hindsight server URL (defaultHINDSIGHT_URLorhttp://localhost:8888).budget— recall budget:'low' | 'mid' | 'high'(default'mid').onToolRetain/onToolRecall— callbacks fired when the model uses the memory tools.
Scope fields: bank id is {tenantId|_}__{user}__{threadId}. namespace is ignored.
Tools
recall returns hindsight_retain, hindsight_recall, and hindsight_reflect in its
tools plus a toolGuidance block. memoryMiddleware merges them into the run so the
model can manage long-term memory itself.
版本历史
- 05280a5 当前 2026-07-30 23:52
