Agent Skills › TanStack/ai › tanstack-ai-memory-in-memory

tanstack-ai-memory-in-memory

GitHub

基于 Map 的零依赖内存适配器，适用于本地开发、测试及单进程演示。数据随进程重启丢失，不支持多进程或持久化场景。支持 topK、embedder 等配置，容量建议不超过十万条记录。

packages/ai-memory/skills/tanstack-ai-memory-in-memory/SKILL.md TanStack/ai

Trigger Scenarios

需要在本地开发环境进行快速原型验证编写 Vitest 或 Playwright 单元测试运行不需要持久化存储的单进程演示程序

Install

npx skills add TanStack/ai --skill tanstack-ai-memory-in-memory -g -y

More Options

Non-standard path

npx skills add https://github.com/TanStack/ai/tree/main/packages/ai-memory/skills/tanstack-ai-memory-in-memory -g -y

Use without installing

npx skills use TanStack/ai@tanstack-ai-memory-in-memory

指定 Agent (Claude Code)

npx skills add TanStack/ai --skill tanstack-ai-memory-in-memory -a claude-code -g -y

安装 repo 全部 skill

npx skills add TanStack/ai --all -g -y

预览 repo 内 skill

npx skills add TanStack/ai --list

SKILL.md

Frontmatter

{
    "name": "tanstack-ai-memory-in-memory",
    "description": "Use when wiring inMemory() from @tanstack\/ai-memory\/in-memory — explains setup, options (embedder, extract, topK\/minScore), when to pick it (dev\/tests\/single-process demos), and what NOT to use it for (multi-process or persistent)."
}

In-Memory Memory Adapter

Zero-dependency recall/save adapter backed by a Map. Records vanish on process restart.

When to use it

Local development.
Vitest / Playwright tests.
Single-process demos where users don't need persistence.

When NOT to use it

Production multi-process deployments — every worker has its own Map; users get inconsistent memory.
Anything that needs survival across restarts.

For production, use redis() (see the tanstack-ai-memory-redis skill).

Setup

import { memoryMiddleware } from '@tanstack/ai-memory'
import { inMemory } from '@tanstack/ai-memory/in-memory'

const memory = inMemory()

memoryMiddleware({ adapter: memory, scope })

Options

inMemory(options?) accepts:

topK (default 6), minScore (default 0.15), kinds — recall tuning.
embedder: { embed(text): Promise<number[]> } — enable semantic scoring (both recall and save embed through it).
extract(turn, scope) — return derived facts to persist alongside the raw turn (e.g. call an LLM to pull out preferences). Without it, save stores the raw user/assistant messages and recall scores them lexically + by recency.
render(hits) — replace the built-in prompt renderer.