搜索

PythonReactSEOPDF
OpenClaw

openclaw-memory-core

Core utilities for OpenClaw memory plugins (redaction, local store, embeddings).

homeofe0 来源安装数☆ 0 仓库 Stars

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。

SkillHub CLI

skillhub install homeofe/openclaw-memory-core

打开来源仓库,查看说明和兼容环境后,按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent,让它先读取说明、核对依赖,并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

OpenClaw Memory Core

Shared library powering OpenClaw's memory plugins (openclaw-memory-brain and openclaw-memory-docs). Provides three core modules:

Redaction

Automatically detects and redacts secrets before they reach memory storage. Covers:

  • API keys (OpenAI, Anthropic, Stripe, Google, GitHub PATs)
  • AWS credentials (access keys, secret keys)
  • Azure storage keys, HashiCorp Vault tokens
  • JWTs, Bearer tokens, PEM private key blocks

Usage: pipe any text through the redactor before storing — secrets are replaced with safe [REDACTED:TYPE] placeholders.

JSONL Store

Local file-based memory store using append-only .jsonl files. Features:

  • CRUD for memory items (kinds: fact, decision, doc, note)
  • Expiration support (expiresAt field)
  • Semantic search via cosine similarity on embeddings
  • No external database required — everything lives in flat files

Embeddings

Deterministic, offline, dependency-free text embedder (HashEmbedder):

  • FNV-1a hash-based vector generation (default 256 dimensions)
  • L2 normalization for cosine similarity search
  • No API calls, no model downloads — works fully offline
  • Not SOTA semantics, but stable and fast for local vector search

Integration

This is a dependency library, not a standalone plugin. Install it as a package dependency:

npm install @elvatis_com/openclaw-memory-core

Used internally by openclaw-memory-brain (auto-capture) and openclaw-memory-docs (explicit capture).

来源信息

Source
github
Repository
openclaw/skills
Path
skills/homeofe/openclaw-memory-core
Version
—
Commit
59a1276e500635577abac5b9182c44ea842723e3
分类来源
rules
状态
active
可见性
public

这些信息来自收录时的来源分析,可能滞后;使用前请核对最新来源文件。

README

@elvatis_com/openclaw-memory-core

Core utilities for building OpenClaw memory plugins - redaction, embeddings, and JSONL-backed vector search.

Installation

npm install @elvatis_com/openclaw-memory-core

Requires Node.js 18+.

Quick start

import {
  JsonlMemoryStore,
  createEmbedder,
  DefaultRedactor,
  uuid,
} from "@elvatis_com/openclaw-memory-core";

// 1. Set up the store
const embedder = createEmbedder();
const store = new JsonlMemoryStore({
  filePath: "./data/memories.jsonl",
  embedder,
});

// 2. Redact secrets before storing
const redactor = new DefaultRedactor();
const { redactedText } = redactor.redact("My API key is sk-proj-abc123def456ghi789");

// 3. Store a memory
await store.add({
  id: uuid(),
  kind: "note",
  text: redactedText,
  createdAt: new Date().toISOString(),
  tags: ["api", "credentials"],
});

// 4. Search by natural language
const results = await store.search("API key");
console.log(results[0]?.item.text);
// => "My API key is [REDACTED:OPENAI_KEY]"

API reference

All exports are available from the package root:

import { /* any export */ } from "@elvatis_com/openclaw-memory-core";

Types
MemoryKind
type MemoryKind = "fact" | "decision" | "doc" | "note";

The four supported item categories.

MemoryItem
interface MemoryItem {
  id: string;
  kind: MemoryKind;
  text: string;
  createdAt: string;          // ISO 8601
  expiresAt?: string;         // ISO 8601 - optional TTL
  source?: {
    channel?: string;
    from?: string;
    conversationId?: string;
    messageId?: string;
  };
  tags?: string[];
  meta?: Record<string, unknown>;
}

The fundamental data unit stored by a MemoryStore.

SearchHit
interface SearchHit {
  item: MemoryItem;
  score: number;  // 0..1 (1 = best match)
}

Returned by store.search(). Results are sorted by score descending.

SearchOpts
interface SearchOpts {
  limit?: number;...

来源内容

SKILL.md
# OpenClaw Memory Core

Shared library powering OpenClaw's memory plugins (`openclaw-memory-brain` and `openclaw-memory-docs`). Provides three core modules:

## Redaction

Automatically detects and redacts secrets before they reach memory storage. Covers:
- API keys (OpenAI, Anthropic, Stripe, Google, GitHub PATs)
- AWS credentials (access keys, secret keys)
- Azure storage keys, HashiCorp Vault tokens
- JWTs, Bearer tokens, PEM private key blocks

Usage: pipe any text through the redactor before storing — secrets are replaced with safe `[REDACTED:TYPE]` placeholders.

## JSONL Store

Local file-based memory store using append-only `.jsonl` files. Features:
- CRUD for memory items (kinds: `fact`, `decision`, `doc`, `note`)
- Expiration support (`expiresAt` field)
- Semantic search via cosine similarity on embeddings
- No external database required — everything lives in flat files

## Embeddings

Deterministic, offline, dependency-free text embedder (`HashEmbedder`):
- FNV-1a hash-based vector generation (default 256 dimensions)
- L2 normalization for cosine similarity search
- No API calls, no model downloads — works fully offline
- Not SOTA semantics, but stable and fast for local vector search

## Integration

This is a dependency library, not a standalone plugin. Install it as a package dependency:

```bash
npm install @elvatis_com/openclaw-memory-core
```

Used internally by `openclaw-memory-brain` (auto-capture) and `openclaw-memory-docs` (explicit capture).
README
# @elvatis_com/openclaw-memory-core

Core utilities for building OpenClaw memory plugins - redaction, embeddings, and JSONL-backed vector search.

## Installation

```bash
npm install @elvatis_com/openclaw-memory-core
```

Requires Node.js 18+.

## Quick start

```ts
import {
  JsonlMemoryStore,
  createEmbedder,
  DefaultRedactor,
  uuid,
} from "@elvatis_com/openclaw-memory-core";

// 1. Set up the store
const embedder = createEmbedder();
const store = new JsonlMemoryStore({
  filePath: "./data/memories.jsonl",
  embedder,
});

// 2. Redact secrets before storing
const redactor = new DefaultRedactor();
const { redactedText } = redactor.redact("My API key is sk-proj-abc123def456ghi789");

// 3. Store a memory
await store.add({
  id: uuid(),
  kind: "note",
  text: redactedText,
  createdAt: new Date().toISOString(),
  tags: ["api", "credentials"],
});

// 4. Search by natural language
const results = await store.search("API key");
console.log(results[0]?.item.text);
// => "My API key is [REDACTED:OPENAI_KEY]"
```

## API reference

All exports are available from the package root:

```ts
import { /* any export */ } from "@elvatis_com/openclaw-memory-core";
```

---

### Types

#### `MemoryKind`

```ts
type MemoryKind = "fact" | "decision" | "doc" | "note";
```

The four supported item categories.

#### `MemoryItem`

```ts
interface MemoryItem {
  id: string;
  kind: MemoryKind;
  text: string;
  createdAt: string;          // ISO 8601
  expiresAt?: string;         // ISO 8601 - optional TTL
  source?: {
    channel?: string;
    from?: string;
    conversationId?: string;
    messageId?: string;
  };
  tags?: string[];
  meta?: Record<string, unknown>;
}
```

The fundamental data unit stored by a `MemoryStore`.

#### `SearchHit`

```ts
interface SearchHit {
  item: MemoryItem;
  score: number;  // 0..1 (1 = best match)
}
```

Returned by `store.search()`. Results are sorted by score descending.

#### `SearchOpts`

```ts
interface SearchOpts {
  limit?: number;...

相关技能

OpenClaw

bambu-studio-ai

heyixuan2

Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...

OpenClaw

geo-optimization

capt-marbles

Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...

OpenClaw

parakeet-stt

carlulsoe

Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API. Use when transcribing audio files, converting speech to text, o...

OpenClaw

feishu-process-feedback

carlzhao007

飞书消息自动处理与进度反馈技能。安装后后台运行,监听飞书任务消息并自动创建独立进程处理。 在处理前后发送实时进度反馈(任务确认、进度百分比、完成通知)。 支持任务类型识别、智能解析、错误重试、并发控制、状态持久化...