← 返回 Skills 市场

Fast Unified Memory

Name: Fast Unified Memory
Author: broedkrummen

作者 Broedkrummen · GitHub ↗ · v1.0.1

cross-platform ⚠ suspicious

398

总下载

当前安装

版本数

在 OpenClaw 中安装

/install fast-unified-memory

功能描述

Provides a high-performance unified memory combining file-based OpenClaw storage with semantic vector search using local Ollama embeddings for fast, private...

使用说明 (SKILL.md)

Skill: Fast Unified Memory

A high-performance unified memory system that integrates OpenClaw memory with semantic memory storage using Ollama's nomic-embed-text model for ultra-fast embeddings.

Overview

This skill provides a unified memory layer that combines:

OpenClaw Memory: Standard file-based memory storage
Semantic Memory: Vector-based memory using Ollama embeddings

Features

⚡ Ultra-fast: ~130ms for combined search (embedding ~40ms + search ~90ms)
🔒 Private: All processing done locally via Ollama
💰 Free: No API costs - uses local Ollama instance
🧠 Semantic: Uses nomic-embed-text for intelligent similarity matching

Requirements

Ollama installed and running
nomic-embed-text model pulled: ollama pull nomic-embed-text

Installation

# Install Ollama first
curl -fsSL https://ollama.ai/install.sh | sh

# Pull the embedding model
ollama pull nomic-embed-text

# Start Ollama
ollama serve

Usage

Commands

# Search both memory systems
node fast-unified-memory.js search "your query"

# Add a memory
node fast-unified-memory.js add "User prefers concise responses"

# List all memories
node fast-unified-memory.js list

# Show system stats
node fast-unified-memory.js stats

Architecture

┌─────────────────────────────────────────────┐
│           FAST UNIFIED MEMORY                │
│                                             │
│  ┌─────────────┐    ┌─────────────┐        │
│  │   OpenClaw  │    │   Semantic  │        │
│  │   Memory    │    │   Memory    │        │
│  │ (files)     │    │  (vectors) │        │
│  └─────────────┘    └─────────────┘        │
│           ↓                  ↓              │
│    [Keyword Match]   [Cosine Similarity]   │
│                                             │
│        Unified Results (ranked)             │
└─────────────────────────────────────────────┘

Performance

Metric	Value
Embedding generation	~40ms
Vector search	~50ms
File search	~40ms
Total search	~130ms

Configuration

The skill uses these defaults:

Ollama URL: http://localhost:11434
Embedding model: nomic-embed-text
Memory storage: ~/.mem0/fast-store.json
OpenClaw memory: ~/.openclaw/workspace/memory/

Files

fast-unified-memory.js - Main CLI tool
SKILL.md - This documentation

Troubleshooting

Ollama not running:

ollama serve

Model not found:

ollama pull nomic-embed-text

Port conflict: The skill assumes Ollama is on port 11434. Update the OLLAMA_URL constant if using a different port.

License

MIT

安全使用建议

What to consider before installing or running this skill: - The core functionality is coherent: it uses a local Ollama instance for embeddings and combines vector search with keyword search over a file-based memory store. - Red flag: the code hard-codes /home/broedkrummen/.openclaw/workspace/memory and default user_id 'broedkrummen'. This is inconsistent with the documented '~/.openclaw/...' and may cause the script to: (a) silently fail on systems with a different username; or (b) read another user's OpenClaw memory if that exact path exists. Either outcome is unexpected and could leak or access private local files unintentionally. Recommended actions before use: - Inspect and (preferably) modify fast-unified-memory.js to make the OpenClaw path configurable. For example, compute MEMORY_DIR from process.env.HOME (or accept a CLI flag or env var) rather than hard-coding a username. - Replace hard-coded userId defaults with a dynamic value (e.g., process.env.USER or a provided --user flag) so mem0 operations are scoped to the current user. - Run the tool in a controlled environment (or with a test user) the first time to confirm which directories it reads and what it writes to ~/.mem0/fast-store.json. - Confirm Ollama is only listening on localhost and that network exposure/ports are acceptable for your threat model. - If you cannot or do not want to edit the code, avoid running it with elevated privileges and search the repository for hard-coded paths/identifiers before running. Confidence note: High confidence in the assessment that the hard-coded path/username is an incoherence and a practical concern. There is no evidence of network exfiltration or external endpoints beyond the documented local Ollama API.

功能分析

Type: OpenClaw Skill Name: fast-unified-memory Version: 1.0.1 The skill is classified as suspicious due to the inclusion of a `curl -fsSL https://ollama.ai/install.sh | sh` command in `SKILL.md`. While intended for installing a prerequisite (Ollama) from its official source, if an AI agent were to execute instructions directly from markdown, this represents a significant arbitrary code execution vulnerability. Additionally, the `fast-unified-memory.js` script contains hardcoded user paths (`/home/broedkrummen/.openclaw/workspace/memory`) and a hardcoded user ID (`broedkrummen`) for memory storage, which are functional bugs and portability vulnerabilities. No evidence of intentional malicious behavior like data exfiltration, persistence, or unauthorized remote control was found.

能力评估

⚠ Purpose & Capability

The skill claims to combine local file-based OpenClaw memory with local Ollama embeddings, which is consistent with the code's behavior. However, the code hard-codes MEMORY_DIR = '/home/broedkrummen/.openclaw/workspace/memory' and default user_id = 'broedkrummen', while SKILL.md documents a tilde (~) path and generic behavior. The hard-coded username/path is not justified by the description and is an incoherence.

⚠ Instruction Scope

SKILL.md instructs only to install and run Ollama, pull the model, and run the CLI. The runtime JS mostly stays inside that scope (calls localhost Ollama embeddings, reads/writes a local JSON store, scans a file directory). However, the code will attempt to read files under a specific absolute path (/home/broedkrummen/...) which is not mentioned in the documentation and could cause the skill to read another user's OpenClaw memory if that path exists. The instructions do not disclose that behavior.

✓ Install Mechanism

No install spec or third-party downloads included by the skill itself. The SKILL.md tells the user to install Ollama from its official install script and pull a model; the skill's code has no external download/exec beyond calling Ollama's local HTTP API. No archive downloads or external code fetches in the skill.

ℹ Credentials

The skill requests no environment variables. It reads process.env.HOME for the mem0 store (expected). But it also embeds a specific username in both the OpenClaw path and mem0 user_id defaults, which is disproportionate/unexpected: these should normally be derived from HOME or a config, not hard-coded. This could cause the tool to ignore the current user or to access another user's files if present.

✓ Persistence & Privilege

The skill does not set always:true and does not request system-wide privileges. It writes/reads only its own store (~/.mem0/fast-store.json) and attempts to read the OpenClaw path. Autonomous invocation (disable-model-invocation: false) is the platform default; combined with the hard-coded path this increases the blast radius slightly but by itself is not unusual.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install fast-unified-memory
安装完成后，直接呼叫该 Skill 的名称或使用 /fast-unified-memory 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.1

- Added main source file: fast-unified-memory.js - Documentation updates: SKILL.md now references itself as the main documentation file instead of MEMORY_INTEGRATION.md - No significant feature or configuration changes introduced

v1.0.0

Fast-unified-memory 1.0.0 initial release: - Introduces a unified memory system combining OpenClaw file-based memory with semantic vector memory using local Ollama embeddings. - Enables ultra-fast semantic and keyword search (~130ms total) with all processing performed locally for privacy and no API costs. - Provides CLI commands for searching, adding, listing, and checking memory system stats. - Requires Ollama and the nomic-embed-text embedding model to be installed and running locally. - Includes technical documentation and troubleshooting guidance.

元数据

Slug fast-unified-memory

版本 1.0.1

许可证 —

累计安装 1

当前安装数 1

历史版本数 2

常见问题