novyx-memory（诺维克斯内存） Skills下载安装命令和教程

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手，先确认命令和权限，再让它执行。

请帮我安装这个 Agent Skill：novyx-memory（诺维克斯内存）
来源仓库：https://github.com/novyxlabs/novyx-memory
安装命令：
openclaw skills install novyx-memory
安装前请先检查当前环境是否支持对应 CLI，并向我确认将要执行的命令、安装目录、联网范围和文件读写权限；确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill；本站只展示命令，不托管安装包，也不自动执行。

ClawHubOpenClaw

openclaw skills install novyx-memory

简介

novyx-memory 是企业级持久内存解决方案，支持 AI 代理的回滚、审计跟踪与知识图谱构建。

适用于需要时间旅行调试、受控操作与多命令历史管理的复杂任务场景。
提供超过 60 个专用命令，强化代理行为可追溯性与状态管理能力。
安装命令为 openclaw skills install novyx-memory，需确认权限范围及是否触发文件读写或数据库操作。
建议参考原始文档了解数据安全与访问控制机制。

SKILL.md

name: novyx-memory
description: Enterprise-grade persistent memory for AI agents — rollback, audit trails, knowledge graph, governed actions, time-travel debugging, and 60+ commands covering 100% of Novyx Core
version: 3.0.0
homepage: https://novyxlabs.com
metadata
openclaw
primaryEnv: NOVYX_API_KEY
requires
env

Novyx Memory

The only memory skill with rollback, cryptographic audit trails, and governed actions. 60+ commands covering 100% of Novyx Core — memory, drafts, knowledge graph, context spaces, time-travel replay, eval scoring, execution tracing, and policy-controlled actions.

Why Novyx Memory

Every other memory skill gives you save and search. Novyx gives you the full stack:

Capability	Novyx	Built-in	SuperMemory	Mem0	memory-tools
Semantic search	✓	✗	✓	✓	✓
Time-travel rollback	✓	✗	✗	✗	✗
Cryptographic audit trail	✓	✗	✗	✗	✗
Draft review workflow	✓	✗	✗	✗	✗
Knowledge graph	✓	✗	✗	✗	✗
Context spaces (multi-agent)	✓	✗	✗	✗	✗
Governed actions	✓	✗	✗	✗	✗
Execution tracing	✓	✗	✗	✗	✗
Memory health eval	✓	✗	✗	✗	✗
Confidence & decay	✓	✗	✗	✗	✓

When to Use This Skill

Agent needs memory that persists across sessions
You need to undo, roll back, or audit what the agent remembered
Multiple agents need shared context spaces
Agent actions need policy approval before execution
You want a knowledge graph built from agent observations
You need time-travel debugging ("what did the agent know at 3pm?")
CI pipeline needs a memory health gate

Automatic Behavior

When active, this skill:

Auto-recalls relevant memories before each response and injects them as context
Auto-saves each user message and agent response to persistent storage
Skips trivial messages (under 15 characters) to conserve API calls
Filters out previously injected context to prevent feedback loops

Commands (60+)

Memory Basics

Command	What it does
`!remember <text> [--tags t1,t2]`	Save a specific fact or note with optional tags
`!search <query>`	Semantic search with relevance scores
`!list [--tag tag] [--limit N]`	List stored memories with optional filters
`!forget <topic>`	Find and delete all memories matching a topic
`!undo [N]`	Delete the last N saved memories (default: 1)
`!supersede <id> <new text>`	Replace an old memory with a corrected version

Draft Review Workflow

Stage memory changes before committing — like git for agent memory.

Command	What it does
`!draft <text> [--branch name]`	Create a reviewable draft
`!drafts`	List pending drafts
`!draft-diff <id>`	Show field-level diff for a draft
`!merge-draft <id>`	Commit draft to canonical memory
`!reject-draft <id>`	Reject a draft without saving
`!branch <name>`	View all drafts in a branch
`!merge-branch <name>`	Merge all drafts in a branch at once
`!reject-branch <name>`	Reject all drafts in a branch

Memory Links

Command	What it does
`!link <from_id> <to_id> [relation]`	Create a directed link between memories
`!unlink <from_id> <to_id>`	Remove a link
`!links <memory_id>`	Show all links for a memory

Knowledge Graph

Build structured knowledge from unstructured observations.

Command	What it does
`!triple <subject> \	<predicate> \	<object>`	Add a knowledge triple
`!triples [--subject x] [--predicate y]`	Query triples with filters
`!entities [--type t]`	List all entities
`!entity <id>`	Get entity with all connected triples
`!del-triple <id>`	Delete a triple
`!del-entity <id>`	Delete entity and cascade triples
`!graph [--relation r]`	View memory graph edges

Context Spaces (Multi-Agent Collaboration)

Isolated memory namespaces that can be shared between agents.

Command	What it does
`!space <name> [--description d]`	Create a context space
`!spaces`	List accessible spaces
`!space-memories <id> [query]`	List or search within a space
`!update-space <id> [--name n]`	Update space metadata
`!del-space <id>`	Delete a space (owner only)
`!share <space_id> <email>`	Share a space with another user
`!shared`	List spaces shared with you
`!accept <token>`	Accept a share invitation
`!revoke <token>`	Revoke a share

Replay (Time-Travel Debugging)

Scrub through the full history of your agent's memory.

Command	What it does
`!timeline [N]`	Full timeline of memory operations
`!snapshot <time>`	Reconstruct memory state at a point in time
`!lifecycle <id>`	Full biography of a single memory
`!replay <id>`	Complete history of a memory
`!replay-diff <t1> <t2>`	Diff memory state between two timestamps
`!recall-at <time> <query>`	What would search have returned in the past?
`!replay-drift <t1> <t2>`	Memory composition drift analysis

Audit & Rollback

Command	What it does
`!audit [N]`	Last N operations with SHA-256 hashes (default: 10)
`!audit-verify`	Verify cryptographic audit chain integrity
`!rollback <time>`	Rewind memory to a point in time ("1h", "2 days ago", ISO)
`!rollback-preview <time>`	Preview what rollback would do without executing
`!rollback-history`	List past rollback operations

Cortex (Autonomous Intelligence)

AI that watches your memory and generates insights automatically.

Command	What it does
`!cortex`	Cortex status and last run
`!cortex-run`	Manually trigger a Cortex cycle
`!insights`	List auto-generated insights
`!cortex-config`	View current configuration

Eval (Memory Health Scoring)

Quantify your agent's memory quality with weighted scoring.

Command	What it does
`!eval`	Run memory health evaluation (recall 40%, drift 30%, conflict 15%, staleness 15%)
`!eval-gate [threshold]`	CI gate — pass/fail on memory quality (default: 0.7)
`!eval-history`	Past evaluation scores with trends
`!eval-drift`	Detect memory drift over time
`!health`	Quick memory stats overview

Tracing (Execution Audit)

Track multi-step agent workflows with cryptographic verification.

Command	What it does
`!trace <name>`	Create a new execution trace
`!trace-step <id> <description> [--type THOUGHT\	ACTION\	OBSERVATION]`	Add a step
`!trace-complete <id>`	Finalize trace with RSA signature
`!trace-verify <id>`	Verify trace chain integrity

Control (Governed Actions)

Policy-evaluated agent actions with approval workflows.

Command	What it does
`!pending`	List pending approval requests
`!approve <id>`	Approve a pending action
`!policy`	View active security policies
`!actions [N]`	Recent action history

Overview

Command	What it does
`!status`	Memory usage, tier, and rollback count
`!dashboard`	Full dashboard with health score and activity
`!context`	Current memory context snapshot
`!stats`	Detailed memory statistics
`!help`	List all 60+ commands

Key Differentiators

Rollback: !rollback 1h restores memory to exactly one hour ago. No other memory skill supports this.
Audit trail: Every operation logged with SHA-256 hashes forming a tamper-proof chain. !audit-verify checks integrity.
Draft workflow: Stage memory changes in branches, review diffs, merge or reject — like git for memory.
Knowledge graph: Build structured triples from unstructured observations. Query relationships, not just content.
Context spaces: Isolated memory namespaces with sharing. Perfect for multi-agent architectures.
Governed actions: Policy-evaluated agent actions with Solo/Team/Enterprise approval workflows.
Time-travel: !recall-at 3pm "project status" shows what the agent would have found at 3pm yesterday.
Eval scoring: Quantified memory health with CI gate integration. Catch memory rot before it matters.
Execution tracing: Cryptographically signed audit trail for multi-step agent workflows.
Graceful degradation: If rate limits are hit or the API is unavailable, the agent continues working — it never crashes.

Tiers

Tier	Price	Memories	Rollbacks	Features
Free	$0	5,000	10/month	Memory, search, audit, rollback
Starter	$12/mo	50,000	100/month	+ Drafts, eval, conflict resolution
Pro	$39/mo	500,000	Unlimited	+ Cortex, replay, knowledge graph, tracing
Enterprise	$199/mo	Unlimited	Unlimited	+ Governed actions, team sharing, SSO

Configuration

Requires NOVYX_API_KEY environment variable. Get a free key at https://novyxlabs.com (5,000 memories, no credit card).

Options:

autoSave (default: true) — Automatically save messages
autoRecall (default: true) — Automatically recall context before each response
recallLimit (default: 5) — Max memories to recall per query

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明，方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用；具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

89.91%

按下载量换算1,496

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API；具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息，不托管安装包，不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果，不能写成本站确认安全。当前只有一个来源，正式发布前建议补源仓库或其他目录站核验。

来源信息

GitHub 仓库

github.com

/novyxlabs/novyx-memory

SKILL.md 来源

clawhub.ai

/novyxlabs/novyx-memory

继续浏览同类 Skills

更多研究检索 Skills（73,675）返回 Skills 目录

上一个 Skill

novu（novu 搜索）

novu 用于查找、检索和筛选相关信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

下一个 Skill

nowait-reasoning-optimizer（nowait 推理优化器）

nowait-reasoning-optimizer 用于查找、检索和筛选相关信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。