openclaw-memory-stack

Total recall, 90% fewer tokens. The best OpenClaw memory plugin — 5-engine local search, structured fact extraction, smart dedup, cross-agent sharing, and self-healing. Replace native memory with something that actually remembers. No cloud API, no subscription.

3,891 stars

Best use case

openclaw-memory-stack is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Total recall, 90% fewer tokens. The best OpenClaw memory plugin — 5-engine local search, structured fact extraction, smart dedup, cross-agent sharing, and self-healing. Replace native memory with something that actually remembers. No cloud API, no subscription.

Teams using openclaw-memory-stack should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/openclaw-memory-stack/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/apptah/openclaw-memory-stack/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/openclaw-memory-stack/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How openclaw-memory-stack Compares

Feature / Agentopenclaw-memory-stackStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Total recall, 90% fewer tokens. The best OpenClaw memory plugin — 5-engine local search, structured fact extraction, smart dedup, cross-agent sharing, and self-healing. Replace native memory with something that actually remembers. No cloud API, no subscription.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# OpenClaw Memory Stack

**Total recall. 90% fewer tokens.**

Your agent forgets past decisions and burns tokens re-reading the same context. Memory Stack runs 5 search engines locally, returns only what matters, and never loses a fact.

> **$49 one-time purchase.** No subscription, no cloud API costs.
> All search and storage runs on your machine. One-time license activation requires internet.
> Buy at [openclaw-memory.apptah.com](https://openclaw-memory.apptah.com)

## Architecture

```
┌──────────────────────────────────────────────────────────────┐
│                  OPENCLAW MEMORY STACK                        │
├──────────────────────────────────────────────────────────────┤
│                                                              │
│  SEARCH PIPELINE (runs on every conversation turn)           │
│                                                              │
│  ┌──────┐ ┌──────┐ ┌──────┐ ┌──────┐ ┌──────┐               │
│  │  E1  │ │  E2  │ │  E3  │ │  E4  │ │  E5  │               │
│  │ Full │ │Vector│ │ DAG  │ │ Fact │ │  MD  │               │
│  │ Text │ │Search│ │Compr.│ │Store │ │Files │               │
│  └──┬───┘ └──┬───┘ └──┬───┘ └──┬───┘ └──┬───┘               │
│     └────────┴────────┴────────┴────────┘                    │
│                        │                                     │
│                        ▼                                     │
│               ┌──────────────┐                               │
│               │ Result Fusion│                               │
│               │ + Reranking  │                               │
│               └──────────────┘                               │
│                        │                                     │
│              ┌─────────┼─────────┐                           │
│              ▼         ▼         ▼                           │
│          ┌──────┐  ┌──────┐  ┌──────┐                        │
│          │  L0  │  │  L1  │  │  L2  │  Token Budget           │
│          │~100t │  │~800t │  │ full │  Control                │
│          └──────┘  └──────┘  └──────┘                        │
│                                                              │
│  CAPTURE (runs after every conversation turn)                │
│                                                              │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐        │
│  │    Fact       │  │   Entity     │  │   Dedup &    │        │
│  │  Extraction   │  │  Tracking    │  │  Supersede   │        │
│  │  (8 types)    │  │  (queryable) │  │  (3-level)   │        │
│  └──────────────┘  └──────────────┘  └──────────────┘        │
│                                                              │
│  CROSS-AGENT SHARING                                         │
│                                                              │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐        │
│  │   CLI API    │  │  Drop Zone   │  │   Unified    │        │
│  │ query/add/   │  │  ~/.openclaw │  │   Global     │        │
│  │   recent     │  │  /external/  │  │   Memory     │        │
│  └──────────────┘  └──────────────┘  └──────────────┘        │
│         ▲                 ▲                 ▲                 │
│  Claude Code       Cursor / Windsurf    Any MCP client       │
│                                                              │
│  SELF-HEALING MAINTENANCE (24h cycle, zero config)           │
│                                                              │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐        │
│  │  Auto-Init   │  │   Graceful   │  │   Health     │        │
│  │  workspace   │  │   Fallback   │  │   Monitor    │        │
│  │  + indexing   │  │  FTS5-only   │  │  + alerting  │        │
│  └──────────────┘  └──────────────┘  └──────────────┘        │
│                                                              │
└──────────────────────────────────────────────────────────────┘
```

## Built-in Code Search

Find function names, variable names, or any pattern across your entire memory — instantly. No extra tools needed, works offline, gets faster the more you use it.

## 5-Engine Search

Five engines search in parallel on every conversation turn:

| Engine | What it does |
|--------|-------------|
| Full-text | Keyword matching with relevance ranking |
| Vector | Semantic search — understands meaning, not just words |
| Compressed history | Conversation DAG with drill-down |
| Fact store | Structured facts — decisions, deadlines, requirements |
| Markdown | Scans memory files directly |

Results are merged with rank fusion, deduplicated, reranked for diversity, and scored with time decay.

## 3-Tier Token Control

Every wasted token is money burned. Memory Stack eliminates the waste.

| Tier | Tokens | When used |
|------|--------|-----------|
| L0 | ~100 | Auto-recall every turn — minimal cost |
| L1 | ~800 | On-demand search summary |
| L2 | full | Full content on request |

## Structured Fact Memory

Extracts 8 fact types automatically: decisions, deadlines, requirements, entities, preferences, workflows, relationships, corrections.

- Structured key/value storage with confidence scores
- Negation-aware — "We will NOT use MongoDB" preserved correctly
- Automatic supersede — when a fact changes, old version archived, new one takes over

## Smart Dedup & Conflict Resolution

- 3-level write-time dedup: exact match, normalized text, structured key match
- Full audit trail via archive table
- Removes duplicates before sending — you never pay twice for the same memory

## Cross-Agent Memory Sharing

Works across Claude Code, Cursor, Windsurf, and any MCP-compatible client.

- CLI commands: `openclaw-memory query/add/recent` — any tool can read/write facts
- Drop zone: drop `.md` files into `~/.openclaw/memory/external/` — auto-ingested, no duplicates
- Unified global memory under `~/.openclaw/memory/` — your memory follows you across workspaces

## Self-Healing Maintenance

Zero maintenance. The plugin takes care of itself.

- Auto-init: detects workspace, creates search index, schedules embedding — no manual setup
- Graceful fallback: if vector search unavailable, runs in keyword-only mode — always functional
- 24h maintenance cycle: rebuilds index on corruption, archives stale facts, alerts on health issues

## OpenClaw Native vs Memory Stack

| | Native | Memory Stack |
|---|--------|-------------|
| Search engines | 2 | 5 (parallel, fused) |
| Token efficiency | Full text every time | Up to 90% fewer |
| Output tiers | Full text | 3 tiers (~100 / ~800 / full) |
| Fact extraction | No | 8 types, structured, negation-aware |
| Duplicate handling | Can pay twice | 3-level dedup, auto-supersede |
| Entity tracking | No | Yes, queryable |
| Cross-agent | No | CLI + drop zone, works with any tool |
| Memory across projects | Separate per workspace | Unified global memory — follows you everywhere |
| Self-healing | No | Auto-maintain, auto-fallback |
| Runs locally | Yes | Yes — all search local, one-time activation online |

## Install

```bash
npx clawhub@latest package install openclaw-memory-stack
```

Then run `./install.sh --key=oc-starter-xxxxxxxxxxxx` to activate with your license key.

Purchase at [openclaw-memory.apptah.com](https://openclaw-memory.apptah.com).

Runs on macOS, Linux, and Windows (WSL2). Requires bash, python3, and OpenClaw 2026.3.2 or later. Bun is optional (enables QMD vector search).

## What the installer does

The included `install.sh` performs the following actions:

- **Files**: Copies plugin and backend files to `~/.openclaw/memory-stack/`, registers plugin in `~/.openclaw/extensions/openclaw-memory-stack/`, updates `~/.openclaw/openclaw.json`
- **License activation**: Sends your license key and a device fingerprint (SHA-256 of machine ID) to `openclaw-api.apptah.com/api/activate` — one-time, at install
- **Periodic verification**: Re-verifies license every 7 days (background, non-blocking). Sends only `{ key, device_id }`. 10-day offline grace period
- **Upgrade downloads**: `install.sh --upgrade` downloads new versions from `openclaw-api.apptah.com` with mandatory SHA-256 checksum verification
- **No telemetry**: No usage data, memory content, or analytics are ever sent. Only license key and device ID leave your machine
- **Optional LLM**: `OPENCLAW_LLM_API_KEY` / `OPENAI_API_KEY` env vars are optional, used only for LLM-powered fact extraction. If not set, falls back to local Ollama/MLX. These keys are sent only to the endpoint you configure (default: api.openai.com), never to our servers

All search and storage runs entirely on your machine.

## License

Proprietary. $49 one-time purchase. All features included. No subscription.
See full terms at [openclaw-memory.apptah.com](https://openclaw-memory.apptah.com).

## Support

Questions or issues? Contact us at **support@apptah.com**.

Related Skills

openclaw-youtube

3891
from openclaw/skills

YouTube SERP Scout for agents. Search top-ranking videos, channels, and trends for content research and competitor tracking.

Content & Documentation

openclaw-search

3891
from openclaw/skills

Intelligent search for agents. Multi-source retrieval with confidence scoring - web, academic, and Tavily in one unified API.

Data & Research

openclaw-media-gen

3891
from openclaw/skills

Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key.

Content & Documentation

OpenClaw Mastery — The Complete Agent Engineering & Operations System

3891
from openclaw/skills

> Built by AfrexAI — the team that runs 9+ production agents 24/7 on OpenClaw.

DevOps & Infrastructure

Agent Memory Architecture

3891
from openclaw/skills

Complete zero-dependency memory system for AI agents — file-based architecture, daily notes, long-term curation, context management, heartbeat integration, and memory hygiene. No APIs, no databases, no external tools. Works with any agent framework.

memory-cache

3891
from openclaw/skills

High-performance temporary storage system using Redis. Supports namespaced keys (mema:*), TTL management, and session context caching. Use for: (1) Saving agent state, (2) Caching API results, (3) Sharing data between sub-agents.

General Utilities

openclaw-safe-change-flow

3891
from openclaw/skills

Safe OpenClaw config change workflow with backup, minimal edits, validation, health checks, and rollback. Single-instance first; secondary instance optional.

DevOps & Infrastructure

jqopenclaw-node-invoker

3891
from openclaw/skills

统一通过 Gateway 的 node.invoke 调用 JQOpenClawNode 能力(file.read、file.write、process.exec、process.manage、system.run、process.which、system.info、system.screenshot、system.notify、system.clipboard、system.input、node.selfUpdate)。当用户需要远程文件读写、文件移动/删除、目录创建/删除、进程管理(列表/搜索/终止)、远程进程执行、命令可执行性探测、系统信息采集、截图采集、系统弹窗、系统剪贴板读写、输入控制(鼠标/键盘)、节点自更新、节点命令可用性排查或修复 node.invoke 参数错误时使用。

DevOps & Infrastructure

Memory

3891
from openclaw/skills

Infinite organized memory that complements your agent's built-in memory with unlimited categorized storage.

Memory Management

openclaw-stock-skill

3891
from openclaw/skills

使用 data.diemeng.chat 提供的接口查询股票日线、分钟线、财务指标等数据,支持 A 股等市场。

Data & Research

openclaw-whatsapp

3891
from openclaw/skills

WhatsApp bridge for OpenClaw — send/receive messages, auto-reply agents, QR pairing, message search, contact sync

Workflow & Productivity

auto-memory

3891
from openclaw/skills

Indestructible agent memory — permanently stored, never lost. Save decisions, identity, and context as a memory chain on the Autonomys Network. Rebuild your full history from a single CID, even after total state loss.

AI Persistence & Memory