openclaw-memories
Agent memory with ALMA meta-learning, LLM fact extraction, and full-text search. Observer calls remote LLM APIs (OpenAI/Anthropic/Gemini). ALMA and Indexer work offline.
Best use case
openclaw-memories is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Agent memory with ALMA meta-learning, LLM fact extraction, and full-text search. Observer calls remote LLM APIs (OpenAI/Anthropic/Gemini). ALMA and Indexer work offline.
Teams using openclaw-memories 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/openclaw-memory-2/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How openclaw-memories Compares
| Feature / Agent | openclaw-memories | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Agent memory with ALMA meta-learning, LLM fact extraction, and full-text search. Observer calls remote LLM APIs (OpenAI/Anthropic/Gemini). ALMA and Indexer work offline.
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
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# OpenClaw Memory System
Three components for agent memory:
1. **ALMA** — Evolves memory designs through mutation + evaluation (offline)
2. **Observer** — Extracts structured facts from conversations via LLM API (requires API key)
3. **Indexer** — Full-text search over workspace Markdown files (offline)
## Environment Variables
Observer requires one of:
- `OPENAI_API_KEY`
- `ANTHROPIC_API_KEY`
- Or pass `apiKey` in config
ALMA and Indexer require no keys or network access.
## How It Works
### ALMA (Algorithm Learning via Meta-learning Agents)
Proposes memory system designs, evaluates them, keeps the best. Uses gaussian mutation and simulated annealing to explore the design space.
```
alma.propose() → design
alma.evaluate(design.id, metrics) → score
alma.best() → top design
alma.top(5) → leaderboard
```
### Observer
Sends conversation history to an LLM, gets back structured facts:
- Kind: world fact / biographical / opinion / observation
- Priority: high / medium / low
- Entities: mentioned people/places
- Confidence: 0.0–1.0 for opinions
Fails gracefully — returns empty array if LLM is unavailable.
### Indexer
Chunks workspace Markdown files and indexes them for search:
- `MEMORY.md` — core facts
- `memory/YYYY-MM-DD.md` — daily logs
- `bank/entities/*.md` — entity summaries
- `bank/opinions.md` — beliefs with confidence
```
indexer.index() → count of chunks indexed
indexer.search('query') → ranked results
indexer.rebuild() → re-index from scratch
```
## Install
```bash
npm install @artale/openclaw-memory
```
## Limitations
- Indexer uses an in-memory mock database, not real SQLite FTS5. Search works but ranking is simplified.
- Observer calls remote APIs — not offline. Only ALMA and Indexer work without network.
- No dashboard — removed in v2 for simplicity.
## Source
5 files, 578 lines, 0 runtime dependencies.
https://github.com/arosstale/openclaw-memoryRelated Skills
openclaw-youtube
YouTube SERP Scout for agents. Search top-ranking videos, channels, and trends for content research and competitor tracking.
openclaw-search
Intelligent search for agents. Multi-source retrieval with confidence scoring - web, academic, and Tavily in one unified API.
openclaw-media-gen
Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key.
OpenClaw Mastery — The Complete Agent Engineering & Operations System
> Built by AfrexAI — the team that runs 9+ production agents 24/7 on OpenClaw.
openclaw-safe-change-flow
Safe OpenClaw config change workflow with backup, minimal edits, validation, health checks, and rollback. Single-instance first; secondary instance optional.
jqopenclaw-node-invoker
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。
openclaw-stock-skill
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。
openclaw-whatsapp
WhatsApp bridge for OpenClaw — send/receive messages, auto-reply agents, QR pairing, message search, contact sync
polymarket-openclaw-trader
Reusable Polymarket + OpenClaw trading operations skill for any workspace. Use when the user needs to set up, run, tune, monitor, and deploy an automated Polymarket trading project (paper/live), including env configuration, risk controls, reporting, and dashboard operations.
openclaw-version-monitor
监控 OpenClaw GitHub 版本更新，获取最新版本发布说明，翻译成中文， 并推送到 Telegram 和 Feishu。用于：(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明
openclaw-essesseff
Interact with the essesseff DevOps platform — call the essesseff Public API (templates, organizations, apps, deployments, images, image lifecycle, environments, retention policies, packages) and automate app creation and Argo CD setup using the essesseff onboarding utility. Use when the user wants to create essesseff apps, manage deployments, promote images through the DEV→QA→STAGING→PROD lifecycle, configure Argo CD environments, manage retention policies, or run the essesseff-onboard.sh script.
Agent World Protocol — OpenClaw Skill
Connect to the Agent World Protocol (AWP) — a persistent open world where AI agents trade real SOL tokens, build structures, claim land, form guilds, complete bounties, fight for territory, and interact with the real economy.