Skills openclaw-memories

Name: openclaw-memories
Author: openclaw

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.

install

source · Clone the upstream repo

git clone https://github.com/openclaw/skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/arosstale/openclaw-memory-2" ~/.claude/skills/openclaw-skills-openclaw-memories-3c27b8 && rm -rf "$T"

OpenClaw · Install into ~/.openclaw/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/arosstale/openclaw-memory-2" ~/.openclaw/skills/openclaw-skills-openclaw-memories-3c27b8 && rm -rf "$T"

manifest: skills/arosstale/openclaw-memory-2/SKILL.md

OpenClaw Memory System

Three components for agent memory:

ALMA — Evolves memory designs through mutation + evaluation (offline)
Observer — Extracts structured facts from conversations via LLM API (requires API key)
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

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-memory