← Back to Skills Marketplace
xuyucheneureka

Autobiographical Memory

by xuyuchen · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
25
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install autobiographical-memory
Description
Structured personal memory system that enables agents to persist, consolidate, and recall episodic and semantic memories across sessions. Use when: (1) recor...
README (SKILL.md)

Autobiographical Memory

Core Concepts

Memory has two complementary layers:

Layer File What it stores
Episodic memory/YYYY-MM-DD.md Raw daily events, conversations, decisions, observations
Semantic MEMORY.md Curated knowledge: user preferences, facts, lessons, identity

The memory lifecycle: Capture → Consolidate → Recall → Review

Quick Start

# Recording an event (episodic)
Append to `memory/YYYY-MM-DD.md`:
- Met with [person] about [topic]. Decision: [outcome].
- User prefers [preference]. Updated MEMORY.md.

# Recalling before responding
1. Run `memory_search` with relevant keywords
2. If results are thin, read recent `memory/YYYY-MM-DD.md` files
3. Check `MEMORY.md` for long-term facts

# Consolidating (periodic maintenance)
1. Read recent daily files (last 7-30 days)
2. Extract significant items → update MEMORY.md
3. Remove stale entries from MEMORY.md

Episodic Memory — Daily Notes

What to Record

Always write to daily notes for:

  • Decisions with rationale: "Chose X over Y because Z"
  • User preferences discovered implicitly or explicitly
  • Important conversations — summary, not transcript
  • Mistakes & lessons — what went wrong, what to do differently
  • Project milestones — what was done, what's blocked
  • Identity changes — if SOUL.md, USER.md, or other self-files changed

What to Skip

  • Routine operations ("checked email, nothing new")
  • Transient states ("feeling tired")
  • Content better stored elsewhere (code snippets in projects, API keys in config)
  • Something the user explicitly said doesn't matter

Format Convention

## Events
- [event description]

## Decisions
- [decision + rationale]

## Observations
- [insights or patterns noticed]

## Notes
- [anything else worth remembering]

Semantic Memory — MEMORY.md

Structure

## User Preferences
- Directly stated preferences without inference

## Project Context
- Active projects and their status

## Relationships & People
- Key people, roles, context

## Technical Environment
- Tools, config, quirks discovered

## Lessons Learned
- Mistakes to avoid, patterns that work

When to Update MEMORY.md

  • User states a clear preference
  • A project direction is set
  • A mistake teaches a lesson worth preserving
  • Every few days during heartbeat: consolidate from daily notes

When to Remove from MEMORY.md

  • Project is done / abandoned
  • Preference was explicitly reversed
  • Information is now obvious context (e.g. "user speaks Chinese" — that's already in USER.md)
  • Stale for >3 months without reference

Consolidation Workflow

Suitable for heartbeat routines. Do this every 3-7 days:

1. List memory/*.md, sort by date (newest first)
2. Read files since last consolidation
3. For each significant item:
   a. Is it already in MEMORY.md? → Skip or update
   b. Is it transient? → Skip (leave in daily note)
   c. Is it important? → Add to MEMORY.md
4. Read MEMORY.md for stale entries → remove or archive
5. Write updated MEMORY.md

Recall Strategy

Before answering questions about prior work, people, preferences, or context:

  1. Search first: memory_search(query="relevant terms") — this searches both daily notes and MEMORY.md
  2. Narrow scope: If search returns weak results, try multiple query phrasings
  3. Deep dive: For specific periods, memory_get(path="memory/YYYY-MM-DD.md") to read raw daily notes
  4. Cross-reference: Check USER.md, SOUL.md, TOOLS.md for identity/preference info

When Recall Fails

  • Say clearly "I checked my records and don't have information about that"
  • Don't fabricate memories
  • If the user says "don't you remember? I told you X" — apologize and record it properly this time

The Forgetting Curve

Not everything needs to persist. Use these filters:

  • Keep in daily notes: Everything noteworthy for 30-90 days
  • Promote to MEMORY.md: Only what's likely to be needed again
  • Delete/archive: What's clearly obsolete after review

References

Scripts

  • scripts/consolidate.py — Scan recent daily notes and suggest MEMORY.md updates
  • scripts/stats.py — Memory file statistics (sizes, dates, coverage)
Usage Guidance
Install only if you want the agent to maintain long-term local memories. Periodically review MEMORY.md and memory/*.md, avoid saving secrets or highly sensitive personal details, and inspect the optional Python scripts locally before running them.
Capability Analysis
Type: OpenClaw Skill Name: autobiographical-memory Version: 1.0.0 The 'autobiographical-memory' skill is a well-structured system for managing an AI agent's long-term memory through local Markdown files. The included Python scripts (scripts/consolidate.py and scripts/stats.py) are simple utilities for scanning daily notes and generating statistics, using only standard libraries and local file access within the expected workspace. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
The stated purpose matches the capability: it is explicitly a cross-session memory system for daily notes and MEMORY.md. This is sensitive by design because it stores user preferences, project context, relationships, lessons, and identity-related information.
Instruction Scope
The instructions are mostly scoped to memory files and include skip/retention guidance, but they also encourage periodic heartbeat consolidation and recall before answering, so users should understand the agent may reuse stored context proactively.
Install Mechanism
There is no install spec, dependency install, or auto-run step. Two local helper scripts are included; one displayed consolidate.py artifact appears neutralized/incomplete after hidden-comment removal, so users should inspect the local script before running it.
Credentials
Local reads and writes of memory files are proportionate to the skill purpose, and there is no evidence of network exfiltration or credential use. The skill also references USER.md, SOUL.md, TOOLS.md, IDENTITY.md, and AGENTS.md as context files, which may contain sensitive or behavior-shaping information.
Persistence & Privilege
Persistence is the core feature and is clearly disclosed. The skill can lead to long-lived stored memories and edits/removals during consolidation, so users should review what is saved and keep backups if needed.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install autobiographical-memory
  3. After installation, invoke the skill by name or use /autobiographical-memory
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: episodic + semantic memory system with consolidation scripts and recall patterns
Metadata
Slug autobiographical-memory
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Autobiographical Memory?

Structured personal memory system that enables agents to persist, consolidate, and recall episodic and semantic memories across sessions. Use when: (1) recor... It is an AI Agent Skill for Claude Code / OpenClaw, with 25 downloads so far.

How do I install Autobiographical Memory?

Run "/install autobiographical-memory" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Autobiographical Memory free?

Yes, Autobiographical Memory is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Autobiographical Memory support?

Autobiographical Memory is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Autobiographical Memory?

It is built and maintained by xuyuchen (@xuyucheneureka); the current version is v1.0.0.

💬 Comments