hierarchical-memory

Manage and navigate a multi-layered, branch-based memory system. This skill helps organize complex agent context into Root, Domain, and Project layers to prevent context bloat. It includes a helper script `add_branch.py` which creates local markdown files and directories to structure your memory.

3,891 stars

Best use case

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

Manage and navigate a multi-layered, branch-based memory system. This skill helps organize complex agent context into Root, Domain, and Project layers to prevent context bloat. It includes a helper script `add_branch.py` which creates local markdown files and directories to structure your memory.

Teams using hierarchical-memory 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/hierarchical-memory/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/balkanblbn/hierarchical-memory/SKILL.md"

Manual Installation

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

How hierarchical-memory Compares

Feature / Agenthierarchical-memoryStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Manage and navigate a multi-layered, branch-based memory system. This skill helps organize complex agent context into Root, Domain, and Project layers to prevent context bloat. It includes a helper script `add_branch.py` which creates local markdown files and directories to structure your memory.

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

# Hierarchical Memory (Neural Branching)

This skill provides a structured method for managing long-term memory in a multi-layered, branched format to prevent context bloat and ensure high-fidelity recall.

## 🛡️ Security & Transparency
This skill includes a Python script `scripts/add_branch.py`. This script is used solely to:
1. Create directories in your `memory/` folder.
2. Create boilerplate markdown files for new memory branches.
3. Append links to these new files in your existing memory maps.
**It does not perform any network activity, access sensitive system files, or execute external code.**

## Memory Architecture

The memory system is organized into three primary layers:

1.  **Layer 1: Root Memory (`MEMORY.md`)**
    - The central nervous system.
    - Contains high-level context about the partnership, core missions, and global goals.
    - Acts as a map to all other memory layers.

2.  **Layer 2: Domain Memories (`memory/domains/*.md`)**
    - Specialized knowledge silos.
    - Examples: `coding.md`, `trading.md`, `social.md`, `research.md`.
    - Contains domain-specific philosophies, tech stacks, and project indices.

3.  **Layer 3: Project Memories (`memory/projects/*.md`)**
    - Deep-dive details for specific initiatives.
    - Examples: `hesapgaraj.md`, `clawguard.md`, `baa.md`.
    - Contains project status, to-dos, technical specs, and history.

## How to Use This Skill

### 1. Recalling Information
- Always start by searching `MEMORY.md`.
- Follow the "Map" links to the relevant Domain or Project file.
- Use `read` to load only the specific branch needed for the current task.

### 2. Adding New Information
- **New Fact about the Partnership:** Update `MEMORY.md`.
- **New Domain:** Create a new file in `memory/domains/` and link it from `MEMORY.md`.
- **New Project:** Create a new file in `memory/projects/` and link it from its primary Domain file.

### 3. Cross-Referencing
- If a project belongs to multiple domains (e.g., a trading bot that requires coding), link the Project file from both Domain files.

## Automation Tools

Use the provided scripts to maintain the hierarchy:
- `scripts/add_branch.py`: Automatically create a new domain or project file with the correct template and linking.

## Best Practices
- **Atomic Writes:** Keep project files focused only on that project.
- **Backlinks:** Every branch should have a "Back to Root" or "Back to Domain" link.
- **Pruning:** During heartbeats, review branches and remove obsolete information.
- **Why This Matters:** Every branch and major entry must include a "Significance" line (Why is this important?) to prevent "Zombie Memory" (useless data accumulation).
- **Recent Delta:** Maintain a `recent_delta.md` in each domain/project folder containing changes from the last 3-7 days for rapid context synchronization.

Related Skills

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

Memory

3891
from openclaw/skills

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

Memory Management

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

Triple-Layer Memory System

3880
from openclaw/skills

三层记忆系统 - 解决 AI Agent 长对话记忆丢失和上下文管理问题

Memory & Context Management

agent-memory-os

3891
from openclaw/skills

Stop agents from "forgetting, mixing projects, and rotting over time" by giving them a practical memory operating system: global memory, project memory, promotion rules, validation cases, and a maintenance loop.

benos-memory-core

3891
from openclaw/skills

Core runtime/volatile memory module for BenOS agent environment. Use to: store and retrieve active session state, open loops, decisions, and scratch notes at runtime.

elite-longterm-memory

3891
from openclaw/skills

Ultimate AI agent memory system with WAL protocol, vector search, git-notes, and cloud backup. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, and SMS.

memory-agent

3891
from openclaw/skills

维护用户审美偏好与创作历史,为其他 Agent 提供可复用的风格参考。当开始新任务或用户表达喜好时触发。

bamdra-memory-upgrade-operator

3891
from openclaw/skills

Safely install, uninstall, reinstall, or upgrade the Bamdra OpenClaw memory suite when stale config, existing plugin directories, or partial installs break normal `openclaw plugins install` flows.

agentmemory

3891
from openclaw/skills

End-to-end encrypted cloud memory for AI agents. 100GB free storage. Store memories, files, and secrets securely.

fsxmemory

3891
from openclaw/skills

Structured memory system for AI agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, and local semantic search.