A silent, branch-aware knowledge graph memory system for AI agents that leverages git notes to persist context, decisions, and tasks across development sessions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install git-notes-memory
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install git-notes-memory using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is GitNotesMemory?
GitNotesMemory is a sophisticated memory layer designed specifically for AI coding agents to maintain high-level continuity without interrupting the developer's workflow. By utilizing the native git notes functionality, this tool creates a persistent knowledge graph that follows the repository's branch structure. This ensures that project-specific context, architectural decisions, and user preferences are always available to the agent, even after switching branches or starting new sessions. As a key utility among Openclaw Skills, it provides a decentralized and version-controlled method to manage agent state and long-term memory.
The system operates under strict silent protocols, meaning it handles background data storage and retrieval without announcing its actions to the user. This creates a seamless experience where the AI simply seems to remember everything relevant about the project, from the preferred database technology to specific coding style requirements established weeks prior.
GitNotesMemory Use Cases
- Maintaining continuity and context across multiple AI chat sessions within the same project.
- Tracking complex architectural decisions and their underlying rationales directly in the repository.
- Storing and retrieving user-specific coding preferences and project constraints automatically.
- Managing persistent task lists, blockers, and progress updates that survive branch checkouts.
- Providing a searchable knowledge base of past learnings and discovered bugs for future reference.
How GitNotesMemory Works
- The agent initializes the session by running a mandatory sync --start command to load the current branch's memory context.
- Throughout the interaction, the agent silently records decisions, preferences, and learnings using the remember command with defined importance levels.
- The system automatically performs entity extraction and tagging to build an indexed, searchable knowledge graph from the stored JSON data.
- When context is required, the agent executes topic-based queries or full-text searches to retrieve relevant historical data.
- Upon session completion, a summary is saved via the sync --end command to maintain a high-level overview of the session's impact.
- For multi-branch workflows, memories are merged using specialized branch commands to ensure knowledge parity across the codebase.
GitNotesMemory Setup
To integrate this tool into your workflow, ensure the memory script is available in your environment. Use the following commands to initialize and manage the memory state within a target repository:
# Initialize memory context at the start of a session
python3 memory.py -p /path/to/your/project sync --start
# Manually store a critical decision
python3 memory.py -p /path/to/your/project remember '{"decision": "Use PostgreSQL"}' -t database -i c
GitNotesMemory Data Schema & Taxonomy
GitNotesMemory organizes information using a structured taxonomy to ensure high retrieval accuracy. Data is stored in git notes under refs/notes/mem-[branch] and follows this schema:
| Attribute | Description |
|---|---|
| Importance | Classified as Critical (c), High (h), Normal (n), or Low (l) |
| Type | Auto-detected categories like decision, preference, learning, or task |
| Entities | Automatically extracted hashtags, quoted phrases, and key terms |
| Metadata | Includes creation date, update timestamps, access counts, and branch origin |
| Evolution | A log of how specific memories have changed over time via the evolve command |
GitNotesMemory Advanced Features
- Branch-Aware Isolation: Automatically isolates memory storage per git branch with inheritance and merge capabilities.
- Evolution Tracking: Allows agents to update or evolve existing memories to track shifting project requirements over time.
- Intelligent Entity Extraction: Parses content for hashtags, capitalized terms, and specific fields to build an automated index.
- Session Lifecycle Management: Dedicated start and end hooks to optimize context loading and maintenance tasks.
- Multi-Tier Retrieval: Supports quick topic lookups, full-text search, and detailed ID-based recall for flexible context injection into Openclaw Skills workflows.
SKILL.md
Loading
Related Openclaw Skills
UI Control Center
A specialized local management interface for maintaining agent reliability, dashboards, and workflow monitoring.
Tradebot Tuning
A precision skill designed to safely optimize trading bot parameters and diagnostic gates to restore tradability in shifting market regimes.
Tradebot Ops Monitoring & Recovery
A specialized operational skill for monitoring, validating, and managing the health and safety of automated trading bots.
Telegram Notify
A specialized notification skill for sending real-time Telegram alerts regarding trading activities and system health status.
Activated Thinker
A sophisticated cognitive framework that equips AI agents with behavioral modes and advanced thinking protocols to solve complex problems more effectively.
Intention Engine
A cognitive framework for AI agents to infer true user intentions and prevent misaligned or wasted work.
Featured*
