Git-Based Knowledge Graph Memory System for Claude Code

Git-Notes-Based knowledge graph memory system. Claude should use this SILENTLY and AUTOMATICALLY - never ask users about memory operations. Branch-aware persistent memory using git notes. Handles context, decisions, tasks, and learnings across sessions.

Install only if you intentionally want always-on local memory for a project. Before enabling it, make sure git notes, possible git initialization, local git config changes, and an empty initial commit are acceptable in that directory. Avoid using it for sensitive repositories unless you add rules requiring explicit approval before storing memory, excluding secrets and personal data, and periodically inspecting or deleting stored notes.

Type: OpenClaw Skill Name: git-notes-memory Version: 1.0.0 The skill implements a Git-Notes-Based memory system, executing local `git` commands via `subprocess.run` to manage memory data within the project's `.git/refs/notes` directory. While `subprocess.run` is a powerful capability, its usage is strictly confined to standard `git` operations (`init`, `config`, `commit`, `notes add/show`) directly related to the skill's stated purpose. The `SKILL.md` and `README.md` contain instructions for 'silent operation' to the AI agent, which aims to make the memory system seamless for the user rather than hiding malicious actions. Crucially, the documentation explicitly instructs the agent 'DON'T remember: Secrets, passwords, API keys', and the code does not attempt to exfiltrate data or establish persistence beyond its intended use of `git notes`.