by anshulforyou · Claude Skill · ★ 108
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no telemetry.
| Stars | 108 |
| Forks | 12 |
| Language | Shell |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 53.4984483268/100 |
| Open Issues | 11 |
| Last Updated | 2026-07-30 |
| Created | 2026-07-07 |
| Platforms | claude-code, cli |
| Est. Tokens | ~10k |
These tools work well together with grandma for enhanced workflows:
Looking for a grandma alternative? If you're comparing grandma with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It
📜 An MCP server for conversation history search and retrieval in Claude Code
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Persistent cross-session memory for Claude & AI agents. Self-host on Redis/Valkey, or use the managed SaaS at
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Claude Code hooks that auto-switch model tier based on task complexity
Explore other popular claude skill tools:
grandma is A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no telemetry.. It is categorized as a Claude Skill with 108 GitHub stars.
grandma is primarily written in Shell. It covers topics such as ai, ai-memory, anthropic.
You can find installation instructions and usage details in the grandma GitHub repository at github.com/anshulforyou/grandma. The project has 108 stars and 12 forks, indicating an active community.
grandma is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to grandma on Agent Skills Hub include Grov, claude-historian-mcp, claude-code-open. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: