No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by WhenMoon-afk · MCP Server · ★ 69
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-memory-mcp safe to install? View the security audit →
Claude Memory MCP Local-first memory database and continuity journal for MCP clients. is a basic local memory database and lightweight continuity journal for AI workflows. It helps an agent resume work coherently by saving compact continuity artifacts, tracking key decisions and state, and returning only the level of detail requested instead of dumping a full archive into context. Use it when you want a local, private continuity store that works across MCP clients and shell scripts. It is intentionally boring infrastructure: SQLite on your machine, one MCP tool, one CLI, explicit import/export, and no hosted service. Published package: Supported CLI command: Storage: local SQLite only Privacy: no telemetry, no network calls, no cloud service Why v3? The last npm-published v2 release was . v3 is an intentional product reset: the older identity-oriented , , and surface is removed, and the project is now focused on simple local continuity. Client-native memory features are useful when your client provides them, but they are usually client-owned. is for a different job: a portable, inspectable, local, private
| Stars | 69 |
| Forks | 14 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 72.9084734827803/100 |
| Last Updated | 2026-09-26 |
| Created | 2025-03-25 |
| Platforms | claude-code, codex, mcp, node |
| Est. Tokens | ~16k |
Looking for a claude-memory-mcp alternative? If you're comparing claude-memory-mcp with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Evidence-first search for AI agents / Claude Code & Codex & Pi & OMP & kimi & mcp
Context-efficient project search and bounded code analysis for Claude Code & Codex & Pi & OMP & kimi ....and r
Persistent memory for AI coding agents
MCP server for free Google AI Mode search with citations. Query optimization, CAPTCHA handling, multi-agent su
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Explore other popular mcp server tools:
claude-memory-mcp is Local citation-backed recall for Pi, OMP, Claude Code, Codex, and ChatGPT history.. It is categorized as a MCP Server with 69 GitHub stars.
claude-memory-mcp is primarily written in TypeScript. It covers topics such as ai-memory, chatgpt, claude-code.
You can find installation instructions and usage details in the claude-memory-mcp GitHub repository at github.com/WhenMoon-afk/claude-memory-mcp. The project has 69 stars and 14 forks, indicating an active community.
claude-memory-mcp is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to claude-memory-mcp on Agent Skills Hub include maestro, sift-light, baoer_signal_grep. 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: