forgetful — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

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 ScottRBK · MCP Server · ★ 300

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is forgetful safe to install? View the security audit →

About forgetful

Forgetful Forgetful is a storage and retrieval tool for AI Agents. Designed as a Model Context Protocol (MCP) server built using the FastMCP framework. Once connected to this service, MCP clients such as Coding Agents, Chat Bots or your own custom built Agents can store and retrieve information from the same knowledge base. Table of Contents Overview Features Quick Start Some Examples How It Works Configuration Documentation Contributing License Overview A lot of us are using AI Agents now, especially in the realm of software development. The pace at which work and decisions are made can make it difficult for you to keep up from a notes and context persistence perspective. So if you are following something like the [BMAD Method](https://github.com/bmad-

ai-agentsai-memoryclaude-codelong-term-memomcpmemory

Quick Facts

Stars300
Forks27
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score67.55872433423/100
Open Issues4
Last Updated2026-09-22
Created2025-10-20
Platformsclaude-code, mcp, python
Est. Tokens~17k

forgetful alternative? Top 6 similar tools

Looking for a forgetful alternative? If you're comparing forgetful 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.

  • vestige by samvallad33 · ⭐ 628

    Cognitive Deterministic Memory Security OS for Agentic AI. Deterministic root-cause retrieval that reaches bac

  • omega-memory by omega-memory · ⭐ 218

    Persistent memory for AI coding agents

  • mem0-mcp-selfhosted by elvismdev · ⭐ 106

    Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j +

  • nocturne_memory by Dataojitori · ⭐ 1.4k

    A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and

  • Wax by christopherkarani · ⭐ 799

    Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple S

  • ai-maestro by 23blocks-OS · ⭐ 791

    AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is forgetful?

forgetful is Opensource Memory for Agents. It is categorized as a MCP Server with 300 GitHub stars.

What programming language is forgetful written in?

forgetful is primarily written in Python. It covers topics such as ai-agents, ai-memory, claude-code.

How do I install or use forgetful?

You can find installation instructions and usage details in the forgetful GitHub repository at github.com/ScottRBK/forgetful. The project has 300 stars and 27 forks, indicating an active community.

What license does forgetful use?

forgetful is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to forgetful?

The top alternatives to forgetful on Agent Skills Hub include vestige, omega-memory, mem0-mcp-selfhosted. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools