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 alibaizhanov · MCP Server · ★ 195
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mengram safe to install? View the security audit →
Give your AI agents memory that actually learns [Website](ht
| Stars | 195 |
| Forks | 34 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 66.9954777498912/100 |
| Open Issues | 25 |
| Last Updated | 2026-09-16 |
| Created | 2026-02-10 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~16k |
These tools work well together with mengram for enhanced workflows:
Looking for a mengram alternative? If you're comparing mengram 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.
Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
The best-benchmarked open-source memory system for AI coding assistants
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work
Explore other popular mcp server tools:
mengram is Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.. It is categorized as a MCP Server with 195 GitHub stars.
mengram is primarily written in Python. It covers topics such as agent-memory, ai-agents, ai-memory.
You can find installation instructions and usage details in the mengram GitHub repository at github.com/alibaizhanov/mengram. The project has 195 stars and 34 forks, indicating an active community.
mengram is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to mengram on Agent Skills Hub include projectmem, Ori-Mnemos, YourMemory. 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: