Mengram
VerifiedHuman-like memory layer for AI agents with semantic, episodic, and procedural memory. Claude Code hooks (auto-save, auto-recall, cognitive profile). 29 MCP tools, knowledge graph, smart triggers, multi-user isolation. Python & JS SDKs.
Install
No auto-install command available for this server.
Check the GitHub repository for setup instructionsSafety Report
details
Authentication detected: env_api_key_py, env_required, bearer_check, connection_string, oauth
details
stdio transport — CORS not applicable
details
Rate limiting detected: rate_limit_middleware, throttle, requests_per
details
2 deps with known issues (medium)
details
2 deps with known issues (medium)
details
No dangerous code patterns detected
details
License: Apache-2.0
details
Last commit 1 days ago
Frequently Asked Questions
What is Mengram?
Human-like memory layer for AI agents with semantic, episodic, and procedural memory. Claude Code hooks (auto-save, auto-recall, cognitive profile). 29 MCP tools, knowledge graph, smart triggers, multi-user isolation. Python & JS SDKs.
Is Mengram safe to use?
Yes, Mengram has passed our 8-point security audit and is rated Verified. All checks including authentication, dependency audit, and known CVE scan passed.
What are alternatives to Mengram?
Similar MCP servers include Context7, Cognee, Hindsight. Each serves a similar purpose but may differ in features, language, and compatibility.
Similar MCP Servers
Context7
VerifiedUp-to-date code documentation for LLMs and AI code editors.
Cognee
CautionMemory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources
Hindsight
UntestedHindsight: Agent Memory That Works Like Human Memory - Built for AI Agents to manage Long Term Memory