Mengram AI Memory API: Semantic, Episodic, and Procedural Memory Extraction
By
Ali Baizhanov
More crust than filling. Mostly air.
Summary
Mengram is an AI memory API that automatically extracts three types of memory: semantic (facts), episodic (events), and procedural (learned workflows) through a single API call. The key feature is that when an AI agent completes a task, Mengram saves the steps so the agent can recall the optimal path with success/failure tracking on subsequent attempts. It integrates with popular AI frameworks like Claude (MCP), LangChain, CrewAI, and OpenClaw, and is free and open-source under Apache 2.0 license.
Key quotes
· 5 pulledAI memory API with 3 types: semantic (facts), episodic (events), and procedural (learned workflows)
One API call extracts all three automatically
Killer feature: your agent completes a task → Mengram saves the steps → next time it already knows the optimal path with success/failure tracking
Works with Claude (MCP), LangChain, CrewAI, OpenClaw
Free, open-source, Apache 2.0
You might also wanna read
Robot Memory System Enables AI Robots to Learn from Past Experiences
Robot Memory (robotmem) is a persistent memory system for AI robots that enables robots to learn from past experiences. The system stores ep
github.com·2mo ago
YourMemory: Open-source persistent memory layer for AI agents using Ebbinghaus forgetting curve
YourMemory is an open-source persistent memory layer for AI agents that implements Ebbinghaus forgetting curve decay to mimic human memory.
github.com·1mo ago
AI agent memory libraries borrow cognitive science terms without the underlying architecture
This article critically examines how AI agent memory libraries borrow terminology from cognitive science (episodic, semantic, procedural mem
brgsk.xyz·5d ago
DiffMem: Git-Based Differential Memory System for AI Agents
DiffMem is a proof-of-concept project that implements a git-based memory storage system for AI agents and conversational systems. It uses Ma
github.com·9mo ago