YourMemory: Self-Pruning MCP Memory Tool Reduces Token Waste by 84%
By
sachit mishra
Worth a glance, not a chew.
Summary
YourMemory is a tool that reduces token waste by 84% through self-pruning memory management for AI agents. It applies the Ebbinghaus forgetting curve to prune irrelevant context while maintaining 52% recall, features a graph engine to find forgotten information, and operates 100% locally.
Key quotes
· 5 pulledMost agents are either amnesiacs or 'hoarders' that choke on stale context and break their own reasoning.
Using the Ebbinghaus curve, it prunes the junk so only the important stuff sticks.
-84% Token Waste: Leaner context, sharper reasoning.
52% Recall: (LoCoMo benchmarked).
100% Local.
You might also wanna read
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
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
Context Mode: MCP Server Reduces Claude Code Context Consumption by 98%
Context Mode is an MCP (Model Context Protocol) server that addresses the problem of context window consumption in AI coding assistants like
mksg.lu·3mo ago