sachitrafa/YourMemory
by Various
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
MCP
sachitrafa/YourMemory
Added 1 June 2026
Overview
YourMemory is a Python library that implements agentic AI memory using Ebbinghaus forgetting curve decay to model how memories fade over time. It reports a 16 percentage point improvement in recall over Mem0 on the LoCoMo benchmark.
Best for
Best for
Developers building AI agents with persistent, time-decaying memory
Use cases
- Implementing long-term memory for AI agents
- Improving recall in conversational AI systems
- Creating context-aware agents with time-decaying memory
How to use
Install
pip install yourmemory Tested with
Claude Code, Claude Desktop, Cursor, Windsurf, Cline, ChatGPT
Notes
YourMemory is a Python library that implements agentic AI memory using Ebbinghaus forgetting curve decay to model how memories fade over time. It reports a 16 percentage point improvement in recall over Mem0 on the LoCoMo benchmark.
232 stars on GitHub. Last updated 2026-05-30.
Use cases
- Implementing long-term memory for AI agents
- Improving recall in conversational AI systems
- Creating context-aware agents with time-decaying memory
Pros
- Achieves +16pp recall over Mem0 on LoCoMo
- Uses Ebbinghaus forgetting curve for realistic memory decay
- Open-source Python library with 232 GitHub stars
Cons
- Benchmark limited to LoCoMo dataset
- Requires additional integration work for production systems
- Small community compared to Mem0
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Achieves +16pp recall over Mem0 on LoCoMo
- Uses Ebbinghaus forgetting curve for realistic memory decay
- Open-source Python library with 232 GitHub stars
Cons
- Benchmark limited to LoCoMo dataset
- Requires additional integration work for production systems
- Small community compared to Mem0
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.