vishalbanwari26/mnemos

Overview

Mnemos provides persistent memory for LLM agents using episodic, semantic, and procedural memory types. It includes auditable forgetting mechanisms and a benchmark that demonstrates recall over days. Written in Python.

Best for

Best for
Developers building Python-based LLM agents that need durable memory.

Use cases

• Give an LLM agent long-term recall across sessions
• Implement structured memory types for agent workflows
• Evaluate memory retention with a built-in benchmark

How to use

Tools exposed

• semantic_heavy
• recency_heavy

Tested with

Claude Code, ChatGPT

Notes

Mnemos provides persistent memory for LLM agents using episodic, semantic, and procedural memory types. It includes auditable forgetting mechanisms and a benchmark that demonstrates recall over days. Written in Python.

0 stars on GitHub. Last updated 2026-08-29. Licensed MIT.

Use cases

• Give an LLM agent long-term recall across sessions
• Implement structured memory types for agent workflows
• Evaluate memory retention with a built-in benchmark

Pros

• Supports three memory types for flexible storage
• Includes auditable forgetting for controlled memory decay
• Comes with a benchmark to verify recall over time

Cons

• Zero stars indicates minimal community adoption
• Unclear maintenance status or documentation depth
• Python-only, limiting language compatibility

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.