LycheeMem/LycheeMem — Lightweight Long-Term Memory for LLM Agents.

Description and use

LycheeMem is an open‑source, lightweight long‑term memory system designed specifically for large language model (LLM) agents. It provides a simple, extensible backend that lets agents store, retrieve, and update contextual information across interactions, enabling more coherent and persistent behavior in autonomous workflows. Ideal for orchestration pipelines and AI/ML applications, LycheeMem offers a minimal‑dependency solution for developers who need scalable, persistent memory without heavyweight infrastructure.

Problem

LycheeMem/LycheeMem helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

Lightweight Long-Term Memory for LLM Agents.

Source