Memory Layer Python Packages

dhee

World memory for AI agents

mneno

A memory layer for AI agents and applications that does more than just “remember”; it preserves useful, compact, and verifiable context over time.

groundmemory

Persistent, semantic memory for AI agents - mcp-native, local-first, framework-agnostic, production-ready

atomicmemory-langflow

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

atomicmemory-hermes

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

engram-memory

World memory for AI agents

devcd

Local-first Developer Context Daemon with explicit state, memory, and policy layers.

memory-garden

Local-first memory layer and memory skill for AI agents that mitigates long-context attention dilution with traceable retrieval, policy-aware memory lifecycle, and auditable forget. 面向 AI Agent 的本地优先记忆层与记忆 Skill，在应用层缓解长上下文注意力稀释与上下文遗忘，支持可追溯检索、策略化记忆生命周期与可审计遗忘

tokyo-brain

Universal memory infrastructure for AI agents

memorg

Give your LLM a memory that actually works.

openmemory-ai

Persistent, semantic memory for AI agents - local-first, framework-agnostic, production-ready