Agent Memory System Python Packages

hypermnesia-mcp

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

crumb-kit

Repo-local, agent-agnostic project memory — your AI agents remember decisions, avoid repeated failures, and resume where they left off

engrama

A memory graph designed for the agent that uses it, not the human who feeds it. Engrama reconstructs context from associations on demand, replacing the "stuff everything into the prompt" reflex with targeted graph traversal. SQLite default, Neo4j optional.

neuro-cortex-memory

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

kektordb-client

AI memory system combining vector search with temporal knowledge graph. Built-in cognitive engine for agents. Supports memory decay, contradiction detection, and MCP integration.

dusha

Dusha (душа, [dʊˈʂa], "soul") is a Python API reference implementation that combines memory, personality, proactive messaging and affect for LLM companions.

soul-engine-mcp

Epistemic Bio-Homeostatic Identity & Memory Kernel for AI Agents with Model Context Protocol (MCP) Interface

topodb

Embedded, temporal, graph-native memory for AI agents.

sodamem

Agentic memory infra for AI agents

gctrl

Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens. A push for data sovereignty.