Semantic Memory Python Packages

yantrikdb

Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). AGPL.

aelfrice

Bayesian memory that learns from feedback for LLM agents

memanto

Memory that AI Agents Love!

mengram-ai

Human-like memory for AI agents — auto-save, auto-recall, cognitive profile. Claude Code hooks, MCP server (29 tools), OpenClaw plugin, semantic/episodic/procedural memory. Free open-source Mem0 alternative.

mnemory

A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifact store for detailed content.

mflow-ai

M-flow builds semantic memory layers that help LLMs reason over your data with structured knowledge graphs.

remembra

Universal memory layer for AI applications. Self-host in minutes. Open source.

cashew-brain

Persistent memory for AI agents. Extract once, recall forever.

agent-immune

Adaptive threat intelligence for AI agent security — semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening.

snipara-memory

Standalone memory engine for coding agents

openparallax-shield

AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.

engram-mem

Dual-memory system (episodic vector + semantic graph) with LLM reasoning for AI agents. CLI, MCP, HTTP API, WebSocket interfaces.

openparallax-memory

AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.

openparallax-channels

AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.

openparallax-audit

AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.

openparallax-sandbox

AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.

mcp-external-memory

An MCP server that gives LLMs persistent, searchable semantic memory

langchain-mengram

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

driftguard-ai

Semantic mistake-memory and guardrail for AI agents. Stops agents from repeating the same failures using causal graphs and semantic matching. Supports MCP, LangGraph, and in-process Python.

obsidian-mem

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

hermes-mnemory

A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifact store for detailed content.

semantic-recall

Semantic Vector Memory for Coding Agents - Long-term memory system with vector embeddings for fuzzy retrieval