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!

switchboard-local

Privacy-aware, local-first router for your CLI coding agents (Codex, Claude Code) and local LLMs (Ollama) — keeps sensitive prompts on-device and cuts premium-model usage.

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.

cashew-brain

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

kyros-sdk

Kyros — The Memory OS for AI Agents Give your AI agents secure, self-correcting, persistent memory in 3 lines of code. Three memory types (episodic, semantic, procedural) with built-in forgetting curves, cryptographic integrity, and automatic contradiction resolution. Model-agnostic REST API with Python and TypeScript SDKs.

remembra

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

subconscious-mcp

Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift_report, stats over stdio.

engram-mem

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

agent-immune

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

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.

smartmemo

Semantic memory for LLM agent calls with an equivalence-first cache architecture.

mflow-ai

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

mcp-external-memory

An MCP server that gives LLMs persistent, searchable semantic memory

atomicmemory-langflow

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

claudecode-memanto

Memory that AI Agents Love!

semanticmemo

Production-grade semantic caching for LLM agents — a learned equivalence classifier replaces the naive cosine threshold that causes false-positive failures.

memanto-mcp

Memory that AI Agents Love!

atomicmemory-hermes

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

hermes-memanto

Memory that AI Agents Love!

openparallax-channels

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

openparallax-sandbox

Python wrapper for the OpenParallax sandbox module

openparallax-memory

Python wrapper for the OpenParallax memory module