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). Apache-2.0.

memanto

Memory that AI Agents Love!

mlx-memo

Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.

aelfrice

Bayesian memory that learns from feedback for LLM agents

snipara-memory

Open source memory engine for coding agents: semantic recall, session bundles, contradiction handling and a local FastAPI API.

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.

memanto-mcp

Memory that AI Agents Love!

twin-cognition

Persistent computational understanding for the AI tools you already use. A governed cognitive layer that transforms distributed observations into reusable understanding across models and interfaces.

atomicmemory-hermes

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!

zer0dex

A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector store, queried before each message. For cross-project recall where flat memory files or vector-only RAG fall short. Local-first. Reference implementation.

subconscious-mcp

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

agent-immune

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

hermes-memanto

Memory that AI Agents Love!

mcp-external-memory

An MCP server that gives LLMs persistent, searchable semantic memory

cashew-brain

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

engram-mem

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

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.

mflow-ai

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

smartmemo

Semantic memory and caching for LLM agents with classifier-validated equivalence instead of naive cosine thresholds.

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.

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.

semanticmemo

Production-grade semantic caching for LLM applications using classifier-validated equivalence, cross-encoder verification and risk-aware cache policies.

chronalyn

Long-term memory for Hermes Agent, with Hindsight recall and verified Mnemosyne checkpoints.