TencentCloud/TencentDB-Agent-Memory Alternatives

if you need a Python-based memory API that is widely adopted and framework-agnostic, instead of TypeScript and TencentDB-centric.

Universal memory layer for AI Agents

if you want an MIT-licensed memory system with published benchmarks and no vendor lock-in.

The best-benchmarked open-source AI memory system. And it's free.

if you need a single-file Rust memory layer that runs serverless with no external database.

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

if you want an AGPL-licensed memory library that plugs into stateful Python agents.

Memory library for building stateful agents

if you need a memory management kit focused on iterative refinement rather than team sharing.

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

if you are building Java agents and want a JVM-native self-evolving memory engine.

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.

if you prefer a TypeScript-first portable memory layer with MCP/CLI adapters.

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

if you need a high-throughput memory engine that can run fully locally via REST.

Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

if you want memory that learns from task outcomes to improve retrieval over time.

Hindsight: Agent Memory That Learns

if you need enterprise-grade structured persistent memory for production agent systems.

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

if you want markdown-native, user-owned, local-first memory that works across apps.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

if you need a universal memory layer with pluggable storage backends and interop.

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

if you want a single self-evolving context database that fuses memory, RAG, and skills.

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

if you need hybrid retrieval and cross-task skill reuse to reduce token usage.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

if you want a Markdown+Milvus-backed memory layer for coding agents like Claude Code/Codex.

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

if you need a TypeScript memory store benchmarked for AI coding agents.

#1 Persistent memory for AI coding agents based on real-world benchmarks

if you want a lightweight local TypeScript memory store without external services.

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

if you need self-managing unbounded context for coding agents.

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

if you need a free local memory engine that stores as Markdown and integrates with common coding agents.

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.

if you prefer a knowledge-graph-backed memory platform for complex relational context.

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

if you only need persistent session memory for Claude Code and want automatic compression.

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

if you need a REST API with autonomous knowledge-graph consolidation for popular agent pipelines.

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

if you want a visual, rollbackable graph-based memory server for MCP that avoids vector RAG.

A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.

if you want a research-oriented agentic memory prototype for academic exploration, not production.

A-MEM: Agentic Memory for LLM Agents