supermemoryai/supermemory Alternatives

Use it if you want a Python-native, Apache-2.0 memory layer with broad integration and active development.

Universal memory layer for AI Agents

Use it if you want a Python/MIT self-hosted memory system that claims top benchmark scores.

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

Use it if you want a Rust serverless single-file memory layer that avoids a separate RAG stack.

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.

Use it if you want a Python AGPL-3.0 memory library for stateful agents and can accept copyleft.

Memory library for building stateful agents

Use it if you are in the AgentScope ecosystem and want an Apache-2.0 memory management kit.

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

Use it if you want a TypeScript-first portable memory core with MCP/CLI adapters.

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

Use it if you want a learning memory agent in Python under MIT, with active development.

Hindsight: Agent Memory That Learns

Use it if you want a local-first, Markdown-native memory layer that is user-owned and portable.

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

Use it if you want a TypeScript self-evolving memory OS with hybrid retrieval and skill reuse.

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.

Use it if you want a Python universal memory layer with Apache-2.0 and extensible storage.

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.

Use it if you want an AGPL-3.0 context database that unifies memory, RAG, and skills.

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

Use it if you prefer a knowledge-graph-based memory platform over a hybrid-search one.

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.

Use it if you want a Milvus-backed unified memory layer with Markdown storage.

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

Use it if you need a governed, team-level memory hub instead of a per-user memory engine.

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.

Use it if your backend is JVM/Java and you need a 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.

Use it if you need enterprise-grade structured agent state infrastructure rather than a simple memory API.

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.

Use it if you want an MCP/REST standalone memory service with knowledge graph consolidation.

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

Use it if you want a self-hosted Go single-binary memory server with MCP, not a library.

Stash — persistent memory layer for AI agents. Episodes, facts, and working context stored in Postgres. MCP server included. Self-hosted, single binary, no cloud required.

Use it if you want a lightweight TypeScript local memory store and will handle extraction yourself.

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

Use it if you need turnkey session memory specifically for Claude Code or coding agents, not a general API.

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

Use it if you want the A-MEM agentic-memory research reference, but expect a stale prototype.

A-MEM: Agentic Memory for LLM Agents

Use it if you want persistent memory optimized for AI coding agents like Claude Code and Codex.

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

Use it if you want a private, local GPU-accelerated memory for Claude Code specifically.

Give your AI agent a brain that remembers. Local memory system for Claude Code — 100% private, GPU-accelerated, zero cloud dependency.

Use it if you want simple local SQLite memory across many coding agents, narrower than Supermemory.

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.