topoteretes/cognee Alternatives

Choose it for a lightweight, widely adopted memory API with simple add/retrieve semantics rather than a graph-centric engine.

Universal memory layer for AI Agents

Choose it if you want a benchmark-optimized, MIT-licensed memory system with a lighter footprint than cognee's graph engine.

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

Choose it for a fast, locally runnable memory API and app that avoids Python dependency, if you prefer TypeScript.

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

Choose it if you need team-level governance and pre-built memory types (chat, skill, wiki, code graph) in a shared hub.

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.

Choose it if you want an adaptive memory engine focused on learning/improving from agent interactions over time.

Hindsight: Agent Memory That Learns

Choose it for a serverless, Rust-based memory layer to replace RAG, if you want a single-file deployment without an external graph DB.

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.

Choose it for production-grade, LLM-agnostic memory that persists structured agent state, if you need enterprise reliability.

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.

Choose it if you want local-first, Markdown-native memory that is user-owned and portable across many apps.

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

Choose it for a simple AGPL-licensed memory library with minimal API, if you prefer a smaller codebase over a graph platform.

Memory library for building stateful agents

Choose it if you're using the AgentScope ecosystem and want a dedicated memory management kit with refinement.

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

Choose it for an extensible, interoperable memory layer designed for complex agent state management and easy integration.

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.

Choose it if you need a Java-based memory engine for JVM agent ecosystems, avoiding Python entirely.

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

Choose it for a TypeScript-native memory layer with MCP server and multiple SDK/adapters, if you want to embed memory in JS projects.

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

Choose it if you want a self-evolving context database that unifies memory, RAG, and skills in one Python package.

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

Choose it for a TypeScript memory OS with hybrid retrieval and cross-task skill reuse, if you want a more feature-rich memory system.

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.

Choose it if you already use Milvus and want a Markdown-backed memory layer that works across multiple agents.

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

Choose it if you need a REST API memory service with a knowledge graph and autonomous consolidation for agent pipelines like LangGraph.

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

Choose it when you only need persistent context for Claude Code sessions and don't want a full knowledge-graph platform.

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

Choose it when your use case is memory for coding agents specifically, and you want a benchmark-validated TypeScript package.

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

Choose it for a compact research-inspired agentic memory, if you prefer MIT license and are okay with a less feature-complete project.

A-MEM: Agentic Memory for LLM Agents

Choose it for unbounded, self-managing context specifically for coding agents within the CortexKit framework.

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

Choose it if you want a lightweight, rollbackable memory server specifically for MCP agents, with a visual representation and graph-like memory.

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.

Choose it when you want a ready-to-run local memory server that works with desktop apps like Claude Desktop, rather than building memory into your own code.

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

Choose it if you want a ready-to-use personal agent that also acts as a shared local memory hub across all your AI tools, instead of building memory into your own app.

🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.