AI agent memory / persistent memory
TypeScript library implementing persistent memory for AI coding agents via MCP, using LLM Wiki patterns, confidence scoring, knowledge graphs, and hybrid search.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Use if you prefer a lightweight JavaScript MCP memory server that compresses context and injects it into future sessions, avoiding the TypeScript engine.
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 if you want a TypeScript portable semantic memory layer with an SDK, MCP server, and host plugins for more modular integration.
Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Use if you need a Python, self-hosted knowledge-graph memory platform for general agents, not a thin TypeScript library.
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 if you want an agent harness that bundles memory with skills and instincts for coding agents rather than a standalone memory layer.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Use if you prefer a widely-adopted Python memory layer with extraction and graph memory for framework-agnostic agents.
Universal memory layer for AI Agents
Use if you want a Python, MIT-licensed memory system with a benchmark focus rather than a drop-in TypeScript module.
The best-benchmarked open-source AI memory system. And it's free.
Use if you need a self-evolving Python context database that unifies memory, RAG, and skills at scale.
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Use if you want a self-hostable memory API/app with an interface, rather than a small embeddable library.
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
Use if you want a team-level, governed memory hub backed by TencentDB with LLM-Wiki and code-graph assets.
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 if you want a Python memory layer that adapts and learns over time, at the cost of TypeScript integration.
Hindsight: Agent Memory That Learns
Use if you want a Rust, serverless single-file memory layer that avoids complex RAG pipelines.
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 if you need enterprise-grade Python memory infrastructure with structured persistent state for production 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.
Use if you want a local-first, Markdown-native Python memory layer that keeps data user-owned.
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Use if you need a Python, AGPL-licensed memory library for building stateful agents.
Memory library for building stateful agents
Use if you want a Python memory management kit focused on refining and curating memory for agents.
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
Use if you want a Python universal memory layer with scalable storage and retrieval for agent state.
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 if you want a Python memory layer backed by Markdown and Milvus for coding agents, with a different search stack.
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Use if you want a TypeScript self-managing memory for coding agents as part of a larger CortexKit ecosystem.
Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.
Use if you want a lightweight Python MCP memory server with graph-like visual structure and rollback.
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.
Use if you want a Python agentic memory module with a research-oriented codebase, though it is older and less actively maintained.
A-MEM: Agentic Memory for LLM Agents
Use if you need a Java-based memory and context engine for JVM agents, not a TypeScript solution.
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 if you want a Python local memory engine for coding agents with a personal-cyber-brain model.
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.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Use if you want a simpler local persistent memory store for desktop coding tools, without graphs or hybrid search.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Use if you want a personal AI agent and local memory hub app, not an embeddable library.
🍙 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.
These projects were analysed and named agentmemory among their alternatives. The relationship is not symmetric — how agentmemory rates them is a separate judgement, made when agentmemory is analysed in its own right.
calls agentmemory “choose when you want a benchmark-focused persistent memory library for coding agents that can be swapped into agent workflows.”
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
calls agentmemory “if you need a TypeScript memory store benchmarked for AI coding agents.”
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.
calls agentmemory “Benchmark-driven persistent memory optimized for coding agents.”
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.
calls agentmemory “Choose when you are building a TypeScript coding agent and want a lightweight memory library tuned to coding workflows and benchmarks.”
Memory library for building stateful agents
calls agentmemory “choose when you specifically need memory for AI coding agents.”
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
calls agentmemory “Choose it when your use case is memory for coding agents specifically, and you want a benchmark-validated TypeScript package.”
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.
calls agentmemory “Use it if you want persistent memory optimized for AI coding agents like Claude Code and Codex.”
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
calls agentmemory “Choose if your use case is specifically coding agents and you want a benchmark-optimized persistent memory.”
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.
calls agentmemory “choose it when you need a TypeScript persistent memory specialized for coding agents.”
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.