AI agent tools for agent memory
Short answer: Our top pick for agent memory: claude-mem, with the highest AgentPick Score (93/100) among tools tagged "agent-memory". Runners-up: tidb (91) and Mem0 (90). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | claude-mem | Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant … | 93/100 | ★ 101k | Apache-2.0 | 13 Oct 2026 |
| #2 | tidb | TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. N… | 91/100 | ★ 41k | Apache-2.0 | 14 Oct 2026 |
| #3 | Mem0 | The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production. | 90/100 | ★ 67k | Apache-2.0 | 14 Oct 2026 |
| #4 | MemPalace | The best-benchmarked open-source AI memory system. And it's free. | 90/100 | ★ 60k | MIT | 14 Oct 2026 |
| #5 | hindsight | Hindsight: Agent Memory That Learns | 90/100 | ★ 50k | MIT | 14 Oct 2026 |
| #6 | cognee | Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free | 89/100 | ★ 32k | Apache-2.0 | 14 Oct 2026 |
| #7 | screenpipe | YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power … | 81/100 | ★ 22k | See repo | 14 Oct 2026 |
| #8 | EverOS | One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. | 81/100 | ★ 13k | Apache-2.0 | 14 Oct 2026 |
| #9 | Octop | A smarter, self-hosted AI assistant — multi-user, multi-agent. | 81/100 | ★ 9.3k | MIT | 14 Oct 2026 |
| #10 | TencentDB-Agent-Memory | TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory,… | 80/100 | ★ 29k | See repo | 14 Oct 2026 |
| #11 | MemOS | Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and Deep… | 80/100 | ★ 12k | Apache-2.0 | 10 Oct 2026 |
| #12 | opensquilla | OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density | 80/100 | ★ 7.1k | Apache-2.0 | 14 Oct 2026 |
| #13 | honcho | Memory library for building stateful agents | 79/100 | ★ 7.6k | AGPL-3.0 | 14 Oct 2026 |
| #14 | ReMe | ReMe: Memory Management Kit for Agents - Remember Me, Refine Me. | 74/100 | ★ 3.6k | Apache-2.0 | 14 Oct 2026 |
| #15 | memsearch | A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus. | 74/100 | ★ 2.7k | MIT | 9 Oct 2026 |
| #16 | memgraph | High-performance open-source in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. Cypher-compatible, built in … | 73/100 | ★ 4.6k | See repo | 14 Oct 2026 |
| #17 | obsidian-wiki | Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents | 73/100 | ★ 3.6k | MIT | 13 Oct 2026 |
| #18 | neo | Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link… | 72/100 | ★ 3.3k | MIT | 14 Oct 2026 |
| #19 | kungfu | Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface. | 68/100 | ★ 4.5k | Apache-2.0 | 3 Oct 2026 |
| #20 | Memori | Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for p… | 65/100 | ★ 17k | See repo | 3 Oct 2026 |
| #21 | memU | Personal memory across agents | 63/100 | ★ 15k | See repo | 13 Oct 2026 |
| #22 | MIRIX | Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visua… | 60/100 | ★ 3.5k | Apache-2.0 | 8 Oct 2026 |
| #23 | Agent-S | Agent S: an open agentic framework that uses computers like a human | 58/100 | ★ 13k | Apache-2.0 | 8 Oct 2026 |
| #24 | julep | Julep — durable, composable AI agents. Flows that crash and resume, retry safely, and explain every step. | 53/100 | ★ 6.6k | Apache-2.0 | 6 Aug 2026 |
| #25 | EvoAgentX | 🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents | 49/100 | ★ 3.4k | See repo | 27 Aug 2026 |
| #26 | LongMemory | Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. | 48/100 | ★ 4.5k | Apache-2.0 | 20 Sept 2026 |
| #27 | SimpleMem | [ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal | 46/100 | ★ 3.8k | MIT | 24 Jul 2026 |
| #28 | agent-memory | Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Cl… | 46/100 | ★ 3.6k | MIT | 14 Oct 2026 |
| #29 | m_flow | A bio-inspired cognitive memory engine — a new paradigm for Graph RAG. | 44/100 | ★ 4.5k | Apache-2.0 | 1 Sept 2026 |
| #30 | Acontext | Agent Skills as a Memory Layer | 39/100 | ★ 3.7k | Apache-2.0 | 14 Jul 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Read the license before using it commercially.
- Check how recently it was updated and how active its issues are.
- Run it on a small, low-risk task first.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for self-hosted setups →
Agent building
AI agent tools for LangChain →
Agent building
AI agent tools for sandbox →
Agent building
AI agent tools for harness engineering →
Agent building
AI agent tools for penetration testing →
Agent building
AI agent tools for benchmark →
Agent building
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.