How to add long-term memory to AI agents: tools by use case
Memory layers that let agents remember users, past conversations and facts across sessions. We list 105 tools for memory for agents below, each with a link-checked page, pricing as the maker states it and alternatives.
Updated
105 tools: 83 open source, 3 source-available, 8 free or freemium, 3 paid, usage-based or enterprise, 8 pricing on the maker's site.
Want the ranked list of memory and RAG products? See the Memory & RAG category.
RAG and documents (24) See the full list →
OpenKnowledge
OpenKnowledge is a free, local-first markdown editor and knowledge base built for working alongside AI agents. It looks and feels like a Notion-style WYSIWYG editor, with callouts, tabs, Mermaid diagrams and media blocks, but every page stays a plain markdown file on your disk. Coding agents such as Claude Code, Codex, Cursor, Gemini CLI and dozens of others can read and write the same files through its integrations, so specs, team wikis and LLM wikis stay in one place that both people and agents keep up to date. It ships as a desktop app plus a web UI and CLI.
Added
xerj
A local-first search engine and MCP server for agents: one Rust binary indexes code, docs, logs, CSV/JSONL and PDFs for full-text, vector and hybrid search plus agent memory, behind an Elasticsearch-compatible API.
Added
Memgraph
In-memory graph database used as the graph layer for GraphRAG pipelines and agent memory, with Cypher queries plus vector and text search.
Added
Pixeltable
Multimodal data layer that combines storage, transforms, indexing and retrieval in one Python library for building agents over images, video and documents.
Added
MarkItDown
Microsoft's Python tool and MCP server that converts PDFs, Office documents, images, audio and web pages to Markdown for LLM and agent pipelines.
Added
Headroom
Library, proxy and MCP server that compresses tool outputs, logs, files and RAG chunks locally before they reach the LLM, cutting tokens for coding agents.
Added
llmware
Framework for building private, local RAG and agent applications with small specialized models on AI PCs, edge and self-hosted setups.
Added
txtai
All-in-one Python framework for semantic search, LLM orchestration and agents built on an embeddings database of vector, graph and relational indexes.
Added
Knowhere
Document parsing and retrieval system that turns messy files into structured, navigable memory for AI agents and RAG.
Added
Neuron AI
PHP framework for creating and orchestrating AI agents with LLMs, tools, vector stores and memory.
Added
Qdrant MCP Server
Official Qdrant MCP server that lets agents store and retrieve memories and documents in the Qdrant vector database.
Added
BaseAI
Web AI framework from Langbase for building AI agents with memory (RAG) and deploying them serverless.
Added
Extend MCP
Extend's MCP server for turning documents into structured data: parse, extract, classify, split and fill PDF forms.
Added
LlamaParse
LlamaIndex's document processing platform that parses PDFs, scans and Office files into markdown or JSON and extracts, classifies and indexes them for agents.
Added
SimpleMem
Research-backed lifelong memory library for LLM agents that stores, compresses and retrieves text and multimodal memories, usable over MCP.
Added
RAGFlow
Open-source RAG engine with deep document parsing and agent features for building grounded question-answering over your files.
Added
Mem0
Mem0 is an open-source memory layer for AI agents that extracts facts from conversations in a single add-only pass, links entities across memories and retrieves them in later sessions, with an Apache-2.0 SDK and a managed platform.
Added
PageIndex
Document index for reasoning-based, vectorless RAG that lets agents navigate long documents like a table of contents.
Added
Chroma
Open-source search and vector database widely used for agent memory and RAG.
Added
MemOS
Memory operating system for LLMs and agents with persistent memory and retrieval.
Added
LanceDB
Open-source multimodal vector database for search, RAG and agent memory.
Added
Activeloop
Deep Lake, a multimodal database for AI that stores vectors, images, text and video so agents and RAG apps can search and retrieve them.
Added
seekdb
AI-native search database for agent storage combining vector, text and structured data.
Added
Agentset
Open-source RAG platform for building agents and apps that answer accurately from your documents.
Added
Agent frameworks and SDKs (17)
Memori
An LLM-, database- and framework-agnostic memory layer that turns what agents do and say into structured, persistent state they can recall in later runs. Open source to self-host, or use Memori Cloud with an API key.
Added
ai-memory
Fabio Akita's open-source long-term memory layer for coding agents: one Rust binary that keeps plain-markdown project memory and typed handoffs shared across 20+ harnesses such as Claude Code, Codex, Cursor and Gemini CLI, so you can switch agents, machines or teammates without re-explaining the project.
Added
Beacon
An open-source memory layer that captures traces from coding agents across harnesses and turns them into self-improving memory and visibility into what your agents did.
Added
AWorld
Agent harness from inclusionAI for building expert agents that search, reproduce and improve on ideas with their own tools and memory.
Added
Oh My OpenAgent (OmO)
Agent harness add-on (OmO) for OpenCode and Pi that runs multi-model coding agent teams with memory, planning and parallel workflows.
Added
TecAdRise Bot
TecAdRise Bot is a free, MIT-licensed Windows desktop app (Electron and Cursor SDK) for running a local team of AI agents, each with its own model, memory, skills, MCP servers, workspace and schedule.
Added
Antigravity SDK
Google's Python SDK for building stateful AI agents powered by Antigravity and Gemini, abstracting the agent loop and runtime.
Added
LangGraph4j
Java library for building stateful multi-agent applications as graphs, working with LangChain4j and Spring AI.
Added
tRPC-Agent-Go
Go framework for production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation and OpenTelemetry.
Added
Nanobot
Ultra-lightweight, self-hosted personal agent framework in Python with a web UI, tools, memory and MCP support.
Added
Agno
Python framework and runtime for building, running and managing multi-agent systems with memory, knowledge and tools.
Added
Letta
Framework for stateful agents with long-term memory (formerly MemGPT).
Added
Osaurus
Native macOS harness for AI agents with any model, memory and autonomous execution.
Added
Honcho
Memory library and service for building stateful agents that remember users.
Added
Deer Flow
ByteDance's open-source long-horizon agent harness that researches, codes and creates using sandboxes, memory and sub-agents.
Added
LangGraph
Framework for stateful, graph-based agent workflows.
Added
Cloudflare Agents
Cloudflare's SDK for building and deploying stateful AI agents on Workers.
Added
Local and self-hosted (14) See the full list →
Memmy
A local-first personal AI agent with a self-evolving long-term memory that its desktop app, CLI and your other AI agents can all share.
Added
OpenLore
A self-hosted knowledge repository for AI agents written in Go, where agents and teams share docs, notes and findings over SSH and MCP with scoped access.
Added
projectmem
A local-first memory layer for coding agents that records issues, attempts, fixes and decisions and warns your agent before it repeats a past mistake.
Added
Graphicle
Graphicle, from KarLex AI, is a single local Rust program that gives Claude Code, Cursor, Codex and other MCP agents a code graph and memory, returning excerpts with file and line references from your code, docs and past sessions, with no account or telemetry.
Added
Agent Sandbox (Kubernetes)
A Kubernetes project that adds a Sandbox resource for running isolated, stateful agent workloads such as code execution and browsers, with warm pools and fast startup on your own cluster.
Added
Dodaios
Open-source desktop agent OS for Windows, macOS and Linux (formerly Personal Jarvis): talk to it and it runs your coding CLIs side by side, your browser and your apps, with offline Whisper speech, a local wiki memory and support for Ollama, Claude or ChatGPT subscriptions.
Added
LongMemory
Local-first memory engine for agents that keeps durable, time-aware memories in SQLite and serves them to Claude, Copilot, Codex and others over MCP, CLI or HTTP.
Added
Webcmd
Browser layer for AI agents that learns how each website works as agents use it and saves that as local memory to make later runs faster and cheaper.
Added
MemPalace
Local-first AI memory system that stores conversations verbatim with a pluggable backend and serves recall to agents without API calls.
Added
Supermemory
Memory and context engine for agents with an API, app and MCP server, which can also run fully locally.
Added
Basic Memory
Persistent memory for Claude, Codex and Cursor stored as local Markdown knowledge, available open source or as a hosted cloud workspace.
Added
Mercury Agent
Self-hosted personal AI agent with a written personality, local memory, permission-gated tools and token budgets, reachable via CLI or Telegram.
Added
Jarvis
Private, local-first desktop AI assistant with voice and text chat, personal memory, dictation and MCP tools.
Added
EverOS
Local-first, portable memory layer for AI agents stored as Markdown.
Added
Codebase context and code search (7)
ktx
An open-source context layer for data and analytics agents that gives Claude Code, Codex and other agents a self-improving map of your warehouse, metrics and business definitions.
Added
Zep
Context layer that unifies business data, documents and conversations into memory so agents complete tasks correctly.
Added
LazyCodex
Agent harness for Codex that adds project memory, planning, execution and verified completion for complex codebases.
Added
Codebase Memory MCP
MCP server that indexes codebases into a persistent knowledge graph so coding agents can look up structure quickly.
Added
Cognee
Open-source memory platform that builds knowledge graphs so agents keep long-term memory.
Added
Graphiti
Builds real-time, temporal knowledge graphs that serve as memory for AI agents.
Added
Context Mode
Context window optimizer for coding agents that sandboxes tool output and persists session memory.
Added
More tools (43)
Cumora
Cumora is a team chat app where AI agents are members of the workspace rather than a chat box you prompt. Each agent gets a persona, its own private memory and files, a status, and a schedule on which it wakes up, reads the room and decides whether to message someone, post an idea or pull a small group together. Agents can message each other, and you can read those side conversations. People join by email or link, agents can be grouped into teams and given projects, and the same live workspace runs on desktop, in the browser and on a phone. It is free during an invite-only preview.
Added
LVLZ
LVLZ is a personal AI agent you run by messaging it like a person, on iMessage or WhatsApp, as a text, voice note or call. It runs errands on real websites in a cloud browser, such as bookings, forms and shopping, turns messages into tasks and projects, fills a CRM from your conversations, and runs routines like a morning brief or a price watch. Everything it does lands in a web workspace, its memory can be read, edited and exported, and it asks before paying, contacting someone new or deleting anything, with cards and passwords kept in an encrypted vault.
Added
Sundae
Sundae is a personal AI assistant you text from iMessage or Android RCS, with no app or account needed. It works on a computer of its own: it books tables, finds flights at current prices, compares shops, reads letters and photos you send, sets reminders, watches prices and builds simple web pages, then texts back with a screenshot so you can check. It remembers what you tell it, asks before spending money, sending, deleting or opening accounts, and stops at checkout for you to pay. It is free to start with a daily limit, with a paid Plus plan, and is in limited beta.
Added
Hy-Memory
Tencent Hunyuan's open-source memory system for agents that extracts, organizes and recalls long-term memories across sessions, with a memory hub and plugins for popular agent tools.
Added
KiwiFS
A markdown filesystem for agents and teams: searchable, structured and versioned knowledge in a single binary that agents can read and write.
Added
Second Brain
A free, open-source shared memory that runs in your own Cloudflare account, so Claude, ChatGPT, Cursor and other MCP clients can recall the same projects, preferences and decisions.
Added
Sno Station
Sno Station turns the coding agents you already use (Claude Code, Codex, Cursor, Hermes, OpenClaw) into one squad on your machine with shared memory, and its Self Learning reviews their sessions and proposes skill-file fixes you approve.
Added
AgentDock (NexusDock)
A secure MCP runtime that lets ChatGPT, Claude and other AI clients operate your Mac, Windows, Linux and Android devices, with memory, tools and reusable automations.
Added
agent-qa (Vostride)
A self-improving AI QA agent with persistent memory that tests web, Android and iOS apps from plain-English test steps, for developers and coding agents.
Added
Bops
Bops, from Orgo, is a Mac app for a team of AI bots that handle business ops such as inbox triage, CRM follow-ups, invoices and reports, each with its own cloud computer, email address, phone number and shared memory.
Added
Macro
Team workspace that links email, chat, docs, tasks, calls and CRM with agents that share one team memory.
Added
Zeroboot
VM sandboxes for running agent code that start in under a millisecond by forking a warm snapshot with copy-on-write memory.
Added
Sentience
Personal AI that builds a private memory from your email, meetings, messages and screen and acts as your digital twin, drafting and answering in your voice.
Added
OpenViking
Context database for AI agents that keeps memory, knowledge and skills in one inspectable virtual filesystem agents can navigate.
Added
Lightpanda
Headless browser written from scratch in Zig for AI agents and automation, built for speed and low memory rather than forked from Chromium.
Added
memU
Lightweight memory system that gives Codex, Claude Code, Cursor and other agents a shared memory across sessions and devices and distills reusable skills.
Added
EvoScientist
Self-evolving AI scientist system that autonomously explores research ideas, runs experiments and improves with growing skills and memory.
Added
LeanCTX
Open-source context gateway that sits between AI tools and your code and data to control and shrink what the model sees.
Added
Mnemosyne
Zero-cloud, SQLite-backed memory layer for Hermes, Claude Code, Cursor, Codex and custom agents with a single Python dependency.
Added
Cheshire Cat
Open-source AI agent microservice designed to be easy to understand and extend, with plugins and memory.
Added
Compozy
Operating system for AI agents that turns Claude Code, Codex, Gemini CLI and Cursor into a team with task handoff, loops, jobs and shared memory.
Added
Memanto
Memory agent that manages what your other agents keep, resolve and forget across platforms.
Added
CORE
Always-on personal AI that builds a memory graph from your email, meetings and tools, then plans and runs tasks like opening a pull request.
Added
Locize MCP
Locize's MCP server with translation-management tools for keys, translation memory, glossary, styleguides and versions.
Added
Dosu
Knowledge infrastructure that keeps docs, specs and agent memory current with your code for teams and coding agents.
Added
Pieces
AI memory layer that captures context from your work so you and your AI tools can recover decisions and resume where you left off.
Added
DeepTutor
Open-source personalized AI tutoring agent from HKU that turns your materials into guided explanations, practice and long-term learning support.
Added
AIOS
Research AI agent operating system that handles scheduling, context switching, memory, storage and tool management for LLM-based agents.
Added
MiMo Code
Xiaomi's terminal coding agent with persistent project memory across sessions; works with any major model provider and is tuned for Xiaomi's MiMo models.
Added
Agent Memory Leaderboard
Public leaderboard and open evaluation protocol, run by a group of universities and labs, for comparing long-term memory systems for agents in recurring submission rounds.
Added
Claude-Mem
Gives coding agents memory across sessions by capturing what they do, compressing it and feeding the relevant context back in later.
Added
Hindsight
Agent memory system that stores experiences and learns from them so agents improve over time.
Added
AgentMemory
Persistent memory layer for AI coding agents.
Added
TencentDB-Agent-Memory
Team-level memory hub that turns conversations, docs and code into shared memory for agents.
Added
Beads
Issue-tracking memory for coding agents so they can keep track of long-running work.
Added
Rowboat
AI coworker with memory that works alongside you and your team.
Added
Acontext
Memory layer that stores agent experience as reusable skills.
Added
ReMe
Memory management kit for agents.
Added
MemMachine
Universal memory layer for AI agents.
Added
Neo4j MCP
Neo4j MCP servers for querying graphs, managing Aura instances and graph memory.
Added
Questwright
AI dungeon master for tabletop RPGs that runs D&D 5e campaigns with dice, combat, battle maps and NPC memory, solo or with friends.
Added
AirJelly
Always-on desktop assistant that watches your workflow, remembers context and acts proactively.
Added
Anchor Action Index
Shared memory of web workflows for Anchor's cloud browsers: computer-use agents replay proven paths as deterministic code and the model only steps in where a page has changed, exposed as tools on Anchor's MCP server and REST API.
Added
GitHub repos (95)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| MarkItDown ↗ | 190,824 | MIT | 2026-10-20 |
| Claude-Mem ↗ | 101,230 | Apache License 2.0 | 2026-10-20 |
| RAGFlow ↗ | 92,335 | Apache License 2.0 | 2026-10-21 |
| Deer Flow ↗ | 83,959 | MIT | 2026-10-21 |
| Headroom ↗ | 75,629 | Apache License 2.0 | 2026-10-21 |
| Oh My OpenAgent (OmO) ↗ | 70,183 | — | 2026-10-21 |
| Mem0 ↗ | 67,147 | Apache License 2.0 | 2026-10-21 |
| MemPalace ↗ | 59,622 | MIT | 2026-10-20 |
| Hindsight ↗ | 50,483 | MIT | 2026-10-21 |
| Nanobot ↗ | 49,096 | MIT | 2026-10-21 |
| Codebase Memory MCP ↗ | 46,717 | MIT | 2026-10-21 |
| LangGraph ↗ | 43,237 | MIT | 2026-10-21 |
| Agno ↗ | 42,769 | Apache License 2.0 | 2026-10-21 |
| DeepTutor ↗ | 41,594 | Apache License 2.0 | 2026-10-18 |
| OpenViking ↗ | 40,217 | GNU Affero General Public License v3.0 | 2026-10-21 |
Top 15 of 95 by stars. Stars and licence come from each repo, checked when the listing was last verified.
Related tasks
Popular with: AI engineers
Tools are matched to tasks by category, use cases and what each tool says it does. Missing one? Submit it free.