Trending open-source projects · updated daily

AI Agent Memory Projects

An LLM call is stateless: everything the model knows about your session has to travel inside the prompt. Agent memory is the layer in between — it decides what gets extracted from a conversation, where that state is stored, and what is pulled back into the context window on the next turn. The projects on this board attack that problem from different angles: embedded stores that run in the same process as the agent, graph memory that keeps entities and relations, vector-backed recall, and systems that summarise a transcript instead of storing it verbatim. Entries come from GitHub topic pages for agent memory, long-term memory, LLM memory and memory management, ranked by stars, so a heavyweight framework and a small single-file library land in the same list. Every card carries language, stars and forks; every page adds description, license, last push date, README and related projects. Stars measure attention, not maintenance — read the activity dates before you give an agent the keys to real user data.

Trending AI Agent Memory Projects

1

thedotmack / claude-mem

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.

TypeScript★ 94,311⑂ 0
View thedotmack/claude-mem
2

666ghj / MiroFish

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物

Python★ 74,064⑂ 0
View 666ghj/MiroFish
3

mem0ai / mem0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

Python★ 65,695⑂ 0
View mem0ai/mem0
4

bojieli / ai-agent-book

《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码

Python★ 48,844⑂ 0
View bojieli/ai-agent-book
5

pingcap / tidb

TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors.

Go★ 40,554⑂ 0
View pingcap/tidb
6

volcengine / OpenViking

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

Python★ 38,148⑂ 0
View volcengine/OpenViking
7

topoteretes / cognee

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.

Python★ 30,855⑂ 0
View topoteretes/cognee
8

supermemoryai / supermemory

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

TypeScript★ 30,665⑂ 0
View supermemoryai/supermemory
9

TencentCloud / 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, Skill, LLM-Wiki, Code-Graph) that are governed

TypeScript★ 27,024⑂ 0
View TencentCloud/TencentDB-Agent-Memory
10

dolthub / dolt

Dolt – Git for Data

Go★ 24,475⑂ 0
View dolthub/dolt
11

MemoriLabs / Memori

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.

Python★ 16,849⑂ 0
View MemoriLabs/Memori
12

alibaba / zvec

A lightweight, lightning-fast, in-process vector database

C++★ 15,974⑂ 999
View alibaba/zvec
13

NevaMind-AI / memU

Personal memory across agents

Python★ 14,418⑂ 0
View NevaMind-AI/memU
14

semantica-agi / semantica

Graph-Native Infrastructure for Context and Accountable AI Systems

Python★ 13,301⑂ 0
View semantica-agi/semantica
15

EverMind-AI / EverOS

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

Python★ 13,087⑂ 0
View EverMind-AI/EverOS
16

MemTensor / 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 DeepSeek Harness support.

TypeScript★ 11,478⑂ 0
View MemTensor/MemOS
17

henrypp / memreduct

Lightweight real-time memory management application to monitor and clean system memory on your computer.

C★ 10,561⑂ 605
View henrypp/memreduct
18

deeplethe / utopia

World's first open-source enterprise world model.

Rust★ 9,403⑂ 0
View deeplethe/utopia
19

plastic-labs / honcho

Memory library for building stateful agents

Python★ 7,266⑂ 0
View plastic-labs/honcho
20

IgorMundstein / WinMemoryCleaner

This free RAM cleaner uses native Windows features to optimize memory areas. It's a compact, portable, and smart application.

C#★ 5,052⑂ 312
View IgorMundstein/WinMemoryCleaner
21

kungfu-systems / kungfu

Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.

C++★ 4,520⑂ 0
View kungfu-systems/kungfu
22

CaviraOSS / LongMemory

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

TypeScript★ 4,510⑂ 0
View CaviraOSS/LongMemory
23

FlowElement-xinliuyuansu / m_flow

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

Python★ 4,505⑂ 0
View FlowElement-xinliuyuansu/m_flow
24

ai-boost / awesome-harness-engineering

Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

Python★ 4,399⑂ 0
View ai-boost/awesome-harness-engineering
25

TencentCloud / Octop

A smarter, self-hosted AI assistant — multi-user, multi-agent.

Python★ 4,327⑂ 0
View TencentCloud/Octop
26

bdwgc / bdwgc

The Boehm-Demers-Weiser conservative C/C++ Garbage Collector (bdwgc, also known as bdw-gc, boehm-gc, libgc)

C★ 3,539⑂ 445
View bdwgc/bdwgc
27

GPUOpen-LibrariesAndSDKs / VulkanMemoryAllocator

Easy to integrate Vulkan memory allocation library

C★ 3,502⑂ 460
View GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator
28

Mirix-AI / MIRIX

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently.

Python★ 3,444⑂ 271
View Mirix-AI/MIRIX
29

pashpashpash / vault-ai

OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend.

JavaScript★ 3,391⑂ 0
View pashpashpash/vault-ai
30

awslabs / agentcore-samples

Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.

Python★ 3,387⑂ 1,331
View awslabs/agentcore-samples
31

letta-ai / letta-code

Stateful agents that are like people, with memory, identity, and the ability to learn and adapt

TypeScript★ 3,385⑂ 0
View letta-ai/letta-code
32

neomjs / 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, Active Hybrid GraphRAG, DreamService

JavaScript★ 3,280⑂ 0
View neomjs/neo
33

MemMachine / MemMachine

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.

Python★ 3,222⑂ 213
View MemMachine/MemMachine
34

memodb-io / memobase

User Profile-Based Long-Term Memory for AI Chatbot Applications.

Python★ 2,907⑂ 0
View memodb-io/memobase
35

zilliztech / memsearch

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

Python★ 2,627⑂ 0
View zilliztech/memsearch
36

kayba-ai / agentic-context-engine

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

Python★ 2,577⑂ 0
View kayba-ai/agentic-context-engine
37

Bitterbot-AI / bitterbot-desktop

Bitterbot - a mesh of agents that turns shared experience into collective capability.

TypeScript★ 2,459⑂ 0
View Bitterbot-AI/bitterbot-desktop
38

cytostack / openwolf

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.

TypeScript★ 2,352⑂ 0
View cytostack/openwolf
39

moorcheh-ai / memanto

Memory that AI Agents Love!

Python★ 2,255⑂ 0
View moorcheh-ai/memanto
40

Xnhyacinth / Awesome-LLM-Long-Context-Modeling

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

★ 2,171⑂ 0
View Xnhyacinth/Awesome-LLM-Long-Context-Modeling
41

cortexkit / magic-context

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

TypeScript★ 2,157⑂ 0
View cortexkit/magic-context
42

agentset-ai / agentset

The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.

TypeScript★ 2,093⑂ 187
View agentset-ai/agentset
43

xzf-thu / VoiceMem

Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively

Python★ 2,018⑂ 0
View xzf-thu/VoiceMem
44

lucidrains / titans-pytorch

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

Python★ 1,981⑂ 0
View lucidrains/titans-pytorch
45

doobidoo / mcp-memory-service

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

Python★ 1,952⑂ 0
View doobidoo/mcp-memory-service
46

MemTensor / memmy-agent

🍙 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.

TypeScript★ 1,952⑂ 0
View MemTensor/memmy-agent
47

tapwork / HeapInspector-for-iOS

Find memory issues & leaks in your iOS app without instruments

Objective-C★ 1,886⑂ 136
View tapwork/HeapInspector-for-iOS
48

plasma-umass / Mesh

A memory allocator that automatically reduces the memory footprint of C/C++ applications.

C++★ 1,883⑂ 84
View plasma-umass/Mesh
49

activeloopai / hivemind

Hivemind turns your traces into reusable skills across agents

TypeScript★ 1,618⑂ 0
View activeloopai/hivemind
50

mex-memory / mex

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

TypeScript★ 1,614⑂ 125
View mex-memory/mex
51

BAI-LAB / MemoryOS

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

Python★ 1,581⑂ 0
View BAI-LAB/MemoryOS
52

Prismer-AI / PrismerCloud

Prismer Cloud

TypeScript★ 1,558⑂ 0
View Prismer-AI/PrismerCloud
53

gioxx / MarvellousSuspender

A free, open-source Chrome extension - no ads, no tracking. Based on The Great Suspender, cleaned up and actively maintained.

JavaScript★ 1,394⑂ 145
View gioxx/MarvellousSuspender
54

AutoArk / TinyEngram

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

Python★ 1,376⑂ 89
View AutoArk/TinyEngram
55

Dataojitori / nocturne_memory

A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia.

Python★ 1,360⑂ 0
View Dataojitori/nocturne_memory
56

Intuition-Lab / personal-model

Build your HUMAN.md.

Python★ 1,320⑂ 0
View Intuition-Lab/personal-model
57

mkirchner / gc

Simple, zero-dependency garbage collection for C

C★ 1,307⑂ 72
View mkirchner/gc
58

microsoft / gctoolkit

Tool for parsing GC logs

Java★ 1,300⑂ 177
View microsoft/gctoolkit
59

0voice / kernel_memory_management

总结整理linux内核的内存管理的资料,包含论文,文章,视频,以及应用程序的内存泄露,内存池相关

★ 1,290⑂ 367
View 0voice/kernel_memory_management
60

IAAR-Shanghai / Awesome-AI-Memory

Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design.

Python★ 1,224⑂ 0
View IAAR-Shanghai/Awesome-AI-Memory
61

zjunlp / LightMem

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

Python★ 1,168⑂ 0
View zjunlp/LightMem
62

LycheeMem / LycheeMem

Lightweight Long-Term Memory for LLM Agents.

Python★ 1,092⑂ 0
View LycheeMem/LycheeMem
63

oceanbase / powercontext

Not only memory but a full story.

Python★ 1,091⑂ 0
View oceanbase/powercontext
64

AnnaSuSu / TechSpar

一个持续进化的面试训练系统。在线体验地址:https://techspar.cn

TypeScript★ 1,082⑂ 0
View AnnaSuSu/TechSpar
65

zpl-c / zpl

📐 Pushing the boundaries of simplicity

C★ 1,074⑂ 50
View zpl-c/zpl
66

NirDiamant / Agent_Memory_Techniques

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti

Jupyter Notebook★ 1,069⑂ 0
View NirDiamant/Agent_Memory_Techniques
67

fuyuxiang / echo-agent

Echo Agent 是一个可自托管、长期运行、持续学习的 AI Agent,面向个人与团队的私有自动化场景。它可以部署在自有服务器上,统一连接模型、工具、记忆、权限与消息入口。内置四层认知记忆、遗忘曲线与矛盾检测机制,能够在跨会话任务中持续沉淀上下文,并保持长期记忆的质量。针对命令执行、文件操作等高风险行为,它提供基于 LLM 的审批与解释机制,为关键操作建立可审计、可追溯的安全边界。原生支持

Python★ 1,049⑂ 0
View fuyuxiang/echo-agent
68

GPUOpen-LibrariesAndSDKs / D3D12MemoryAllocator

Easy to integrate memory allocation library for Direct3D 12

C++★ 1,035⑂ 120
View GPUOpen-LibrariesAndSDKs/D3D12MemoryAllocator
69
70

Captainarash / The_Holy_Book_of_X86

A simple guide to x86 architecture, assembly, memory management, paging, segmentation, SMM, BIOS....

★ 979⑂ 126
View Captainarash/The_Holy_Book_of_X86
71

tigerless-labs / 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. Claude Code and Codex share one store. No API key.

Python★ 958⑂ 0
View tigerless-labs/agent-memory
72

ZeroIntensity / pointers.py

Bringing the hell of pointers to Python.

Python★ 934⑂ 11
View ZeroIntensity/pointers.py
73

Shy2593666979 / AgentChat

AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI

Python★ 899⑂ 0
View Shy2593666979/AgentChat
74

CodeAbra / iai-personal-memory-engine

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time.

Python★ 890⑂ 0
View CodeAbra/iai-personal-memory-engine
75

topoteretes / awesome-ai-memory

A list of AI memory projects

Python★ 880⑂ 133
View topoteretes/awesome-ai-memory
76

vshulcz / deja-vu

One memory shared by Claude Code, Codex, Cursor, Copilot CLI, OpenClaw and 28 more coding agents, built from the session history already on disk.

Go★ 878⑂ 0
View vshulcz/deja-vu
77

riponcm / projectmem

Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed.

Python★ 828⑂ 0
View riponcm/projectmem
78

Victorwz / LongMem

Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".

Python★ 828⑂ 0
View Victorwz/LongMem
79

desplega-ai / agent-swarm

Your Company Agentic Operating System

TypeScript★ 813⑂ 0
View desplega-ai/agent-swarm
80

AVIDS2 / memorix

Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro

TypeScript★ 791⑂ 0
View AVIDS2/memorix
81

gamenet / redis-memory-analyzer

Redis memory profiler to find the RAM bottlenecks throw scaning key space in real time and aggregate RAM usage statistic by patterns.

Python★ 791⑂ 80
View gamenet/redis-memory-analyzer
82

ReflexioAI / claude-smart

Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

Python★ 781⑂ 0
View ReflexioAI/claude-smart
83

codefuse-ai / CodeFuse-muAgent

An Innovative Agent Framework Driven by KG Engine

Python★ 774⑂ 82
View codefuse-ai/CodeFuse-muAgent
84

rapidsai / rmm

NVIDIA RMM is a library for allocating and managing GPU memory in C++ and Python.

C++★ 731⑂ 260
View rapidsai/rmm
85

dongshuyan / compass-skills

司南:个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents

Python★ 729⑂ 0
View dongshuyan/compass-skills
86

agentic-box / memora

Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.

Python★ 727⑂ 0
View agentic-box/memora
87

neo4j-labs / create-context-graph

AI agents with graph based reasoning memory, scaffolded in seconds

Python★ 726⑂ 0
View neo4j-labs/create-context-graph
88

DasterProkio / awesome-ai-companion

Open-source AI companions, desktop pets, long-term memory & proactive chat. 人机恋开源项目大全。让你的家机能够脱离官端自主存在,拥有记忆和主动性。

HTML★ 712⑂ 0
View DasterProkio/awesome-ai-companion
89

okf-memory / okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure.

Go★ 705⑂ 0
View okf-memory/okf-agent-memory
90

caspianmoon / memoripy

Evidence-first local memory for AI agents with temporal versions, admission policies, citations, explainable recall, MCP, and audit tooling.

Python★ 695⑂ 60
View caspianmoon/memoripy
91

swarmclawai / swarmvault

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern.

TypeScript★ 694⑂ 0
View swarmclawai/swarmvault
92

swarmclawai / swarmclaw

Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter

TypeScript★ 677⑂ 0
View swarmclawai/swarmclaw
93

jmerelnyc / Photo-agents

Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.

Python★ 674⑂ 0
View jmerelnyc/Photo-agents
94

framerslab / agentos

TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

TypeScript★ 670⑂ 0
View framerslab/agentos
95

jaredrhod / ai-memory-vault

Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No vector database, just markdown.

★ 665⑂ 0
View jaredrhod/ai-memory-vault
96

EverMind-AI / SkillCorpus

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

Python★ 662⑂ 0
View EverMind-AI/SkillCorpus
97

TeleAI-UAGI / Awesome-Agent-Memory

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

Python★ 642⑂ 0
View TeleAI-UAGI/Awesome-Agent-Memory
98

Arvincreator / project-golem

OS-level autonomous AI agent with long-term memory, multi-agent coordination, Titan Chronos scheduler & Moltbot Social Core

JavaScript★ 639⑂ 0
View Arvincreator/project-golem
99

agentic-os-org / ANOLISA

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

Rust★ 629⑂ 0
View agentic-os-org/ANOLISA
100

samvallad33 / vestige

Cognitive Deterministic Memory Security OS for Agentic AI that reaches backward through time to find the quiet change behind today's failure, not the lookalike.

Rust★ 628⑂ 0
View samvallad33/vestige

Long-Term & Persistent Agent Memory

Vector, Graph & Retrieval Memory

Agent Memory Frameworks

On-Device & Embedded Memory Stores

More AI Trending Projects

1

cloudflare / security-audit-skill

JavaScript★ 17,418⑂ 959▲ 3,155 stars
2

affaan-m / ECC

JavaScript★ 263,267⑂ 39,395▲ 1,012 stars
3

Tencent / BrowserSkill

TypeScript★ 5,916⑂ 417▲ 612 stars
4

vercel-labs / json-render

TypeScript★ 16,987⑂ 905▲ 585 stars
5

addyosmani / agent-skills

JavaScript★ 97,396⑂ 10,274▲ 556 stars
6

anthropics / claude-code

TypeScript★ 146,908⑂ 23,988▲ 483 stars

What agent memory actually means

A language model has no memory of its own. Every call starts blank, so anything an agent needs to know — a user preference, a decision taken three sessions ago, the contents of a repository it just read — has to be reconstructed and placed into the prompt. Agent memory is the machinery that does the reconstruction. It is usually three jobs glued together: extraction (deciding which part of a conversation is worth keeping), storage (a vector index, a graph, a relational table, or plain files on disk) and retrieval (choosing what goes back into the context window on the next call). Almost every project on this board is an opinionated answer to one question: where does state live, and how is it fetched.

The distinction that matters in production is not the short-term versus long-term label, but the prompt-token budget. A system that stores every turn and replays all of it drowns the context window and pays for it on every request; a system that retrieves three relevant facts costs almost nothing. That trade-off — how much to remember versus how much to re-send — separates a weekend demo from something you can run for a month.

Long-term memory, summarisation and graph recall

Long-term memory is whatever survives the end of a session: facts about a person, decisions taken on a project, the state of a task. Three shapes dominate the projects below. Summarisation compresses the running transcript so recent turns stay cheap to send. Vector recall embeds each memory as text plus an embedding and fetches the nearest by similarity — quick to build, weak at questions that need structure. Graph memory extracts people, projects and relations, then walks them at query time; it answers questions like which library did we drop and why far better than similarity search, at the cost of an extraction step you must maintain.

The three are not exclusive. The stronger systems here write to two stores at once — a cheap summary for the live conversation, and a structured, searchable store for everything older.

On-device and self-hosted memory

On-device memory means the memory layer runs beside the model — same process, same container, same laptop — instead of posting user data to a hosted service. Two families dominate. Embedded stores are essentially a database file with vector search bolted on: no server, no network, no per-query bill. Self-hosted servers buy you a retention policy you can actually explain to a user and a deletion path that does not depend on someone else’s API. If data residency or offline operation is the requirement, start with the embedded tools — they are the ones that keep working with the network cable unplugged.

Agent memory questions

What is an AI agent memory system? The component that persists information between model calls and decides what goes back into the context window: normally an extraction step, a store, and a retrieval policy.

Does agent memory need a vector database? No. Vector search is one retrieval strategy and the easiest to start with. Graph stores, SQLite tables and flat files are all used in production, especially when the questions you ask are structural rather than semantic.

What is on-device memory for AI agents? A memory store running on the same machine or in the same process as the agent, so nothing is sent to a third party and recall keeps working offline. Embedded databases and local vector indexes are the usual building blocks.

Is agent memory the same as fine-tuning? No. Fine-tuning changes the weights and is expensive to update. Memory changes what is in the prompt, which means you can edit, delete and audit it per user — usually exactly what privacy rules demand.

How do I stop memory from growing forever? Give it a write policy and a decay rule: score memories as they are written, expire the low-value ones, and cap the retrieved set. Every mature project on this board exposes some version of that policy.

Related AI Trending Lists