#Memory-management

Showing 60 of 61 repositories tagged #memory-management, ranked by stars

mem0ai
mem0ai
mem0

Universal memory layer for AI Agents

Score
100
โ˜… 60.5k โ‘‚ 7.0k +14/day
Python
topoteretes
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.

Score
88
โ˜… 27.5k โ‘‚ 2.7k +175/day
Python
MemoriLabs
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. 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.

Score
75
โ˜… 15.5k โ‘‚ 2.8k +14/day
Python
EverMind-AI
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.

Score
62
โ˜… 10.7k โ‘‚ 849 +162/day
Python
MemTensor
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

Score
50
โ˜… 10.1k โ‘‚ 924 +48/day
TypeScript
MemMachine
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.

Score
38
โ˜… 3.3k โ‘‚ 194 +51/day
Python
agentset-ai
agentset-ai
agentset

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

Score
100
โ˜… 2.0k โ‘‚ 183 โ€”
TypeScript
tapwork
tapwork
HeapInspector-for-iOS

Find memory issues & leaks in your iOS app without instruments

Score
100
โ˜… 1.9k โ‘‚ 136 โ€”
Objective-C
rentruewang
rentruewang
aioway

AI on the way. An RDBMS approach to deep learning. Declarative, explainable, scalable, optimizable, easy to deploy, all that good stuff.

Score
100
โ˜… 1.8k โ‘‚ 65 โ€”
Python
mex-memory
mex-memory
mex

Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.

Score
100
โ˜… 1.1k โ‘‚ 65 โ€”
TypeScript
zpl-c
zpl-c
zpl

๐Ÿ“ Pushing the boundaries of simplicity

Score
70
โ˜… 1.1k โ‘‚ 49 โ€”
C
zjunlp
zjunlp
LightMem

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

Score
25
โ˜… 956 โ‘‚ 88 +4/day
Python
ZeroIntensity
ZeroIntensity
pointers.py

Bringing the hell of pointers to Python.

Score
12
โ˜… 934 โ‘‚ 11 โ€”
Python
topoteretes
topoteretes
awesome-ai-memory

A list of AI memory projects

Score
95
โ˜… 809 โ‘‚ 92 +5/day
Python
codefuse-ai
codefuse-ai
CodeFuse-muAgent

An Innovative Agent Framework Driven by KG Engine

Score
37
โ˜… 773 โ‘‚ 81 โ€”
Python
caspianmoon
caspianmoon
memoripy

An AI memory layer with short- and long-term storage, semantic clustering, and optional memory decay for context-aware applications.

Score
84
โ˜… 691 โ‘‚ 61 โ€”
Python
madneal
madneal
articles-translator

:books:Translate the distinct technical blogs. Please star or watch. Welcome to join me.

Score
100
โ˜… 621 โ‘‚ 65 โ€”
LeoYeAI
LeoYeAI
openclaw-auto-dream

Automatic memory consolidation for OpenClaw agents โ€” like sleep for your AI. Powered by MyClaw.ai

Score
74
โ˜… 553 โ‘‚ 26 โ€”
HTML
ortuman
ortuman
nuke

A memory arena implementation for Go.

Score
100
โ˜… 552 โ‘‚ 20 โ€”
Go
TeleAI-UAGI
TeleAI-UAGI
Awesome-Agent-Memory

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

Score
89
โ˜… 521 โ‘‚ 59 +10/day
Python
mmtk
mmtk
mmtk-core

Memory Management ToolKit

Score
100
โ˜… 504 โ‘‚ 85 +4/day
Rust
taylorsatula
taylorsatula
mira-OSS

This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure when dropped into tools/ folder, and the system prompt composes from modular trinkets. I would like to think I've made an elegant brain-in-box. You load it and send cURL requests - it talks back, learns, and uses tools. Contributions welcome.

Score
79
โ˜… 469 โ‘‚ 42 โ€”
Python
essentialdevelopercom
essentialdevelopercom
quiz-app

A repository reflecting the progress made on the "How to Build iOS Apps with Swift, TDD & Clean Architecture" YouTube series, by Caio & Mike.

Score
80
โ˜… 435 โ‘‚ 134 โ€”
Swift
struct
struct
isoalloc

A general purpose memory allocator that implements an isolation security strategy to mitigate memory safety issues while maintaining good performance

Score
80
โ˜… 390 โ‘‚ 30 โ€”
C
unagex
unagex
kondense

Automated resources sizing tool for containers in kubernetes

Score
0
โ˜… 368 โ‘‚ 11 โ€”
Go
OnlyTerp
OnlyTerp
openclaw-optimization-guide

Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide.

Score
68
โ˜… 361 โ‘‚ 42 โ€”
JavaScript
EdgeTypE
EdgeTypE
better-deepseek

A powerful browser extension that supercharges DeepSeek Chat with custom tooling, persistent memory, and seamless project scaffolding. Generate and download files, run Python in-browser, create PowerPoint and Excel documents, build multi-file projects as ZIP archives, and manage custom skills and characters.

Score
80
โ˜… 312 โ‘‚ 30 +15/day
JavaScript
Lyellr88
Lyellr88
MARM-Systems

Stop re-explaining yourself to AI. MARM offers persistent memory, cross-agent context sharing, write queues, swarm-ready presets, and compaction for clean recall. Includes a live web dashboard for managing memories, logs, and sessions. MCP connects over HTTP & STDIO and works with major LLMs like Claude, Codex, Grok, Gemini, and other models.

Score
90
โ˜… 305 โ‘‚ 57 โ€”
Python
caura-ai
caura-ai
caura-memclaw

Governed shared memory for AI agent fleets โ€” multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

Score
63
โ˜… 278 โ‘‚ 34 +19/day
Python
zesterer
zesterer
broom

An ergonomic tracing garbage collector that supports mark 'n sweep garbage collection

Score
0
โ˜… 252 โ‘‚ 9 โ€”
Rust
stas00
stas00
ipyexperiments

Automatic GPU+CPU memory profiling, re-use and memory leaks detection using jupyter/ipython experiment containers

Score
0
โ˜… 235 โ‘‚ 14 +1/day
Jupyter Notebook
manuelescobar-dev
manuelescobar-dev
LLM-Tools

Open-source calculator for LLM system requirements.

Score
50
โ˜… 182 โ‘‚ 29 โ€”
Python
tao-hpu
tao-hpu
cognitive-workspace

๐Ÿง  Active memory management system enabling functional infinite context for LLMs through cognitive workspace architecture

Score
0
โ˜… 99 โ‘‚ 11 โ€”
TeX
pinkpixel-dev
pinkpixel-dev
mem0-mcp

โœจ mem0 MCP Server: A memory system using mem0 for AI applications with model context protocl (MCP) integration. Enables long-term memory for AI agents as a drop-in MCP server.

Score
53
โ˜… 98 โ‘‚ 13 +1/day
TypeScript
lerim-dev
lerim-dev
lerim

Compiles AI agent traces and truns them into reusable context.

Score
60
โ˜… 96 โ‘‚ 6 +1/day
Python
bonigarcia
bonigarcia
context-engineering

Context Engineering: Build Consistent, Accurate, Predictable AI Systems

Score
58
โ˜… 95 โ‘‚ 16 +1/day
Python
Gegenbauer
Gegenbauer
CatSpy

Tool for browsing log.

Score
60
โ˜… 88 โ‘‚ 12 +2/day
Kotlin
xuanlinAI
xuanlinAI
overmind

็Ž„้œ–่ถ…่„‘ ยท ๆ— ้‡็ฝ‘็ปœ v4 ้‡ๆž„็‰ˆโ€” 66 ๆจกๅ—6้€š้“ AI ่ฎค็Ÿฅ็ฅž็ป็ณป็ปŸ ยท ่ฃ…ไธ€ๆฌก๏ผŒไฝ ๆ‰€ๆœ‰็š„ AI ๅทฅๅ…ทไปŽๆญคๅ…ฑไบซไธ€ไธชๆฐธ่ฟœไธๅคฑๅฟ†็š„ๅคง่„‘ใ€‚่ทจไผš่ฏ่ฎฐๅฟ† ยท ๅคš Agent ไบ’้€š ยท ่‡ชๅŠจไปฃ็ ๅฎกๆŸฅ ยท ้›ถ้…็ฝฎ

Score
42
โ˜… 83 โ‘‚ 12 โ€”
JavaScript
Anonym0usWork1221
Anonym0usWork1221
C-Android-Memory-Tool

Android Memory Access at Runtime: Reading and Writing Using Memory Files and Maps

Score
40
โ˜… 83 โ‘‚ 29 +1/day
C++
jedisct1
jedisct1
was-not-wasm

A hostile memory allocator to make WebAssembly applications more predictable.

Score
20
โ˜… 83 โ‘‚ 1 โ€”
Rust
tomik395
tomik395
ESP32-AI

Speak to your ESP32 and it speaks back! Your new personal assistance is tiny, highly intelligent, and ready to be built from your home.

Score
0
โ˜… 82 โ‘‚ 10 โ€”
C++
jerrinsg
jerrinsg
go-pmem

Native persistent memory support for Go

Score
0
โ˜… 82 โ‘‚ 6 โ€”
Go
sandst1
sandst1
remind

A memory layer for AI Agents

Score
47
โ˜… 80 โ‘‚ 10 +1/day
Python
vincent-pradeilles
vincent-pradeilles
weakable-self

A Swift micro-framework to easily deal with weak references to self inside closures

Score
20
โ˜… 79 โ‘‚ 7 โ€”
Swift
mohitmishra786
mohitmishra786
BitsAndBytes

A comprehensive systems programming toolkit implementing low-level concepts in C, from memory management to OS internals. Features practical implementations of computer architecture concepts with a focus on performance and hardware interaction.

Score
40
โ˜… 78 โ‘‚ 7 โ€”
C
klundberg
klundberg
Weakify

Provides a way use a method on a class as a closure value that would be referenced by some other component without causing memory leaks.

Score
0
โ˜… 74 โ‘‚ 4 โ€”
Swift
OpenPawz
OpenPawz
openpawz

OpenPawz is a native, offline-first desktop AI platform (Tauri v2 + Rust) that lets you run local models or connect to any compatible provider. It gives you private-by-default agents with hybrid memory, strong security guardrails, and extensibility through built-ins plus n8n community integrations

Score
60
โ˜… 72 โ‘‚ 19 โ€”
Rust
ukkit
ukkit
memcord

๐Ÿง  Self-hosted, privacy-first MCP server for long-term AI memory โ€” save, search & summarize Claude/ChatGPT chat history locally. No cloud, no database.

Score
50
โ˜… 69 โ‘‚ 11 +2/day
Python
openscilab
openscilab
memor

Reproducible Structured Memory for LLMs

Score
26
โ˜… 65 โ‘‚ 4 +1/day
Python
syrin-labs
syrin-labs
syrin-harness

The Python Harness for Production AI Multi-Agent Systems

Score
32
โ˜… 61 โ‘‚ 13 โ€”
Python
Deltaidiots
Deltaidiots
memoripilot

Give Copilot a memory! MemoriPilot provides seamless, persistent context management that makes Copilot aware of your project decisions, progress, and architectural patterns - dramatically improving the relevance and quality of AI assistance.

Score
0
โ˜… 57 โ‘‚ 4 โ€”
TypeScript
howardpen9
howardpen9
hermes-gbrain-bridge

Convert Hermes / OpenClaw agent memory (JSONL sessions, MEMORY.md) to markdown for gBrain ingest

Score
40
โ˜… 55 โ‘‚ 6 +3/day
TypeScript
JingbiaoMei
JingbiaoMei
ATM-Bench

ATM-Bench: A benchmark for long-term personalized memory QA spanning ~4 years of multimodal data (images, videos, emails). Features referential queries, evidence-grounded answering, and multi-source reasoning. Paper: "According to Me: Long-Term Personalized Referential Memory QA"

Score
16
โ˜… 53 โ‘‚ 2 +2/day
Python
avasol
avasol
galadriel-public

A self-hosted Claude agent that actually remembers โ€” verbatim memory palace at zero retrieval cost, Discord + web UI, and 90%-cheaper repeat calls via prompt caching.

Score
21
โ˜… 49 โ‘‚ 8 โ€”
Python
yacine-cherif
yacine-cherif
mcp-server-brainflow-docs

BrainFlow - Shared Team's Memory - Company Brain - MCP server documentation and setup guide

Score
30
โ˜… 48 โ‘‚ 0 โ€”
mem7ai
mem7ai
mem7

Memory layer for AI Agents and OpenClaw powered by Rust

Score
5
โ˜… 38 โ‘‚ 0 โ€”
Rust
ceorkm
ceorkm
kratos-mcp

๐Ÿ›๏ธ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Score
11
โ˜… 37 โ‘‚ 7 +1/day
TypeScript
Felo-Inc
Felo-Inc
memclaw

Persistent project memory for AI coding agents โ€” isolated workspaces per project, web dashboard to review what your agent remembers, team collaboration. Free to use.

Score
20
โ˜… 35 โ‘‚ 6 +1/day
JavaScript
SelfMemory
SelfMemory
SelfMemory

Let your memories live forever by passing your knowledge to the next generation with SelfMemory.

Score
0
โ˜… 33 โ‘‚ 1 โ€”
Python
Toowiredd
Toowiredd
claude-skills-automation

Fully automated memory and context management for Claude Code using hooks - Zero friction, zero context loss

Score
10
โ˜… 32 โ‘‚ 1 โ€”
Shell
Related Topics
#llm#memory#rag#ai#ai-agents#python#mcp#long-term-memory#agents#agent-memory#openclaw#developer-tools

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly