#Memory-management
Showing 60 of 61 repositories tagged #memory-management, ranked by stars
Universal memory layer for AI Agents
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.
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.
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
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.
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
Find memory issues & leaks in your iOS app without instruments
AI on the way. An RDBMS approach to deep learning. Declarative, explainable, scalable, optimizable, easy to deploy, all that good stuff.
Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
๐ Pushing the boundaries of simplicity
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
Bringing the hell of pointers to Python.
A list of AI memory projects
An Innovative Agent Framework Driven by KG Engine
An AI memory layer with short- and long-term storage, semantic clustering, and optional memory decay for context-aware applications.
:books:Translate the distinct technical blogs. Please star or watch. Welcome to join me.
Automatic memory consolidation for OpenClaw agents โ like sleep for your AI. Powered by MyClaw.ai
A memory arena implementation for Go.
Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.
Memory Management ToolKit
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.
A repository reflecting the progress made on the "How to Build iOS Apps with Swift, TDD & Clean Architecture" YouTube series, by Caio & Mike.
A general purpose memory allocator that implements an isolation security strategy to mitigate memory safety issues while maintaining good performance
Automated resources sizing tool for containers in kubernetes
Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide.
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.
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.
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.
An ergonomic tracing garbage collector that supports mark 'n sweep garbage collection
Automatic GPU+CPU memory profiling, re-use and memory leaks detection using jupyter/ipython experiment containers
Open-source calculator for LLM system requirements.
๐ง Active memory management system enabling functional infinite context for LLMs through cognitive workspace architecture
โจ 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.
Compiles AI agent traces and truns them into reusable context.
Context Engineering: Build Consistent, Accurate, Predictable AI Systems
Tool for browsing log.
็้่ถ ่ ยท ๆ ้็ฝ็ป v4 ้ๆ็โ 66 ๆจกๅ6้้ AI ่ฎค็ฅ็ฅ็ป็ณป็ป ยท ่ฃ ไธๆฌก๏ผไฝ ๆๆ็ AI ๅทฅๅ ทไปๆญคๅ ฑไบซไธไธชๆฐธ่ฟไธๅคฑๅฟ็ๅคง่ใ่ทจไผ่ฏ่ฎฐๅฟ ยท ๅค Agent ไบ้ ยท ่ชๅจไปฃ็ ๅฎกๆฅ ยท ้ถ้ ็ฝฎ
Android Memory Access at Runtime: Reading and Writing Using Memory Files and Maps
A hostile memory allocator to make WebAssembly applications more predictable.
Speak to your ESP32 and it speaks back! Your new personal assistance is tiny, highly intelligent, and ready to be built from your home.
Native persistent memory support for Go
A memory layer for AI Agents
A Swift micro-framework to easily deal with weak references to self inside closures
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.
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.
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
๐ง Self-hosted, privacy-first MCP server for long-term AI memory โ save, search & summarize Claude/ChatGPT chat history locally. No cloud, no database.
Reproducible Structured Memory for LLMs
The Python Harness for Production AI Multi-Agent Systems
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.
Convert Hermes / OpenClaw agent memory (JSONL sessions, MEMORY.md) to markdown for gBrain ingest
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"
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.
BrainFlow - Shared Team's Memory - Company Brain - MCP server documentation and setup guide
Memory layer for AI Agents and OpenClaw powered by Rust
๐๏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.
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.
Let your memories live forever by passing your knowledge to the next generation with SelfMemory.
Fully automated memory and context management for Claude Code using hooks - Zero friction, zero context loss