Search Results for "memory"
Sort By:
Showing 497 open source projects for "memory"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
1
Memory OS
A 7-layer memory operating system for Hermes Agent
Memory OS is a local memory operating system for Hermes Agent. It is designed to help an AI agent retain project context, decisions, structured facts, reasoning patterns, and prior conversations across sessions. The system uses seven memory layers that combine flat files, SQLite, full-text search, structured facts, semantic recall, Qdrant vector storage, and a self-curating wiki pipeline. -
2
Basic Memory
Persistent AI memory using local Markdown knowledge graphs
Basic Memory creates a semantic knowledge graph by linking related ideas, making it easier to retrieve, expand, and connect information over time. With a local-first design, your data stays private and portable, while optional cloud sync enables cross-device access. It combines simplicity with powerful indexing and search, giving you a flexible way to build long-term memory for projects, research, and workflows. -
3
AirLLM
AirLLM 70B inference with single 4GB GPU
AirLLM is an open source Python library that enables extremely large language models to run on consumer hardware with very limited GPU memory. The project addresses one of the main barriers to local LLM experimentation by introducing a memory-efficient inference technique that loads model layers sequentially rather than storing the entire model in GPU memory. This layer-wise inference approach allows models with tens of billions of parameters to run on devices with only a few gigabytes of VRAM. ... -
4
Retrobios
Complete BIOS and firmware packs for RetroArch, Batocera, Recalbox
...It is designed to provide a minimal firmware layer that initializes hardware and prepares systems to boot, often used for educational purposes or retrocomputing experiments. The project likely explores how early computing systems managed hardware abstraction, memory initialization, and device communication before modern operating systems take control. It emphasizes simplicity and transparency, allowing developers to study and modify core boot processes at a granular level. The architecture is typically close to bare metal, requiring knowledge of assembly language and hardware interfaces. It may also serve as a foundation for building custom operating systems or experimenting with low-level system design. ... -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
5
MemoryOS
MemoryOS is designed to provide a memory operating system
MemoryOS is an open-source framework designed to provide a structured memory management system for AI agents and large language model applications. The project addresses one of the major limitations of modern language models: their inability to maintain long-term context beyond the limits of their prompt window. MemoryOS introduces a hierarchical memory architecture inspired by operating system memory management principles, allowing agents to store, update, retrieve, and generate information from multiple layers of memory. -
6
FlashAttention
Fast and memory-efficient exact attention
FlashAttention is a high-performance deep learning optimization library that reimplements the attention mechanism used in transformer models to be significantly faster and more memory-efficient than standard implementations. It achieves this by using IO-aware algorithms that minimize memory reads and writes, reducing the quadratic memory overhead typically associated with attention operations. The project provides implementations of FlashAttention, FlashAttention-2, and newer iterations optimized for modern GPU architectures such as NVIDIA Hopper and AMD accelerators. ... -
7
MemOS
AI memory OS for LLM and Agent systems
MemOS is an experimental operating system and runtime built around the concept of memory-centric computing, where memory objects are first-class citizens and program execution is organized around efficient, persistent memory access rather than traditional process and file system boundaries. The project explores rethinking system abstractions by tightly coupling computation with memory objects so that programs can operate on large datasets without expensive serialization or context switching. ... -
8
Hindsight
Hindsight: Agent Memory That Learns
Hindsight is an advanced, open-source memory system for AI agents designed to enable long-term learning, reasoning, and consistency across interactions by treating memory as a first-class component of intelligence rather than a simple retrieval layer. It addresses one of the core limitations of modern AI agents, which is their inability to retain and meaningfully use past experiences over time, by introducing a structured, biomimetic memory architecture inspired by how human memory works. ... -
9
ReMe
Memory Management Kit for Agents
ReMe is a memory management kit for AI agents that gives them structured, persistent memory capabilities, enabling agents to extract, store, and reuse information across sessions, tasks, and interactions. It is designed to support long-running agent workflows where context matters and working memory alone isn’t enough, helping agents remember user preferences, task histories, and relevant past observations. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
10
vLLM
A high-throughput and memory-efficient inference and serving engine
vLLM is a fast and easy-to-use library for LLM inference and serving. High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more. -
11
MemPalace
The highest-scoring AI memory system ever benchmarked
MemPalace is an open-source AI memory system designed to solve one of the most persistent limitations of large language models: the loss of context between sessions. Instead of relying on summarization or selective extraction like most memory tools, it takes a radically different approach by storing conversations in their entirety and making them retrievable through structured organization and semantic search. -
12
EverMemOS
Long-term memory OS for AI with structured recall and context awarenes
EverMemOS is an open-source memory operating system built to give AI agents long-term, structured memory. It captures conversations, transforms them into organized memory units, and enables agents to recall past interactions with context and meaning. Instead of treating each prompt independently, it builds evolving user profiles, tracks preferences, and connects related events into coherent narratives. -
13
Operit AI
Powerful Android AI agent with tools, automation, and Linux shell
...Operit supports both local and remote AI models, including offline execution through frameworks like llama.cpp and MNN, helping preserve user privacy while maintaining flexibility. Operit also includes an intelligent memory system that stores, organizes, and retrieves user interactions to provide more personalized and context-aware responses. In addition, it offers workflow automation, plugin extensibility, & a rich tool ecosystem, making it suitable for advanced productivity. -
14
MemMachine
Universal memory layer for AI Agents
MemMachine is a universal memory layer designed for AI agents that provides persistent, rich memory storage and retrieval capabilities so autonomous agent systems can recall context, personal preferences, and long-term interaction history across sessions, models, and use cases. Unlike ephemeral LLM prompt state, MemMachine supports distinct memory types—short-term conversational context, long-term persistent knowledge, and profile memory for personalized facts—persisted in optimized stores (e.g., graph databases for episodic lines of reasoning and SQL for user facts) to support robust, context-aware intelligence in agents. ... -
15
OpenMemory
Local long-term memory engine for AI apps with persistent storage
OpenMemory is a self-hosted memory engine designed to provide long-term, persistent storage for AI and LLM-powered applications. It enables developers to give otherwise stateless models a structured memory layer that can store, retrieve, and manage contextual information over time. OpenMemory is built around a hierarchical memory architecture that organizes data into semantic sectors and connects them through a graph-based structure for efficient retrieval. -
16
MemClaw
Persistent memory for AI agent fleets (OSS)
...It also supports agent integrations through MCP and OpenClaw-style workflows, making it useful for multi-agent systems that need persistent recall. Its architecture goes beyond a simple vector database by adding rules about who can store, retrieve, and share each memory. caura-memclaw is best suited for teams building AI agents that need long-term memory, controlled sharing, compliance awareness, and safer cross-agent coordination. -
17
memsearch
A Markdown-first memory system, a standalone library for any AI agent
memsearch is a markdown-first memory system designed to provide long-term memory capabilities for AI agents through structured storage and semantic retrieval. It enables agents to store, organize, and retrieve information using embeddings and hybrid search techniques, ensuring that relevant context is always available. The system supports advanced features such as reranking and progressive disclosure, which help prioritize the most useful information for a given query. ... -
18
SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents
SimpleMem is a lightweight memory-augmented model framework that helps developers build AI applications that retain long-term context and recall relevant information without overloading model context windows. It provides easy-to-use APIs for storing structured memory entries, querying those memories using semantic search, and retrieving context to augment prompt inputs for downstream processing. -
19
QwenPaw
A personal AI assistant, easy to install
...QwenPaw emphasizes extensibility through modular components that developers can customize for research, personal assistants, automation systems, or enterprise AI workflows. The architecture integrates agent collaboration, planning systems, and long-term contextual memory to create more persistent and adaptive interactions. -
20
Hermes Agent
The agent that grows with you
Hermes Agent is a fully open-source autonomous AI agent designed to run persistently on your own machine or server, becoming more capable the longer it operates by learning from experience and building reusable procedural skills. Rather than functioning as a stateless chatbot, it maintains long-term memory across sessions and can generate searchable “Skill Documents” that capture how it solved complex tasks so it doesn’t start from scratch each time. The agent interfaces with messaging platforms like Telegram, Discord, Slack, and WhatsApp through a single gateway process, and also offers an interactive terminal user interface with history, autocomplete, and streamable tool output. ... -
21
Memori
SQL-native memory layer enabling persistent context for AI agents
Memori is an open source SQL-native memory engine designed to add persistent memory capabilities to AI applications, large language models, and multi-agent systems. It provides a memory layer that automatically captures conversations and interactions between users and AI models, allowing systems to retain knowledge across sessions instead of operating statelessly. It extracts structured information such as facts, preferences, rules, and summaries from interactions and stores them in standard SQL databases for later retrieval. ... -
22
LangChain
⚡ Building applications with LLMs through composability ⚡
Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. But using these LLMs in isolation is often not enough to create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge. This library is aimed at assisting in the development of those types of applications. -
23
Koila
Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code
Koila is a lightweight Python library designed to help developers avoid memory errors when training deep learning models with PyTorch. The library introduces a lazy evaluation mechanism that delays computation until it is actually required, allowing the framework to better estimate the memory requirements of a model before execution. By building a computational graph first and executing operations only when necessary, koila reduces the risk of running out of GPU memory during the forward pass of neural network training. ... -
24
HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
...The framework aims to push the boundaries of video generation quality, incorporating multiple innovative approaches to improve the realism and coherence of the generated content. Release of FP8 model weights to reduce GPU memory usage / improve efficiency. Parallel inference code to speed up sampling, utilities and tests included. -
25
xLSTM
Neural Network architecture based on ideas of the original LSTM
xLSTM is an open-source machine learning architecture that reimagines the classic Long Short-Term Memory (LSTM) network for modern large-scale language modeling and sequence processing tasks. The project introduces a new recurrent neural network design that incorporates exponential gating mechanisms and enhanced memory structures to overcome limitations of traditional LSTM models. By introducing innovations such as matrix-based memory and improved normalization techniques, xLSTM improves the ability of recurrent networks to capture long-range dependencies in sequential data. ...