Search Results for "memory" - Page 3
Sort By:
Showing 3192 open source projects for "memory"
View related business solutions-
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.
-
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
1
TavernAI
Atmospheric adventure chat for AI language models
...It allows users to connect to various AI backends, including local and cloud-based models, enabling flexibility in how conversations are generated and managed. The platform supports advanced character creation, allowing users to define personalities, memory, and behavior patterns that influence how the AI responds during interactions. TavernAI includes features such as persistent chat histories, branching conversations, and contextual memory, making it suitable for long-form storytelling, roleplaying, and creative writing. It also provides a rich interface with support for extensions and plugins, enabling users to expand functionality and tailor the experience to specific use cases. -
2
libmdbx
One of the fastest embeddable key-value ACID database
libmdbx (Lightning Memory-Mapped Database Extended) is a high-performance, key-value database library derived from LMDB (Lightning Memory-Mapped Database). It is designed for fast, scalable, and ACID-compliant data storage with minimal resource consumption. -
3
Intel PCM
Intel® Performance Counter Monitor (Intel® PCM)
Intel® Performance Counter Monitor (Intel® PCM) is an application programming interface (API) and a set of tools based on the API to monitor performance and energy metrics of Intel® Core™, Xeon®, Atom™ and Xeon Phi™ processors. PCM works on Linux, Windows, Mac OS X, FreeBSD, DragonFlyBSD and ChromeOS operating systems. -
4
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. -
$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.
-
5
PHP7
PHP7 / Laravel Multi-format Streaming Parser
...DOM loading loads all the documents, making it easy to navigate and parse, and as such provides maximum flexibility for developers. Streaming implies iterating through the document, acts like a cursor, and stops at each element in its way, thus avoiding memory overkill. Thus, when it comes to big files, callbacks will be executed meanwhile file is downloading and will be much more efficient as far as memory is concerned. -
6
beszel
Lightweight server monitoring hub with historical data, docker stats
A lightweight server resource monitoring hub with historical data, docker stats, and alerts. -
7
ZeroClaw
Fast, small, and fully autonomous AI assistant infrastructure
ZeroClaw is a Rust-native autonomous AI agent framework engineered for teams and developers who need highly efficient, secure, and modular AI automation infrastructure that can run reliably in both production and self-hosted environments. It is designed around a trait-based architecture so that model providers, communication channels, memory systems, and tooling integrations can be swapped or extended without rewriting core components, giving engineers flexibility and long-term maintainability. The framework features a compact single binary with fast cold and warm startup times and very low memory overhead, making it suitable even for resource-constrained hardware like small servers or edge devices. ... -
8
Dragonfly
A modern replacement for Redis and Memcached
...Designed to fully utilize the power of modern cloud hardware and deliver on the data demands of modern applications, Dragonfly frees developers from the limits of traditional in-memory data stores. The power of modern cloud hardware can never be realized with legacy software. Dragonfly is optimized for modern cloud computing, delivering 25x more throughput and 12x lower snapshotting latency when compared to legacy in-memory data stores like Redis, making it easy to deliver the real-time experience your customers expect. ... -
9
LVGL
Powerful and easy-to-use embedded GUI library with many widgets
Powerful and easy-to-use embedded GUI library with many widgets, advanced visual effects (opacity, antialiasing, animations), and low memory requirements (16K RAM, 64K Flash). LVGL provides everything you need to create an embedded GUI with easy-to-use graphical elements, beautiful visual effects, and a low memory footprint. LVGL is an open-source graphics library providing everything you need to create an embedded GUI with easy-to-use graphical elements, beautiful visual effects, and a low memory footprint. ... -
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.
-
10
Ruffle
A Flash Player emulator written in Rust
...On the web side, Ruffle is embedded into pages or installed as a browser extension; in the desktop version, it can open .swf files directly or embed them in applications. Because it’s built with memory safety in mind, Ruffle helps avoid many of the security vulnerabilities that plagued classic Flash (buffer overflows, use-after-free, etc.). It strives to support multiple versions of ActionScript (1, 2 and parts of 3) and a wide swath of the Flash API so as much content as possible works unchanged. -
11
Pingora
A library for building fast, reliable and evolvable network services
Pingora is a Rust-based high-performance HTTP proxy and networking framework developed by Cloudflare to eventually replace NGINX. Designed for extreme reliability and memory-safe concurrency, it handles over 40 million requests per second in production and reduces CPU/memory usage significantly compared to traditional web servers. -
12
Zep
Zep: A long-term memory store for LLM / Chatbot applications
Easily add relevant documents, chat history memory & rich user data to your LLM app's prompts. Understands chat messages, roles, and user metadata, not just texts and embeddings. Zep Memory and VectorStore implementations are shipped with your favorite frameworks: LangChain, LangChain.js, LlamaIndex, and more. Automatically embed texts and messages using state-of-the-art opeb source models, OpenAI, or bring your own vectors. -
13
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. ... -
14
Olric
Distributed, in-memory key/value store and cache
A lightweight, distributed in-memory data store designed for key-value caching and ephemeral storage. -
15
H2 Database
H2 is an embeddable RDBMS written in Java
Welcome to H2, the Java SQL database. Very fast, open source, JDBC API. Embedded and server modes; in-memory databases. Browser-based Console application. Small footprint: around 2.5 MB jar file size. Browser-based Console application. Encrypted databases. Fulltext search. Pure Java with small footprint: around 2.5 MB jar file size. ODBC driver. This database can be used in embedded mode, or in server mode. ou may get a security warning from the firewall. -
16
xleak
A fast terminal Excel viewer with an interactive TUI
xleak is a lightweight tool for detecting memory leaks and resource mismanagement in C/C++ programs by tracing heap allocations and deallocations with minimal overhead. It hooks into your program’s allocation functions to observe memory usage patterns, helping developers identify locations where memory was allocated but never freed, which is a common source of bugs and performance issues in unmanaged languages. -
17
OnlineStats.jl
Single-pass algorithms for statistics
OnlineStats does statistics and data visualization for big/streaming data via online algorithms. High-performance single-pass algorithms for statistics and data viz. Updated one observation at a time. Algorithms use O(1) memory. Algorithms use O(1) memory. -
18
ProcDump for Linux
A Linux version of the ProcDump Sysinternals tool
...It gives developers and system administrators a practical way to generate core dumps when an application meets specific performance or diagnostic conditions. The tool is useful when a process is unstable, consumes too much CPU or memory, throws .NET exceptions, crosses thread or file descriptor thresholds, or receives selected signals. It supports immediate dumps, repeated dumps, delayed dumps, and dumps triggered by monitored process behavior. It also includes resource tracking for certain allocation APIs, helping teams investigate memory leaks and unreleased resources. ... -
19
MemU
MemU is an open-source memory framework for AI companions
MemU is an agentic memory layer for LLM applications, specifically designed for AI companions. Transform your memory into an intelligent file system that automatically organizes, connects, and evolves with your memories. Simple, fast, and reliable memory infrastructure for AI applications. Powerful tools and dedicated support to scale your AI applications with confidence. -
20
LazyCodex
The one and only agent harness for complex codebases
LazyCodex is an agent harness for using Codex on complex software projects. It is designed to add structure around AI coding sessions through memory, planning, execution, verification, skills, hooks, routing, and diagnostics. The project helps developers move beyond one-off prompts by giving the agent a more organized workflow inside a codebase. It supports project memory so context can persist across sessions and decisions do not need to be repeatedly reintroduced. LazyCodex also emphasizes verified completion, which means the workflow is built around checking whether tasks are actually finished rather than only generating code. ... -
21
Memobase
Fast backend for long-term AI user memory via structured profiles
Memobase is an open source backend system that enables long-term user memory functionality for AI applications by capturing and structuring information about users across interactions. Its design centers on creating user profiles and recording event timelines, allowing AI systems to remember, understand, and evolve in their behaviour toward individual users over time. Instead of relying purely on traditional embedding-based retrieval or RAG systems, Memobase uses profile and timeline structures to deliver memory that reflects user context efficiently and meaningfully. ... -
22
data.table
Extends base R’s data for high-performance data manipulation
...Relies only on base R; maintained API, active community; good memory efficiency. Non-equi joins, overlapping range joins, ordered joins, joining with aggregations, etc. -
23
Martin
Blazing fast and lightweight PostGIS, MBtiles and PMtiles tile server
Martin is a fast and lightweight tile server for serving vector and raster tiles from PostGIS-enabled PostgreSQL databases. Written in Rust, it is optimized for performance and low memory usage, making it suitable for production geospatial applications. Martin supports modern web mapping standards and integrates seamlessly with MapLibre and other mapping libraries. -
24
Infinispan
Infinispan is an open source data grid platform
Infinispan is a distributed in-memory data grid and caching system designed for high-performance computing. It allows applications to scale dynamically by distributing data across multiple nodes, reducing latency and improving resilience. -
25
SerenityOS
The Serenity Operating System
SerenityOS is an open source Unix-like operating system project with its own custom kernel, graphical user interface, system libraries, and userland tools. It combines a nostalgic “90s UI aesthetic” with modern system capabilities: a preemptive, multi-threaded kernel, own browsers, network stack, file systems, IPC, security features, and a suite of graphical / developer applications. The project is both a hobbyist OS and a polished engineering sandbox.