Showing 3193 open source projects for "memory"

View related business solutions
  • 99.99% Uptime for MySQL and PostgreSQL Databases Icon
    99.99% Uptime for MySQL and PostgreSQL Databases

    Sub-second maintenance. 2x read/write performance. Built-in vector search for AI apps.

    Cloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
    Try Free
  • Build Agents and Models on One Platform Icon
    Build Agents and Models on One Platform

    Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

    Gemini 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.
    Try It Free
  • 1
    Neuron AI

    Neuron AI

    The PHP Agentic Framework to build production-ready AI driven apps

    Neuron AI is a PHP agentic framework for building production-ready AI applications that connect models, memory, vector databases, and tools into working agents. It is designed for developers who want to create systems such as RAG pipelines, multi-agent workflows, and business process automations without having to hand-build every integration from scratch. The framework provides an Agent class that can be extended to inherit core capabilities like memory, tools, function calling, and retrieval-augmented generation. ...
    Downloads: 3 This Week
    Last Update:
    See Project
  • 2
    Anima

    Anima

    Open-source Agent OS for hardware intelligence

    Anima is an open-source Agent OS designed to make hardware behave more intelligently. Instead of acting as a basic smart-home control panel, it gives connected devices perception, memory, decision-making, and extensible AI capabilities. The system runs as an intelligent hardware agent runtime inside the local network. It discovers devices, tracks their state, and controls real hardware through adapters. Anima uses an LLM-powered brain to interpret the environment, user intent, memory, and device-specific skills before planning actions. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 3
    CoPaw

    CoPaw

    Your Personal AI Assistant; easy to install, deploy on local or coud

    ...It includes a browser-based Console for chatting, configuring models, managing memory, and extending capabilities with custom skills. With built-in cron scheduling, heartbeat check-ins, and extensible skill loading, CoPaw grows with your workflow over time. Easy installation options—including pip, one-line scripts, Docker, and cloud deployment—make it accessible for both developers and non-technical users.
    Downloads: 9 This Week
    Last Update:
    See Project
  • 4
    DeepSeek-Reasonix

    DeepSeek-Reasonix

    DeepSeek-native AI coding agent for your terminal

    ...Reasonix includes a coding mode with filesystem and shell tools, a lighter chat mode, one-shot task execution, health checks, session utilities, and project-scoped memory. It supports reviewed SEARCH/REPLACE edits, plan mode, MCP servers, web search, hooks, skills, semantic indexing, transcript replay, event logs, and cost or cache tracking. The project is especially useful for developers who want an open, terminal-first coding agent optimized for DeepSeek’s cache mechanics. It also includes a prerelease desktop client for users who prefer a GUI over the same agent loop.
    Downloads: 21 This Week
    Last Update:
    See Project
  • Host LLMs in Production With On-Demand GPUs Icon
    Host LLMs in Production With On-Demand GPUs

    NVIDIA L4 GPUs. 5-second cold starts. Scale to zero when idle.

    Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
    Try Free
  • 5
    Box64

    Box64

    Linux Userspace x86_64 Emulator with a twist, targeted at ARM64 Linux

    Box86 lets you run x86 Linux programs (such as games) on non-x86 Linux systems, like ARM (the host system needs to be 32bit little-endian). Because box86 uses the native versions of some “system” libraries, like libc, libm, SDL, and OpenGL, it’s easy to integrate and use with most applications, and performance can be surprisingly high in some cases. Many games already work without much tweaking, for example: WorldOfGoo, Airline Tycoon Deluxe, and FTL. Many of the GameMaker Linux games also...
    Downloads: 212 This Week
    Last Update:
    See Project
  • 6
    hhuOS

    hhuOS

    hhuOS - A small operating system

    hhuOS is an educational operating system project developed by students at Heinrich Heine University (HHU) in Düsseldorf, Germany. It is built from scratch in C and Assembly and intended as a teaching tool to help students grasp the foundations of kernel development, memory management, system calls, and multitasking. The project focuses on clarity, modularity, and hands-on experimentation with real OS components, making it suitable for OS development courses or personal exploration.
    Downloads: 4 This Week
    Last Update:
    See Project
  • 7
    PerfView

    PerfView

    PerfView is a CPU and memory performance-analysis tool

    PerfView is a free performance analysis tool that helps isolate CPU and memory-related performance issues. It is a Windows tool, but it also has some support for analyzing data collected on Linux machines. It works for a wide variety of scenarios, but has a number of special features for investigating performance issues in code written for the .NET runtime. If you are unfamiliar with PerfView, there are PerfView video tutorials.
    Downloads: 27 This Week
    Last Update:
    See Project
  • 8
    ZIG

    ZIG

    General-purpose programming language and toolchain

    A general-purpose programming language and toolchain for maintaining robust, optimal, and reusable software.
    Downloads: 15 This Week
    Last Update:
    See Project
  • 9
    Reflexion

    Reflexion

    Reflexion: Language Agents with Verbal Reinforcement Learning

    ...Instead of relying solely on a single-pass response, Reflexion enables agents to evaluate their own outputs, identify errors, and refine their reasoning over multiple iterations, leading to more accurate and reliable results. The framework introduces a mechanism where agents maintain a memory of past attempts and use that memory to guide future decisions, effectively simulating a learning process without requiring traditional model retraining. This approach is particularly useful for complex reasoning tasks, coding challenges, and decision-making scenarios where initial outputs may be incomplete or incorrect. Reflexion also emphasizes transparency by making intermediate reasoning steps explicit, allowing developers to inspect how conclusions are reached and where improvements occur.
    Downloads: 2 This Week
    Last Update:
    See Project
  • Build Securely on Azure with Proven Frameworks Icon
    Build Securely on Azure with Proven Frameworks

    Lay a foundation for success with Tested Reference Architectures developed by Fortinet’s experts. Learn more in this white paper.

    Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
    Download Now
  • 10
    Lossless Claw

    Lossless Claw

    LCM (Lossless Context Management) plugin for OpenClaw

    ...This structure enables agents to dynamically reconstruct detailed context by expanding summaries when needed, effectively simulating perfect long-term memory.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 11
    Claude-Flow

    Claude-Flow

    The leading agent orchestration platform for Claude

    ...The platform supports both quick swarm tasks and persistent multi-agent sessions known as hives, facilitating distributed AI collaboration with persistent contextual memory. At its core, Claude-Flow integrates Dynamic Agent Architecture (DAA) for self-organizing agent management, neural pattern recognition accelerated by WebAssembly SIMD, and a SQLite-based memory system for context retention and knowledge persistence across tasks. It automates development workflows via pre- and post-operation hooks, providing seamless coordination, code formatting, validation, and performance optimization.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 12
    ByteRover CLI

    ByteRover CLI

    The portable memory layer for autonomous coding agents

    ...ByteRover is useful when agents need persistent context instead of starting from scratch every time they enter a project. Its main value is making agent memory more structured, shareable, and practical across teams, tools, and long-running development workflows.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 13
    Claude Subconscious

    Claude Subconscious

    Give Claude Code a subconscious

    Claude Subconscious is an experimental plugin that enhances AI coding workflows by introducing a persistent “memory layer” for Claude Code through integration with Letta’s agent framework. It operates as a background agent that continuously observes user interactions, reads project files, and processes session transcripts to build long-term contextual memory. Unlike standard AI interactions that reset between sessions, this system accumulates knowledge over time, allowing it to recall user preferences, project structures, and recurring patterns across multiple sessions. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 14
    R-KV

    R-KV

    Redundancy-aware KV Cache Compression for Reasoning Models

    ...Modern transformer models rely heavily on KV caches during autoregressive decoding, which store intermediate attention states to accelerate generation. However, these caches can consume large amounts of memory, especially in reasoning-oriented models with long context windows. R-KV introduces a method for compressing the KV cache during decoding, allowing models to maintain reasoning performance while reducing memory consumption and computational overhead. The approach focuses on identifying which attention heads and cache components are most important for maintaining reasoning quality, allowing less critical information to be compressed or discarded. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 15
    Jimfs

    Jimfs

    An in-memory file system for Java 8+

    Jimfs is an in-memory file system for Java that fully implements the java.nio.file API introduced in Java 7 and enhanced in Java 8 and beyond. Developed by Google, it allows developers to create and manipulate file systems entirely in memory, making it ideal for testing, simulation, and temporary file operations without touching the actual disk. Jimfs supports most standard file operations, including file and directory creation, deletion, copying, symbolic and hard links, as well as stream-based file reading and writing. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 16
    Vince's CSV Parser

    Vince's CSV Parser

    A modern C++ library for reading, writing, and analyzing CSV

    ...Furthermore, I wanted support for special use cases such as calculating statistics on very large files. With the deluge of large datasets available, a performant CSV parser is a necessity. By using overlapped threads, memory-mapped IO, and efficient data structures, this parser can quickly tackle large CSV files. Furthermore, this parser has a minimal memory footprint and can handle larger-than-RAM files.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 17
    Autopsy

    Autopsy

    Autopsy® is a digital forensics platform and graphical interface

    ...It can be used by law enforcement, military, and corporate examiners to investigate what happened on a computer. You can even use it to recover photos from your camera's memory card. Autopsy was designed to be intuitive out of the box. Installation is easy and wizards guide you through every step. All results are found in a single tree. See the intuitive page for more details. Autopsy was designed to be an end-to-end platform with modules that come with it out of the box and others that are available from third-parties.
    Downloads: 146 This Week
    Last Update:
    See Project
  • 18
    StaticArrays.jl

    StaticArrays.jl

    Statically sized arrays for Julia

    StaticArrays.jl is a Julia package that provides statically sized arrays with fast, stack-allocated memory storage and optimized performance for small array computations. It is particularly useful in numerical computing where small fixed-size matrices or vectors are used frequently, such as in robotics, physics simulations, or linear algebra. StaticArrays eliminate dynamic memory allocation overhead and enable compile-time optimizations for performance close to hand-written loops.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 19
    PCSX2

    PCSX2

    The Playstation 2 emulator

    ...Its purpose is to emulate the PS2's hardware, using a combination of MIPS CPU Interpreters, Recompilers and a Virtual Machine that manages hardware states and PS2 system memory. This allows you to play PS2 games on your PC, with many additional features and benefits. The PCSX2 project has been running for more than ten years. Past versions could only run a few public domain game demos, but newer versions can run most games at full speed, including popular titles such as Final Fantasy X and Devil May Cry 3. ...
    Downloads: 254 This Week
    Last Update:
    See Project
  • 20
    Vibe-Trading

    Vibe-Trading

    Vibe-Trading: Your Personal Trading Agent

    ...It features a swarm-based architecture with prebuilt expert agent teams for research, trading, and risk management. Advanced backtesting engines provide statistical validation, optimization, and performance metrics. The system also includes persistent memory, enabling it to learn from past interactions and refine strategies over time. Overall, it delivers an end-to-end AI-driven trading environment for both research and execution.
    Downloads: 13 This Week
    Last Update:
    See Project
  • 21
    youki

    youki

    A container runtime written in Rust

    ...However, the container runtime requires the use of system calls, which requires a bit of special handling when implemented in Go. This is too tricky (e.g. namespaces(7), fork(2)); with Rust, it's not that tricky. And, unlike in C, Rust provides the benefit of memory safety. While Rust is not yet a major player in the container field, it has the potential to contribute a lot: something this project attempts to exemplify. youki has the potential to be faster and use less memory than runc, and therefore works in environments with tight memory usage requirements. Here is a simple benchmark of a container from creation to deletion.
    Downloads: 1 This Week
    Last Update:
    See Project
  • 22
    Windrecorder

    Windrecorder

    Windrecorder is a memory search app by records everything

    Windrecorder is an open-source personal memory search engine that continuously records on-screen activity in a highly optimized and storage-efficient format. It captures screen content locally and builds a searchable database using OCR and image understanding, allowing users to rewind and rediscover anything they have previously seen. The system indexes only meaningful visual changes, extracting text, browser data, and contextual information to improve search accuracy and reduce storage overhead. ...
    Downloads: 12 This Week
    Last Update:
    See Project
  • 23
    GmSSL

    GmSSL

    Password toolbox that supports national secret

    ...It supports mainstream operating systems and processors including mobile terminals, and supports cryptographic keys, Cipher cards and other typical domestic cryptographic hardware provide feature-rich command line tools and multiple compiled language programming interfaces. GmSSL 3.0 greatly reduces memory requirements and binary code volume, does not rely on dynamic memory, and can be used in low-power embedded environments (MCU, SOC, etc.) National secret algorithm and SSL protocol are embedded in existing projects. The default CMake build system can be easily used with default compilation tools such as Visual Studio and Android NDK. ...
    Downloads: 3 This Week
    Last Update:
    See Project
  • 24
    NanoClaw

    NanoClaw

    A lightweight alternative to Clawdbot / OpenClaw

    ...The project connects directly to WhatsApp, letting you deploy an assistant that can chat in a familiar interface while still supporting real agent behaviors instead of simple call-and-response prompts. It includes memory so the assistant can retain important context across interactions, enabling more consistent follow-through on ongoing tasks. It also supports scheduled jobs, making it suitable for recurring reminders, periodic automations, and timed workflows without needing an external orchestrator.
    Downloads: 16 This Week
    Last Update:
    See Project
  • 25
    Go Container Registry

    Go Container Registry

    Go library and CLIs for working with container registries

    ...The library handles authentication via a pluggable keychain system that understands Docker config files, credential helpers, and environment credentials. It understands multiple on-disk layouts (tarball, OCI layout, remote) and lets you transform images in memory by adding or rebasing layers, adjusting config, and annotating manifests. Because everything is regular Go code, it’s straightforward to embed in CI/CD systems, policy engines, and bespoke supply-chain tooling.
    Downloads: 22 This Week
    Last Update:
    See Project