Showing 74 open source projects for "ram"

View related business solutions
  • Our Free Plans just got better! | Auth0 Icon
    Our Free Plans just got better! | Auth0

    With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

    You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
    Try free now
  • $300 Free Credits to Build on Google Cloud Icon
    $300 Free Credits to Build on Google Cloud

    New customers can spin up VMs, build with AI, and query data at no cost.

    Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
    Start Free
  • 1
    oMLX

    oMLX

    LLM inference server with continuous batching & SSD caching

    ...It serves text models, vision-language models, OCR models, embeddings, and rerankers through OpenAI- and Anthropic-compatible APIs. Continuous batching allows concurrent requests, while a tiered KV cache keeps active data in RAM and moves colder blocks to SSD for reuse. Models can be pinned, unloaded manually, or evicted automatically when memory runs low. A web dashboard provides monitoring, chat, downloads, benchmarks, integrations, and per-model settings. It also supports tool calling, structured output, MCP integration, and experimental multi-Mac inference.
    Downloads: 125 This Week
    Last Update:
    See Project
  • 2
    Edge0

    Edge0

    Run 35B MoE models in ~2.5 GB of RAM

    Edge0 is an open-source inference framework designed to run large mixture-of-experts language models on devices with limited memory. It streams neural network expert weights from SSD storage instead of loading every parameter into RAM. A trained routing predictor anticipates which experts will be needed and loads their weights ahead of execution. Recover-LoRA helps restore model quality after memory-efficient modifications. The framework supports experimental 8B and 35B-class models and targets consumer computers and mobile devices. Platform-specific inference engines are available for macOS, iOS, Android, and Windows. ...
    Downloads: 20 This Week
    Last Update:
    See Project
  • 3
    QualityScaler

    QualityScaler

    Image/video AI upscaler app (BSRGAN)

    Qualityscaler is a Windows app that uses BSRGAN Artificial Intelligence to enhance, enlarge and reduce noise in photographs and videos. QualityScaler is completely written in Python, from the backend to the front end. Image/list of images upscale. Video upscale. Drag&drop files [image / multiple images/video] Automatic image tiling and merging to avoid gpu VRAM limitation. Resize image/video before upscaling. Multiple Gpu support. Compatible images - png, jpeg, bmp, webp, tif. Compatible...
    Downloads: 103 This Week
    Last Update:
    See Project
  • 4
    MESHROOM

    MESHROOM

    3D reconstruction software

    ...Automatically estimate fisheye circle or manually edit it. Take advantage of motorized-head file. Easy to integrate in your Renderfarm System. Add specific rules to select the most suitable machines regarding CPU, RAM, GPU requirements of each Node.
    5.0 out of 5 stars 1 Review
    Downloads: 221 This Week
    Last Update:
    See Project
  • Build Securely on AWS with Proven Frameworks Icon
    Build Securely on AWS 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
  • 5
    mac code

    mac code

    Claude Code, but it runs on your Mac for free

    mac code is a local AI coding agent designed to run large language models directly on Apple Silicon machines without relying on cloud services, effectively transforming a Mac into a self-contained AI development environment. The project focuses on enabling models that traditionally exceed available RAM to run efficiently by streaming model weights from SSD storage, thereby overcoming hardware limitations through innovative memory management techniques. It operates as a CLI-based assistant that routes user prompts into different execution paths such as chat, shell commands, or web search, functioning as a multi-purpose development agent. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 6
    DictDataBase

    DictDataBase

    A python NoSQL dictionary database, with concurrent access and ACID

    DictDataBase (DictDB) is a lightweight, Python-based in-memory database that uses dictionaries as its primary data structure. It provides a simple and efficient way to store, retrieve, and manipulate data without requiring an external database server. DictDB is useful for applications needing fast lookups, temporary storage, or embedded database functionalities.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 7
    gensim

    gensim

    Topic Modelling for Humans

    Gensim is a Python library for topic modeling, document indexing, and similarity retrieval with large corpora. The target audience is the natural language processing (NLP) and information retrieval (IR) community.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 8
    InvokeAI

    InvokeAI

    InvokeAI is a leading creative engine for Stable Diffusion models

    ...It provides a streamlined process with various new features and options to aid the image generation process. It runs on Windows, Mac and Linux machines, and runs on GPU cards with as little as 4 GB or RAM. InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products. This fork is supported across Linux, Windows and Macintosh. ...
    5.0 out of 5 stars 1 Review
    Downloads: 11 This Week
    Last Update:
    See Project
  • 9
    whichllm

    whichllm

    Find the local LLM that actually runs and performs best

    whichllm is a command-line tool for finding local large language models that can realistically run on a user’s hardware. It detects the machine’s available resources, including GPU, CPU, memory, and storage, then recommends models based on practical fit rather than parameter count alone. The project is useful for users who are unsure which local LLM will perform well on their system. It focuses on real, recency-aware benchmarks so recommendations better reflect current model performance....
    Downloads: 0 This Week
    Last Update:
    See Project
  • Custom VMs From 1 to 96 vCPUs With 99.95% Uptime Icon
    Custom VMs From 1 to 96 vCPUs With 99.95% Uptime

    General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.

    Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
    Start Free
  • 10
    Datasets

    Datasets

    Hub of ready-to-use datasets for ML models

    ...We also feature a deep integration with the Hugging Face Hub, allowing you to easily load and share a dataset with the wider NLP community. There are currently over 2658 datasets, and more than 34 metrics available. Datasets naturally frees the user from RAM memory limitation, all datasets are memory-mapped using an efficient zero-serialization cost backend (Apache Arrow). Smart caching: never wait for your data to process several times.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 11
    DESERT OS Linux

    DESERT OS Linux

    Beautiful XFCE distribution

    ... - Smart Updates: Auto-detects the fastest mirrors for quick downloads. Current release: STABLE: DESERT 5.5 - Base: Ubuntu 26.04 LTS - Desktop Environment: XFCE 4.20 System Requirements Minimum: RAM: 3 GB Storage: 20 GB Recommended: RAM: 4 GB or more Storage: 30 GB SSD Site: https://sites.google.com/view/desertoslinux YouTube: https://www.youtube.com/channel/UCcG_7MlTyQJaRYtIIRIxxgA
    Leader badge
    4.4 out of 5 stars 5 Reviews
    Downloads: 1,487 This Week
    Last Update:
    See Project
  • 12
    Echo System Info Viewer

    Echo System Info Viewer

    Simple and lightweight system information viewer for Windows

    Echo System Info Viewer is a lightweight Windows system information viewer that quickly displays essential hardware and system details. The application shows real-time CPU usage, memory (RAM) usage, and disk space information in a simple and clean interface. Unlike heavy monitoring software, Echo System Info Viewer is designed to be extremely fast, minimal, and fully offline. Key benefits: Instant system overview Real-time CPU and RAM usage Disk space information Lightweight and portable No telemetry, no ads Works completely offline Typical use cases: Quickly check CPU and RAM usage View basic system information on Windows Monitor system performance on older computers Lightweight alternative to heavy monitoring tools
    Downloads: 10 This Week
    Last Update:
    See Project
  • 13
    Phantom-Optimizer

    Phantom-Optimizer

    Fast, no-bloat Windows optimizer for better speed and performance.

    Phantom Optimizer is a lightweight Windows optimization tool focused on speed, privacy, and full user control. It offers startup tweaks, junk cleanup, RAM boosts, and performance improvements without bloated UIs or background services. Built for Windows 10/11 and optimized for portable use.
    Leader badge
    Downloads: 33 This Week
    Last Update:
    See Project
  • 14
    ZClicker (AutoClicker)

    ZClicker (AutoClicker)

    A Modern Fully-Fledged Mouse and Keyboard AutoClicker

    ZClicker is a fast, modern, and easy-to-use Windows autoclicker for automating mouse clicks, holds, and keyboard presses. The Free version includes single, double, triple, and hold modes, repeat controls, configurable click intervals, and a global F5 start/stop hotkey. ZClicker Pro adds background window clicking, precise click positions, macro recording and editing, reusable presets, customizable hotkeys, appearance themes, and more. Download ZClicker Free or explore ZClicker Pro...
    Leader badge
    2.5 out of 5 stars 2 Reviews
    Downloads: 4,726 This Week
    Last Update:
    See Project
  • 15
    FeniceOS

    FeniceOS

    Linux live in italiano su Debian 12 e MATE, da chiavetta USB

    ...Include: Professore Digitale (lezioni e quiz di informatica anche offline), LibreOffice, Thunderbird e Claws Mail, Firefox ESR e Falkon, Negozio dei programmi (Debian e Flathub), Fenice Ottimizza per i PC con poca RAM. Nessuna telemetria. Edizione live: i dati non restano allo spegnimento e non c'è un installatore. Requisiti: 64 bit, 2 GB di RAM consigliati, chiavetta da 8 GB. Libretto d'uso e script di costruzione: danilodauria.github.io/feniceos
    Leader badge
    Downloads: 1 This Week
    Last Update:
    See Project
  • 16
    StudioOllamaUI

    StudioOllamaUI

    StudioOllamaUI is a local, portable interface for Ollama

    ...Unzip, run, and that's it. It doesn't clutter your registry or leave traces on your disk. AI for Everyone: No expensive GPU? No problem. Optimized to run smoothly on your CPU and RAM. Total Privacy: Everything stays on your machine. No data leaves for the cloud, and no hidden files are left on your system.
    4.5 out of 5 stars 2 Reviews
    Downloads: 17 This Week
    Last Update:
    See Project
  • 17
    REDACT

    REDACT

    Erase everything. Leave nothing.

    REDACT 4.0.0 is an open-source Windows anti-forensics & artifact sanitization suite that permanently destroys 285 system artifacts — browser history, registry traces, NTFS change journals, Windows Recall AI snapshots, live RAM, and encrypted volume key material. New in 4.0.0: Auto-Trigger Engine — 7 triggers: USB Panic, Login Failure, Dead Man's Switch, VPN Disconnect, WiFi Change, Time Window, Forensic Tool Detection. BitLocker and VeraCrypt header destruction renders encrypted volumes permanently unrecoverable. EFS key wipe and Windows Hello NGC store included. ...
    Downloads: 18 This Week
    Last Update:
    See Project
  • 18
    ALSC - Advanced Linux System Cleaner

    ALSC - Advanced Linux System Cleaner

    Simplify the maintenance and cleaning of Linux systems.

    This program was developed to facilitate maintenance and cleaning of Linux systems.
    5.0 out of 5 stars 2 Reviews
    Downloads: 11 This Week
    Last Update:
    See Project
  • 19
    PC Workman HCK

    PC Workman HCK

    AI-powered PC monitoring that explains. Not shows numbers/spikes.

    ... -9-layer routing, learns your usage patterns over weeks. -TURBO mode: one click stops unnecessary services (Gaming/Work/Economy profiles), switches power plan, flushes RAM, freezes idle apps. -One click restores everything. -Thermal Baseline: learns normal temperatures per workload type. 72C while gaming? Normal. 72C on idle? Alert. -Voltage monitoring with industrial-grade anomaly detection (Nelson Rules SPC). -Ghost Driver Hunter: finds old drivers from hardware you removed years ago. -DeepMonitor: HWMonitor-style sensor table with 90-day SQLite history. 373 process definitions. ...
    5.0 out of 5 stars 10 Reviews
    Downloads: 14 This Week
    Last Update:
    See Project
  • 20
    PyMapStitcher-3---Cuda-Maps-Downloader

    PyMapStitcher-3---Cuda-Maps-Downloader

    A low ram maps downloader to keep your ram free.

    PyMapStitcher 3 is a desktop application for downloading, stitching, and exporting very large satellite map areas as GeoTIFF/BigTIFF files. The software supports GPU acceleration with NVIDIA CUDA and CuPy, direct GeoTIFF georeferencing, WebView-based map selection, and high-performance tile processing for large-scale mapping workflows.
    5.0 out of 5 stars 1 Review
    Downloads: 0 This Week
    Last Update:
    See Project
  • 21
    Maginat

    Maginat

    MAGINAT OS - Independent Linux distribution (LFS)

    ...It ships as a live ISO with a graphical installer (English, Italian and Spanish), runs with Secure Boot enabled, and offers optional LUKS disk encryption and dual-boot with other systems. It uses the 6.18 LTS kernel, includes an app store and printing support, and keeps the desktop lightweight (about 270 MB of RAM at idle in a virtual machine). Source code and website: https://github.com/Aleps31/Maginat
    Downloads: 30 This Week
    Last Update:
    See Project
  • 22
    SEZOY

    SEZOY

    Windows deployment platform for USB/NETWORK boot, zero-touch

    SEZOY turns any Windows PC into a network boot server with a web dashboard. Client machines - physical or virtual - boot over the LAN using Legacy PXE, UEFI PXE, iPXE, or wired/wireless UEFI HTTP Boot, with SecureBoot ON supported via signed boot files. From one boot menu, each machine can install Windows fully unattended or live-boot dozens of Linux distros (Ubuntu, Debian, Kali, Arch, Fedora/Rocky, Mint and more), using pristine ISOs with no USB sticks and no ISO patching. SEZOY runs in...
    5.0 out of 5 stars 1 Review
    Downloads: 30 This Week
    Last Update:
    See Project
  • 23
    BerOS

    BerOS

    Minimal Debian-based Remote thin client OS (RDP/VNC/SSH Support)

    BerOS is a minimal, bootable Debian 12 (Bookworm) Live OS designed to turn any PC into a secure RDP thin client. Booting straight into a lightweight Openbox session, it launches a custom RDP portal. Key Features: * High-Performance RDP: Powered by FreeRDP with RemoteFX, client-side audio, clipboard sync, and auto-resolution. * Dual-Security Modes: User Mode locks settings. Admin Mode (default pass: admin) allows modifying connections, network (DHCP/Static IP via NetworkManager), and...
    Leader badge
    Downloads: 91 This Week
    Last Update:
    See Project
  • 24
    Petoron-P2P-Messenger

    Petoron-P2P-Messenger

    minimalistic, secure and autonomous P2P messenger

    Petoron P2P Messenger (P-P2P-M) Architecture: Pure P2P - no servers, no databases Key storage: Keys generated in memory, never stored, erased after use Metadata: Only IP and port exist during the session - everything else is encrypted & obfuscated Encryption: PQS v1.2 - PBKDF2-HMAC-SHA256 (200k), BLAKE2s-MAC, custom stream cipher + fake padding Authentication: BLAKE2s-MAC (16 bytes) - instant failure on any data change Packet obfuscation: --stealth mode - padding, hidden structures Connection: Direct peer-to-peer only Anonymity: No accounts, logins, or phone numbers Third-party access: Impossible without physical access to both peers during session History: No storage — all in RAM, wiped on close Message size: Limited only by RAM & MTU — no artificial limits External dependencies: None DPI/blocking resistance: Harder to detect, can be masked Autonomy: Fully offline until peers connect 26.01.26 Add pqs_chat_tor.py github.com/01alekseev/Petoron-P2P-Messenger
    Downloads: 0 This Week
    Last Update:
    See Project
  • 25

    GromacsProSuite

    Graphical User Interface for Gromacs

    ...The software automates tasks such as topology generation, solvation, ion addition, minimization, equilibration, and production runs while executing GROMACS commands in the background. Built-in monitoring tracks CPU, RAM, and disk usage to ensure stable performance during parallel processing. Beyond simulation execution, it includes advanced trajectory processing and analysis tools such as RMSD, RMSF, SASA, clustering, PCA, hydrogen-bond analysis, Ramachandran plots, and FEL mapping. With integrated visualization and plotting utilities, it offers a unified platform for researchers, educators, and students to perform complete MD workflows efficiently and reproducibly. ...
    5.0 out of 5 stars 8 Reviews
    Downloads: 11 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • 2
  • 3
  • Next