Search Results for "disk"
Sort By:
Showing 35 open source projects for "disk"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
1
Colibrì
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine
...Colibri includes terminal chat, an OpenAI-compatible text API, and a browser client, but disk-bound generation can be slow on cold caches. -
2
whisper.cpp
Port of OpenAI's Whisper model in C/C++
...The command downloads the base.en model converted to custom ggml format and runs the inference on all .wav samples in the folder samples. whisper.cpp supports integer quantization of the Whisper ggml models. Quantized models require less memory and disk space and depending on the hardware can be processed more efficiently. -
3
Text Generation Web UI
Oobabooga - The definitive Web UI for local AI, with powerful features
...Advanced chat features (send images, get audio responses with TTS). Very efficient text streaming. Parameter presets, 8-bit mode. Layers splitting across GPU(s), CPU, and disk. CPU mode, FlexGen, DeepSpeed ZeRO-3, API with streaming and without streaming. LLaMA model, including 4-bit GPTQ. RWKV model, LoRA (loading and training), Softprompts, and extensions. -
4
Paperless-ngx
A community-supported supercharged version of paperless
Paperless-ngx is a community-supported open-source document management system that transforms your physical documents into a searchable online archive so you can keep, well, less paper. -
$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
Kimi K3 in C
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU
...It demonstrates inference from a roughly 1.56 TB checkpoint with measured memory use as low as 8.24 GB. The runtime streams model trunk layers and routed experts from disk instead of keeping all weights resident in memory. Memory presets balance pinned layers and an expert LRU cache for laptops, desktops, workstations, and servers. Incremental generation preserves KV cache and recurrent state between tokens. The repository also includes tokenization, safetensors loading, diagnostics, benchmarks, trace replay, and comparisons against a PyTorch reference. -
6
FlexLLMGen
Running large language models on a single GPU
...Instead of requiring expensive multi-GPU systems, the framework uses techniques such as memory offloading, compression, and optimized batching to run large models on commodity hardware. The architecture distributes computation and memory usage across the GPU, CPU, and disk in order to maximize the number of tokens processed during inference. This design allows organizations to deploy powerful language models for high-volume tasks without the infrastructure costs typically associated with large-scale AI systems. The project is particularly useful for workloads that prioritize throughput over latency, including benchmarking experiments and large corpus analysis. -
7
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
LMCache is an extension layer for LLM serving engines that accelerates inference, especially with long contexts, by storing and reusing key-value (KV) attention caches across requests. Instead of rebuilding KV states for repeated or shared text segments, LMCache persists and retrieves them from multiple tiers—GPU memory, CPU DRAM, and local disk—then injects them into subsequent requests to reduce TTFT and increase throughput. Its design supports reuse beyond strict prefix matching and enables sharing across serving instances, improving efficiency under real multi-tenant traffic. The broader project includes examples, tests, a server component, and public posts describing cross-engine sharing and inter-GPU KV transfers. ... -
8
VectorChord
Scalable, fast, and disk-friendly vector search in Postgres
VectorChord is an open-source vector database built for local and edge deployment. It supports efficient vector indexing and retrieval using ANN (approximate nearest neighbor) algorithms and is optimized for integration with LLM and AI applications. VectorChord is lightweight and can be embedded in a variety of environments for fast semantic search. -
9
Genie AI
Your best AI pair programmer in VS Code
Your best AI pair programmer. Save conversations and continue any time. A Visual Studio Code - ChatGPT Integration. Supports, GPT-4o GPT-4 Turbo, GPT3.5 Turbo, GPT3, and Codex models. Create new files, and view diffs with one click; your copilot to learn code, add tests, find bugs, and more. -
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
MCP Monitor
A system monitoring tool that exposes system metrics
The MCP System Monitor is a tool that exposes system metrics via the Model Context Protocol (MCP), allowing Large Language Models (LLMs) to retrieve real-time system information through an MCP-compatible interface. -
11
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.... -
12
Acontext
Context data platform for building observable, self-learning AI agents
Acontext is a cloud-native context data platform designed to support the development and operation of advanced AI agents. It provides a unified system to store and manage contexts, multimodal messages, artifacts, and task workflows, enabling developers to engineer context effectively for their agent products. The platform observes agent tasks and user feedback in real time, offering robust observability into workflows and helping teams understand how agents perform over time. Acontext also... -
13
WASTE
Run the full 2.78-trillion-parameter Kimi K3 model
...It keeps the shared model trunk in memory and streams only the experts selected for each token from fast NVMe storage. A bounded cache reuses recently needed experts, while lookahead routing begins disk reads before the next layer requires them. Its main target is the full 2.78-trillion-parameter Kimi K3 model, including multimodal image input. The engine has no third-party runtime dependency on its CPU inference path and exposes both a CLI and C library. An optional server provides an OpenAI-compatible chat API with streaming, tools, structured output, and image support. ... -
14
LEANN
Local RAG engine for private multimodal knowledge search on devices
...LEANN introduces a storage-efficient approximate nearest neighbor index combined with on-the-fly embedding recomputation to avoid storing large embedding vectors. By recomputing embeddings during queries and using compact graph-based indexing structures, LEANN can maintain high search accuracy while minimizing disk usage. It aims to act as a unified personal knowledge layer that connects different types of data such as documents, code, images, and other local files into a searchable context for language models. -
15
Kong
The Cloud-Native API Gateway
Kong is a next generation cloud-native API platform for multi-cloud and hybrid organizations. When building for the web, mobile, or Internet of Things, you’ll need a common functionality to run your software, and Kong is that solution. Kong acts as a gateway, connecting microservices requests and APIs natively while also providing load balancing, logging, monitoring, authentication, rate-limiting, and so much more through plugins. Kong is highly extensible as well as platform agnostic,... -
16
AnyTXT Searcher
A Powerful Desktop Full-Text Search Engine, Just Like Local Google.
...You can quickly find any text in any file on your disk by Anytxt almost in 0.1 second. It works on Windows 11,10, 8, 7, Vista, XP, 2008, 2012, 2016,2022... AnyTXT Searcher supports the following file formats: Plain text (txt, cpp, py, html, etc.) Microsoft OneNote (one) Microsoft Word (doc, docx) Microsoft Excel (xls, xlsx) Microsoft PowerPoint (ppt, pptx) PDF WPS Office (wps, et, dps) EBook (epub, mobi, azw3, fb2 etc.) -
17
StudioOllamaUI
StudioOllamaUI is a local, portable interface for Ollama
...No Python, no libraries, no drama. 100% Portable: Just like a portable browser. 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. -
18
OnnxStream
Lightweight inference library for ONNX files, written in C++
The challenge is to run Stable Diffusion 1.5, which includes a large transformer model with almost 1 billion parameters, on a Raspberry Pi Zero 2, which is a microcomputer with 512MB of RAM, without adding more swap space and without offloading intermediate results on disk. The recommended minimum RAM/VRAM for Stable Diffusion 1.5 is typically 8GB. Generally, major machine learning frameworks and libraries are focused on minimizing inference latency and/or maximizing throughput, all of which at the cost of RAM usage. So I decided to write a super small and hackable inference library specifically focused on minimizing memory consumption: OnnxStream. ... -
19
Aviary
Ray Aviary - evaluate multiple LLMs easily
...Providing an extensive suite of pre-configured open source LLMs, with defaults that work out of the box. Supporting Transformer models hosted on Hugging Face Hub or present on local disk. Aviary has native support for autoscaling and multi-node deployments thanks to Ray and Ray Serve. Aviary can scale to zero and create new model replicas (each composed of multiple GPU workers) in response to demand. Ray ensures that the orchestration and resource management is handled automatically. Aviary is able to support hundreds of replicas and clusters of hundreds of nodes, deployed either in the cloud or on-prem. -
20
YYeTsBot
Renren Film and Television bot, fully connected to Renren resources
Renren Film and Television bot, fully connected to all Renren Film and television resources without deletion of resources. The database of this site is permanently open source and free. You can directly send the name of the episode you want to watch, and you can choose to share the webpage or link (ed2k and magnet links). When searching for resources, it will be searched according to my predetermined priority (everyone video offline, subtitle man), of course, you can also use commands to... -
21
VAMS
Virtual Assistant Maintenance System
Virtual Assistant Maintenance System also knowns as VAMS is an AI software application, that helps users with some computer maintenance issues. Application Requirements: Operating System: Windows 8.1/10 /11 Processor: Intel Core i5 or equivalent RAM: 4GB or higher Free Disk Space: 500MB -
22
Voice Cloning App
A Python/Pytorch app for easily synthesising human voices
...Firstly, you'll need to find a deep speech model for your language by going to coqui. You'll then need to download the model.pbmm and alphabet.txt files for your language. Requires Windows 10 or Ubuntu 20.04+ operating system, 5GB+ Disk space, and NVIDIA GPU with at least 4GB of memory & driver version 456.38+ (optional). Automatic dataset generation (with support for subtitles and audiobooks) Additional language support. Local & remote training. Easy train start/stop. Data importing/exporting. -
23
gImageReader
A graphical frontend to tesseract-ocr
gImageReader is a simple Gtk/Qt front-end to tesseract. Features include: - Import PDF documents and images from disk, scanning devices, clipboard and screenshots - Process multiple images and documents in one go - Manual or automatic recognition area definition - Recognize to plain text or to hOCR documents - Recognized text displayed directly next to the image - Post-process the recognized text, including spellchecking - Generate PDF documents from hOCR documents **Note**: This page is only a mirror for the downloads. ... -
24
Paperless-ng
A supercharged version of paperless, scan, index and archive docs
Paperless is a simple Django application running in two parts, a Consumer (the thing that does the indexing) and a Web server (the part that lets you search & download already-indexed documents). Paper is a nightmare. Environmental issues aside, there’s no excuse for it in the 21st century. It takes up space, collects dust, doesn’t support any form of a search feature, indexing is tedious, it’s heavy and prone to damage & loss. I wrote this to make “going paperless” easier. I do not have to... -
25
DownloadBot
A distributed cross-platform Telegram Bot
A distributed cross-platform Telegram Bot that can control your Aria2 server, control server files and also upload to OneDrive / Google Drive. This project is mainly to use a small hard disk server for offline downloading, for large BitTorrent files to be downloaded in sections according to the size of the hard disk, each time downloading a part, then uploading the network disk, deleting and then downloading the other parts, until all the files are downloaded. At the same time, communication via the bot protocol facilitates use on machines that cannot intranet penetration and simplifies the usual use of download programs for added convenience. ...