Search Results for "zero" - Page 76
Sort By:
Showing 1900 open source projects for "zero"
View related business solutions-
$300 Free Credits to Build on Google CloudPut 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.
-
Build Data Resilience - Take the Assessment TodayIs your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
-
1
Oct.0 Nikon Z remote control app
Advanced Remote control and tethering app for Nikon Z ML cameras
Based on Nikon SDK C# wrapper and EMGU repositories - Oct.0 is a standalone Windows 64bit lightweight app, developed to remotely control select Nikon Z Mirrorless camera bodies by means of wired or wireless controllers attached to a x64 PC. Oct.0 allows for replicating most of the camera body controls (buttons) functions via GUI buttons or keyboard shortcuts, as well as allowing tethering functions such as saving the files to destination folder on a PC, and invoking a remote LiveView session. -
2
Zero-Trust-File-Access-Demo
Zero Trust architecture at the file system level
Implement the Zero Trust File Access Control with encryption enabled, it can enhance the file security. By default all files will be encrypted automatically, all processes or users can't read the encrypted files, they will get the raw encrypted data. You can authorize the processes or users to access these encrypted files. EaseFilter File Control Filter Driver allows you to control the file I/O operations with the filter rule configuration by setting the whitelist and blacklist processes or users, you can allow or block the specific file I/O operation to the specific process or user, you can control who can read your file, allow or block the file modification, prevent your important file from being deleted, renamed. -
3
LongCat-2.0
Trillion-parameter MoE model for coding and million-token reasoning
LongCat-2.0 is Meituan’s flagship open-weight Mixture-of-Experts language model designed for frontier-scale coding, reasoning, and autonomous agent workflows. It features 1.6 trillion total parameters with approximately 48 billion activated per token, combining high capability with efficient sparse inference. The model was pretrained on more than 35 trillion tokens and trained entirely on a large-scale cluster of domestically developed AI accelerators, demonstrating stable frontier-scale... -
4
ROTMG Script is an auto-it script built and compiled to automate some of the tasks in ROTMG. Current features: + auto-heal (0-100% HP setting - using spells currently) + auto-nexus (0-100% HP setting) + item recognition/database - ~50% done + auto-loot - ~50% done Updates to come + auto-heal with potions +
-
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.
-
5
CLIP-ViT-bigG-14-laion2B-39B-b160k
CLIP ViT-bigG/14: Zero-shot image-text model trained on LAION-2B
...Developed by LAION and trained by Mitchell Wortsman on Stability AI’s compute infrastructure, it pairs a ViT-bigG/14 vision transformer with a text encoder to perform contrastive learning on image-text pairs. This model excels at zero-shot image classification, image-to-text and text-to-image retrieval, and can be adapted for tasks such as image captioning or generation guidance. It achieves an impressive 80.1% top-1 accuracy on ImageNet-1k without any fine-tuning, showcasing its robustness in open-domain settings. Its training dataset is uncurated and web-sourced, meaning it reflects the biases and risks of large-scale internet data. ... -
6
Ling 3.0 Tiny
Lightweight MoE model for local reasoning, coding, and AI agents
Ling-3.0-tiny is inclusionAI’s lightweight hybrid reasoning Mixture-of-Experts model, designed to provide capable reasoning and agentic performance at low inference cost. It contains 7.9B total parameters while activating only 1.3B per token, using a hybrid architecture that alternates Kimi Delta Attention and Multi-Head Latent Attention with a sparse 128-expert MoE. The model supports both fast responses and configurable multi-step thinking, covering general agents, coding, mathematics,... -
7
LocalLLM Studio
Chat with local GGUF LLMs on your own machine
Chat with local GGUF LLMs on your own machine — private, offline, model-agnostic. LLM Apps & Agents Apache-2.0 v1.0.5 100% AI-built 0 0 Get LocalLLM Studio View source Website Run open-weight language models (GGUF) fully offline on your own hardware via llama.cpp: a chat interface with system prompts, conversation history, adjustable sampling, and simple retrieval over your own files. You supply the model file — nothing is sent to any server. At a glance Downloads 0 Views 5 Rating No ratings yet License Apache-2.0 Built by Python (tkinter + CLI), llama-cpp-python Branch main Updated Sep 4, 2026 Screenshots Releases All artifacts are signed — verify your download . ... -
8
fashion-clip
CLIP model fine-tuned for zero-shot fashion product classification
FashionCLIP is a domain-adapted CLIP model fine-tuned specifically for the fashion industry, enabling zero-shot classification and retrieval of fashion products. Developed by Patrick John Chia and collaborators, it builds on the CLIP ViT-B/32 architecture and was trained on over 800K image-text pairs from the Farfetch dataset. The model learns to align product images and descriptive text using contrastive learning, enabling it to perform well across various fashion-related tasks without additional supervision. ... -
9
Quick Mail
A full-featured desktop email client
A full-featured desktop email client — IMAP, POP, calendars and chat, with no account requirements and nothing phoning home. Email Clients & Tools MPL-2.0 v140.13.0esr 100% AI-built 0 0 Get Quick Mail View source Website Quick Mail is a complete desktop email client built from the Thunderbird open-source project. Full IMAP/POP/SMTP support, OpenPGP end-to-end encryption, calendars and address books, RSS, and multi-account management — rebranded and configured by QuickOpen with telemetry and data-reporting disabled at build time. ... -
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.
-
10
XTTS-v2
Multilingual voice cloning model with 6-second voice samples
XTTS-v2 is an open-source multilingual text-to-speech and voice cloning model developed by Coqui. It enables zero-shot voice cloning using as little as six seconds of reference audio, allowing users to generate speech that closely matches a target speaker without additional training. The model supports 17 languages and can perform cross-language voice cloning, meaning a voice recorded in one language can be used to synthesize speech in another while preserving speaker identity. ... -
11
OpenVLA 7B
Vision-language-action model for robot control via images and text
...It takes camera images and natural language instructions as input and outputs normalized 7-DoF robot actions, enabling control of multiple robot types across various domains. Built on top of LLaMA-2 and DINOv2/SigLIP visual backbones, it allows both zero-shot inference for known robot setups and parameter-efficient fine-tuning for new domains. The model supports real-world robotics tasks, with robust generalization to environments seen in pretraining. Its actions include delta values for position, orientation, and gripper status, and can be un-normalized based on robot-specific statistics. ... -
12
granite-timeseries-ttm-r2
Tiny pre-trained IBM model for multivariate time series forecasting
...Unlike massive foundation models, TTM models are designed to be lightweight yet powerful, with only ~805K parameters, enabling high performance even on CPU or single-GPU machines. The r2 version is pre-trained on ~700M samples (r2.1 expands to ~1B), delivering up to 15% better accuracy than the r1 version. TTM supports both zero-shot and fine-tuned forecasting, handling minutely, hourly, daily, and weekly resolutions. It can integrate exogenous variables, static categorical features, and perform channel-mixing for richer multivariate forecasting. The get_model() utility makes it easy to auto-select the best TTM model for specific context and prediction lengths. ... -
13
llms-txt-gen
CLI to generate a clean llms.txt so AI assistants find your site.
A zero-dependency Node CLI that generates an llms.txt file for your website, so AI assistants like ChatGPT and Perplexity can find your most important pages. Part of the FixAEO toolkit for AI search visibility. More at fixaeo.com. -
14
VaultGemma
VaultGemma: 1B DP-trained Gemma variant for private NLP tasks
...Training ran on TPU v6e using JAX and Pathways with privacy-preserving algorithms (DP-SGD, truncated Poisson subsampling) and DP scaling laws to balance compute and privacy budgets. Benchmarks on the 1B pre-trained checkpoint show expected utility trade-offs (e.g., HellaSwag 10-shot 39.09, BoolQ 0-shot 62.04, PIQA 0-shot 68.00), reflecting its privacy-first design. -
15
-
16
vaultkeepr
Decentralized zero-knowledge password manager with IPFS storage.
...Unique features include on-chain digital inheritance via smart contracts on Base L2 (gasless, ERC-4337), built-in TOTP authenticator, breach monitoring via HIBP k-anonymity, encrypted document vault with NFC scanning, and email alias generation. Available on Chrome, Firefox, and iOS. Android is in private beta. Built by a solo developer. Fully open-source, zero telemetry. -
17
unidepth-v2-vitl14
Metric monocular depth estimation (vision model)
Estimates absolute (metric) depth from single RGB images, along with camera intrinsics and uncertainty. Designed to generalize across domains (zero-shot) using a self‑prompting camera module and pseudo-spherical prediction space. -
18
GREECE
https://cse.google.gr/cse/publicurl?cx=015705803977090371190:fjdqrltw2bs#gsc.tab=0
-
19
CloudTierSDK
CloudTier Storage Tiering SDK
...The migration of files to the cloud happens transparently and securely, with no disruption to existing applications or infrastructure. The SDK uses on-premises storage as Tier 0 (hot storage) and cloud storage as Tier 1 (cold storage). Cooler or less frequently accessed data is automatically moved to cloud storage, freeing up local storage capacity. Your applications can continue to access all files as if they reside locally—no changes to your code or workflow are required. -
20
Reactive Resume
A one-of-a-kind resume builder that keeps your privacy in mind. Comple
Reactive Resume is a free and open-source resume builder that simplifies the process of creating, updating, and sharing your resume. With zero user tracking or advertising, your privacy is a top priority. The platform is extremely user-friendly and can be self-hosted in less than 30 seconds if you wish to own your data completely. It's available in multiple languages and comes packed with features such as real-time editing, dozens of templates, drag-and-drop customisation, and integration with OpenAI for enhancing your writing. ... -
21
Qwen3-Next
Qwen3-Next: 80B instruct LLM with ultra-long context up to 1M tokens
...The model natively supports a context length of 262K tokens and can be extended up to 1 million tokens using RoPE scaling (YaRN), making it highly capable for processing large documents and extended conversations. Multi-Token Prediction (MTP) boosts both training and inference, while stability optimizations such as weight-decayed and zero-centered layernorm ensure robustness. Benchmarks show it performs comparably to larger models like Qwen3-235B on reasoning, coding, multilingual, and alignment tasks while requiring only a fraction of the training cost. -
22
Cake Fuzzer
Security testing tool for CakePHP based web applications
...The goals of the project are: - create an automated process of discovering vulnerabilities in applications based on the CakePHP Framework; - no application knowledge requirement or pre-configuration of the web application; - result with minimal or close to 0 amount of false positives; - require minimal security knowledge to run the scanner. -
23
alefa
alefa: Control the launch and execution of other programs.
"alefa" is a command line utility that allows to control the launch and execution of other programs. "alefa" means "run", "go", "launch" or "execute" in malagasy language. It is often useful to write (more or less) simple scripts to rerun some commands until they "succeed", or to launch other commands indefinitely. There are numerous common use cases. Such things should be easily automated so that we can do other tasks without being distracted and without having to restart such... -
24
filepilot-enterprise-vault
Self-hosted vault for team server credentials & audit logging
https://abhibagul.github.io/filepilot/enterprise.html FilePilot Enterprise Vault is a free, open-source, self-hosted credential server for teams that need shared access to FTP, SFTP, FTPS, SCP, S3, and WebDAV servers — without passing around passwords. Admins provision encrypted connection profiles once, then issue scoped, revocable access tokens to teammates instead of raw credentials. Credentials are protected with two-tier AES-256-GCM envelope encryption, organized into isolated Vault... -
25
chess-viewer
Free, no-signup chess diagram generator. Paste a FEN, customize the bo
ChessViewer is a free, modern, browser-based chess diagram editor. Set up any position via drag-and-drop or FEN, customize the board, and instantly export high-quality images (PNG, JPEG, SVG) for books, blogs, or videos. No installation or account required.
