Search Results for "visual-" - Page 6
Sort By:
Showing 530 open source projects for "visual-"
View related business solutions-
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
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.
-
1
Phi-3-MLX
Phi-3.5 for Mac: Locally-run Vision and Language Models
Phi-3-Vision-MLX is an Apple MLX (machine learning on Apple silicon) implementation of Phi-3 Vision, a lightweight multi-modal model designed for vision and language tasks. It focuses on running vision-language AI efficiently on Apple hardware like M1 and M2 chips. -
2
RAG Anything
RAG-Anything: All-in-One RAG Framework
RAG-Anything is an open-source unified framework that extends the Retrieval-Augmented Generation (RAG) paradigm to fully multimodal document and knowledge retrieval, enabling systems to ingest, parse, represent, and query rich content that includes text, images, tables, formulas, and other structured or visual elements. Traditional RAG systems are typically limited to text and cannot effectively work across heterogeneous document layouts, but RAG-Anything addresses this by modeling multimodal content in ways that preserve cross-modal relationships and semantic context, often treating content elements as interconnected knowledge entities rather than separate data silos. ... -
3
DeepSeek-OCR
Contexts Optical Compression
DeepSeek-OCR is an open-source optical character recognition solution built as part of the broader DeepSeek AI vision-language ecosystem. It is designed to extract text from images, PDFs, and scanned documents, and integrates with multimodal capabilities that understand layout, context, and visual elements beyond raw character recognition. The system treats OCR not simply as “read the text” but as “understand what the text is doing in the image”—for example distinguishing captions from body text, interpreting tables, or recognizing handwritten versus printed words. It supports local deployment, enabling organizations concerned about privacy or latency to run the pipeline on-premises rather than send sensitive documents to third-party cloud services. ... -
4
Droidrun
Powerful framework for controlling Android and iOS devices
Droidrun is a native mobile agent platform that gives users natural-language control over real Android devices to automate any mobile app workflow, from logins and bookings to purchases and data extraction, including access to mobile-only content behind app logins, rate limits, or platform restrictions. Its cloud offering lets users spin up agents in seconds with preinstalled apps, run tasks in parallel across multiple devices, and compose complex, multi-step conditional workflows using... -
Compliant and Reliable File Transfers Backed by Top Security CertificationsStop relying on non-certified, legacy file transfer tools that creak under the weight of modern security demands. Get full audit trails, advanced access controls and more supported by an award-winning team of experts. Start your free 25-day trial today.
-
5
Unlimited OCR Works
Welcome the Era of One-shot Long-horizon Parsing
...The repository also includes example code for batch inference over image folders or PDF inputs. Overall, it is useful for researchers and developers who need advanced OCR, long-document parsing, and model-based extraction from complex visual documents. -
6
Pycorrector
Pycorrector is a toolkit for text error correction
Pycorrector is a Python toolkit for Chinese text error correction. It focuses on common error types such as similar-sounding characters, visually similar characters, grammar issues, proper noun errors, missing words, extra words, wrong words, and word-order problems. The project implements multiple correction approaches, including KenLM, ConvSeq2Seq, BERT, MacBERT, ELECTRA, ERNIE, GPT-style models, and newer Qwen-based correction models. It is designed for use cases such as input method... -
7
GPTImage2Skill
GPT Image 2 prompt gallery, image prompt library, agentic skill
...It provides reusable image prompts across creative, technical, academic, interface, design, photography, typography, gaming, anime, map, tattoo, and reference-editing use cases. The project is designed to help agents and users produce stronger visual outputs without starting from a blank prompt every time. Its gallery is organized into category files so an agent can load only the relevant prompt references instead of overwhelming the context window. It also includes installation paths for skill-capable environments such as Claude Code, Codex, OpenClaw, and other agent runtimes. ... -
8
Context Engineering
A frontier, first-principles handbook
...It takes inspiration from thought leaders like Andrej Karpathy and bridges theory with practical examples, offering structured guidance on context orchestration, memory, retrieval, and state control within AI workflows. With extensive materials drawn from research, surveys, and visual explanations, the project acts as both a learning resource and a reference for practitioners looking to improve model behavior by engineering richer inputs. -
9
Qwen3-Omni
Qwen3-omni is a natively end-to-end, omni-modal LLM
...It uses a Thinker-Talker architecture with a Mixture-of-Experts (MoE) design, early text-first pretraining, and mixed multimodal training to support strong performance across all modalities without sacrificing text or image quality. The model supports 119 text languages, 19 speech input languages, and 10 speech output languages. It achieves state-of-the-art results: across 36 audio and audio-visual benchmarks, it hits open-source SOTA on 32 and overall SOTA on 22, outperforming or matching strong closed-source models such as Gemini-2.5 Pro and GPT-4o. To reduce latency, especially in audio/video streaming, Talker predicts discrete speech codecs via a multi-codebook scheme and replaces heavier diffusion approaches. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
Agent Sprite Forge
Agent Skill for generating 2D sprite sheets and map, transparent PNG
...The system supports multi-frame sprite generation, animation sequencing, and transparent background rendering for easier integration into game engines. Its architecture is designed around automation and repeatability, enabling developers to generate large batches of visual assets through structured prompt workflows. Overall, agent-sprite-forge acts as an AI-assisted creative tool for accelerating 2D game art production and experimentation. -
11
Slither
Static Analyzer for Solidity
Slither is a Solidity static analysis framework written in Python 3. It runs a suite of vulnerability detectors, prints visual information about contract details, and provides an API to easily write custom analyses. Slither enables developers to find vulnerabilities, enhance their code comprehension, and quickly prototype custom analyses. Slither is the first open-source static analysis framework for Solidity. Slither is fast and precise; it can find real vulnerabilities in a few seconds without user intervention. ... -
12
VGGSfM
VGGSfM: Visual Geometry Grounded Deep Structure From Motion
VGGSfM is an advanced structure-from-motion (SfM) framework jointly developed by Meta AI Research (GenAI) and the University of Oxford’s Visual Geometry Group (VGG). It reconstructs 3D geometry, dense depth, and camera poses directly from unordered or sequential images and videos. The system combines learned feature matching and geometric optimization to generate high-quality camera calibrations, sparse/dense point clouds, and depth maps in standard COLMAP format. Version 2.0 adds support for dynamic scene handling, dense point cloud export, video-based reconstruction (1000+ frames), and integration with Gaussian Splatting pipelines. ... -
13
Perception Models
State-of-the-art Image & Video CLIP, Multimodal Large Language Models
...The project supports a wide range of research applications, from visual recognition and dense prediction to fine-grained multimodal understanding. Additionally, it includes several large-scale open datasets for both image and video perception. -
14
hCaptcha Challenger
Gracefully face hCaptcha challenge with multimodal llms
hCaptcha Challenger is an open-source automation framework designed to solve hCaptcha verification challenges using computer vision models and multimodal reasoning techniques. The project integrates machine learning models capable of analyzing visual captcha tasks and identifying the correct responses required to pass the verification process. Instead of relying on third-party captcha-solving services or browser scripts, the system operates independently by using pretrained neural networks that can classify images, detect objects, and interpret spatial relationships. The framework includes support for multiple types of captcha challenges such as object selection, drag-and-drop puzzles, and image labeling tasks. ... -
15
Android Use
Automate native Android apps with AI using accessibility APIs
android-action-kernel is an open source Python library designed to let AI agents control and automate native Android applications running on real devices or emulators. It fills a gap in automation tooling by focusing on mobile-first workflows where traditional browser or desktop-based automation doesn’t work; such as logistics, gig work, field operations, and other industries reliant on phones or tablets. The project works by using Android’s accessibility API to extract structured UI state... -
16
Gemma
Gemma open-weight LLM library, from Google DeepMind
...This repository provides the official implementation of the Gemma PyPI package, a JAX-based library that enables users to load, interact with, and fine-tune Gemma models. The framework supports both text and multi-modal input, allowing natural language conversations that incorporate visual content such as images. It includes APIs for conversational sampling, parameter management, and integration with fine-tuning methods like LoRA. The Gemma library can operate efficiently on CPUs, GPUs, or TPUs, with recommended configurations depending on model size. Through included tutorials and Colab notebooks, users can explore examples covering sampling, multi-modal interactions, and fine-tuning workflows. ... -
17
Flagsmith
Open source feature flagging and remote config service
Release features with confidence; manage feature flags across web, mobile, and server-side applications. Use our hosted API, deploy to your own private cloud, or run on-premises. Flagsmith provides an all-in-one platform for developing, implementing, and managing your feature flags. Whether you are moving off an in-house solution or using toggles for the first time, you will be amazed by the power and efficiency gained by using Flagsmith. Flagsmith makes it easy to create and manage feature... -
18
VisPy
Main repository for Vispy
Vispy is an open-source, high-performance interactive visualization library in Python, designed for creating scientific visualizations and interactive plots. It leverages the power of modern Graphics Processing Units (GPUs) through OpenGL to render large datasets efficiently. Vispy supports a wide range of visualization types, including 2D plots, 3D visualizations, volume rendering, and more, making it suitable for scientific research, data analysis, and educational purposes. -
19
VisualGLM-6B
Chinese and English multimodal conversational language model
VisualGLM-6B is an open-source multimodal conversational language model developed by ZhipuAI that supports both images and text in Chinese and English. It builds on the ChatGLM-6B backbone, with 6.2 billion language parameters, and incorporates a BLIP2-Qformer visual module to connect vision and language. In total, the model has 7.8 billion parameters. Trained on a large bilingual dataset — including 30 million high-quality Chinese image-text pairs from CogView and 300 million English pairs — VisualGLM-6B is designed for image understanding, description, and question answering. Fine-tuning on long visual QA datasets further aligns the model’s responses with human preferences. ... -
20
Claude Blog
Claude Code blog skill suite
...It is built as a full-lifecycle blog engine with 30 sub-skills, 5 agents, 12 content templates, on-demand references, Python scripts, and automated tests. The workflow is designed to produce production-ready content rather than one-shot AI drafts. It uses a five-gate delivery contract covering capability, format, visual quality, content review, and asset integrity. Commands support new blog posts, rewrites, content audits, briefs, editorial calendars, strategy, outlines, SEO checks, personas, taxonomy, multilingual workflows, research, audio narration, and Google data. Claude Blog is best suited for solo publishers, marketing teams, agencies, and Claude Code skill builders who want structured editorial automation. -
21
Videomass
Videomass is a free, open source and cross-platform GUI for FFmpeg
Videomass is a free, open-source graphical interface for FFmpeg designed to make advanced video and audio processing accessible to both beginners and experienced users. Built in Python using wxPython, it provides a cross-platform environment for managing encoding, conversion, and editing tasks through a visual interface. The software supports multitasking operations, allowing users to process multiple media files simultaneously. It offers extensive configuration options while also providing presets to simplify common workflows. Videomass integrates closely with FFmpeg, exposing powerful capabilities such as transcoding, filtering, and format conversion without requiring command-line interaction. ... -
22
docext
An on-premises, OCR-free unstructured data extraction
...Unlike traditional document processing pipelines that rely heavily on optical character recognition, docext leverages multimodal AI models capable of understanding both visual and textual information directly from document images. This allows the system to detect and extract structured elements such as tables, signatures, key fields, and layout information while maintaining semantic understanding of the document content. The toolkit can also convert complex documents into structured markdown representations that preserve formatting and contextual relationships. -
23
Unstract
No-code LLM Platform to launch APIs and ETL Pipelines
Unstract is a powerful open-source, no-code platform built to automate the extraction and structuring of unstructured documents using large language models and flexible workflows, enabling developers and data teams to turn messy files into organized JSON content without complex coding. It integrates a visual Prompt Studio environment where users can iteratively design extraction schemas, compare outputs from different models, and monitor costs and accuracy side by side, making it easier to refine prompts and extraction logic before deploying at scale. Unstract supports deploying structured extraction as REST API endpoints or embedding it into data engineering ETL pipelines, which allows it to plug directly into data warehouses, cloud storage, or downstream analytics systems. ... -
24
LangExtract
A Python library for extracting structured information
...It is designed to transform free-form text into reliable, schema-constrained data while maintaining traceability back to the source material. Each extracted entity is precisely grounded in its original context, allowing visual inspection and validation via automatically generated interactive HTML visualizations. LangExtract supports a wide range of models, including Google Gemini, OpenAI GPT, and local LLMs via Ollama, making it adaptable to different deployment environments and compliance needs. The system excels at handling long documents using optimized chunking, multi-pass extraction, and parallel processing to ensure both high recall and structured consistency. -
25
PaddleX
PaddlePaddle End-to-End Development Toolkit
PaddleX is a deep learning full-process development tool based on the core framework, development kit, and tool components of Paddle. It has three characteristics opening up the whole process, integrating industrial practice, and being easy to use and integrate. Image classification and labeling is the most basic and simplest labeling task. Users only need to put pictures belonging to the same category in the same folder. When the model is trained, we need to divide the training set, the...