Search Results for "visual-"
Sort By:
Showing 14 open source projects for "visual-"
View related business solutions-
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.
-
Our Free Plans just got better! | Auth0You 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.
-
1
PixelRAG
The beginning of scalable pixel-native search
PixelRAG is a visual retrieval-augmented generation system that searches documents by how they look, not only by the text they contain. It renders web pages, PDFs, and images into screenshot tiles, then performs retrieval over those visual representations. This approach preserves layout, tables, charts, diagrams, infographics, and other visual structure that traditional HTML or text parsing can miss. -
2
CyberPPT
A Codex Skill for generating high-density, editable PowerPoints
...It extracts facts, numbers, claims, recommendations, conflicts, and caveats from formats such as PDF, DOCX, TXT, and XLSX. The workflow builds an MBB-style evidence table before developing storylines and converging on an SCR narrative. Users select from eight fixed visual systems, after which the skill plans each slide’s hierarchy, grid, charts, palette, and information density. Image-generation blueprints guide reconstruction while native text, shapes, tables, charts, and vectors preserve core editability. Multiple quality gates inspect structure, visuals, overflow, spatial alignment, curves, and editable elements. ... -
3
Self-Operating Computer
A framework to enable multimodal models to operate a computer
...Notably, it was the first known project to implement a multimodal model capable of viewing and controlling a computer screen. The framework supports features like Optical Character Recognition (OCR) and Set-of-Mark (SoM) prompting to enhance visual grounding capabilities. It is designed to be compatible with macOS, Windows, and Linux (with X server installed), and is released under the MIT license. -
4
Codex-5.5-codex-instruct-5.5
Prompt-injection utility aimed at modifying how Codex CLI behaves
...It claims to use an official configuration mechanism rather than binary modification, network interception, or process tampering. The project includes a Python script, an examples folder, assets, a README, and an MIT license. Its documentation also points users toward a newer visual project with desktop UI, provider switching, session management, and packaged installers. Because the stated purpose is to bypass safety restrictions, it should be treated as unsafe prompt-bypass research material rather than a normal developer productivity tool. -
$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
Agent S
Agent S: an open agentic framework that uses computers like a human
...The latest version, Agent S3, surpasses human-level performance on the OSWorld benchmark, demonstrating state-of-the-art results in complex multi-step computer tasks. Agent S combines powerful foundation models (such as GPT-5) with grounding models like UI-TARS to translate visual inputs into precise executable actions. It supports flexible deployment via CLI, SDK, or cloud, and integrates with multiple model providers including OpenAI, Anthropic, Gemini, Azure, and Hugging Face endpoints. With optional local code execution, reflection mechanisms, and compositional planning, Agent S provides a scalable and research-driven framework for building advanced computer-use agents. -
6
NVIDIA AI Blueprint
Suite of reference architectures for building GPU-accelerated vision
...The project is organized around real-time video intelligence, downstream analytics, and agentic offline processing. It supports workflows such as natural-language video search, visual question answering, long-video summarization, clip retrieval, verified alerts, and incident analysis. It is designed for technical users who need deployable reference architectures for smart spaces, warehouse automation, SOP validation, monitoring, and operational video analytics. The repository includes Python agent code, Docker Compose deployment configurations, skills, scripts, and a Next.js-based UI. -
7
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. -
8
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. -
9
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... -
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.
-
10
ComfyUI-HunyuanVideoWrapper
ComfyUI wrapper nodes for HunyuanVideo
...The system introduces specialized nodes such as text-image encoders that allow multiple image inputs to be referenced directly within prompts. This makes it possible to guide generation using both visual and textual context simultaneously. The wrapper is designed to fit seamlessly into ComfyUI pipelines, enabling chaining with other nodes for advanced workflows. It supports prompt-based referencing of images, where placeholders in text correspond to connected inputs, allowing fine control over generation behavior. The project is particularly useful for creators experimenting with multimodal AI video synthesis. -
11
MolmoWeb
Open multimodal web agent built by Ai2
...Unlike traditional automation tools that rely on structured HTML parsing or predefined APIs, MolmoWeb operates directly from screenshots of web pages, interpreting visual content in the same way a human user would. This approach allows it to generalize across different websites without requiring site-specific integrations, making it highly adaptable to diverse web environments. -
12
ticket
Fast, powerful, git-native ticket tracking in a single bash script
...It stores each ticket as a Markdown file with YAML frontmatter, making them human-readable and easy to version control alongside your code, while also allowing IDEs to jump straight to ticket definitions. The CLI provides common subcommands to create, list, edit, close, and manage dependencies between tickets, enabling clear hierarchical task structures and visual dependency trees. Its design is rooted in the Unix philosophy of simplicity, composability, and transparency, meaning it integrates well with other standard tools like grep, jq, and ripgrep when installed. Teams can use ticket to track bugs, features, chores, and epics with priority levels and tags, all by staying within the terminal and Git ecosystem. -
13
airda
airda(Air Data Agent
airda(Air Data Agent) is a multi-smart body for data analysis, capable of understanding data development and data analysis needs, understanding data, generating data-oriented queries, data visualization, machine learning and other tasks of SQL and Python codes. -
14
Universe Starter Agent
A starter agent that can solve a number of universe environments
The universe-starter-agent repository is an archived OpenAI codebase designed as a starter reinforcement-learning agent that can interact with and solve tasks in OpenAI’s Universe environment platform. Its purpose is to serve as a baseline or reference implementation so researchers or developers can see how to build agents that operate in real-time, visual environments (e.g., games, browser apps) via pixel observations and keyboard/mouse actions. Under the hood, this starter agent implements a version of the A3C (Asynchronous Advantage Actor-Critic) algorithm, adapted for the specific challenges of Universe environments (e.g., network latency, VNC streaming, asynchronous observations). ...
- Previous
- You're on page 1
- Next