Search Results for "visual-"
Sort By:
Showing 21 open source projects for "visual-"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
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.
-
1
Graphify
AI coding assistant skill (Claude Code, Codex, OpenCode, OpenClaw)
...The architecture emphasizes flexibility, enabling users to customize how data is mapped and displayed. It may also include analytical features to explore patterns, clusters, or anomalies within the graph. Overall, Graphify serves as a bridge between raw data and visual insight. -
2
video-use
Edit videos with Claude Code
...Designed to work with Claude Code, it automates the entire editing process—from cutting clips to rendering the final output—without requiring manual timelines or complex software interfaces. The system intelligently analyzes audio transcripts and visual cues to make precise, context-aware editing decisions. It supports a wide range of content types, including interviews, tutorials, montages, and talking-head videos. By combining structured text representations with on-demand visual previews, it minimizes processing overhead while maintaining high-quality results. Overall, Video Use reimagines video editing as an AI-driven, conversational workflow. -
3
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. -
4
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. ... -
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.
-
5
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. -
6
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. -
7
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. -
8
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. -
9
A.I.G
Full-stack AI Red Teaming platform
...Users can deploy it via Docker or scripts to get a modern web UI that guides them through tasks like scanning third-party frameworks for known CVEs and experimenting with prompt security against attack vectors. The tool provides both a visual interface and a comprehensive API, making integration with internal security systems or CI/CD pipelines practical for ongoing risk management. -
Build Securely on AWS with Proven FrameworksMoving 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.
-
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
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. ... -
12
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. -
13
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... -
14
Open-AutoGLM
An open phone agent model & framework
...It aims to create an “AI phone agent” that can perceive on-screen content, reason about user goals, and execute sequences of taps, swipes, and text input via automated device control interfaces like ADB, enabling hands-off completion of multi-step tasks such as navigating apps, filling forms, and more. Unlike traditional automation scripts that depend on brittle heuristics, Open-AutoGLM uses pretrained large language and vision-language models to interpret visual context and natural language instructions, giving the agent robust adaptability across apps and interfaces. -
15
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. -
16
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. -
17
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. -
18
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. -
19
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). ... -
20
aCompute
Aims to enable researcher to tap in to mobile computing capability
This is a software agent based computing program that will enable researchers and other users to tap in computing power of machine available by sharing work load on the fly with zero configuration on network & resources A self organizing agent program that will understand network and its resource. where as the only job left to researcher is to split up jobs in several chunks of programs either parallel or sequential jobs and go issue the job (A visual Modeler or Scripting support need to be yet designed) Software agents will automatically manage the rest or resource management, sharing , cloning of tasks etc. new resources can be added and removed from the system on fly; in layman terms the project will create an agent program that enable sharing & execution of program among all the available resources whether it be desktop, laptop, pda . thereby one can accelerate research to the very extent of resource availability with out bothering about anything... ... -
21
Pythia is a natural language question answering system, which uses Speech Recognition and Text To Speech technologies to communicate with the user.
- Previous
- You're on page 1
- Next