Search Results for "agent"
Sort By:
Showing 35 open source projects for "agent"
View related business solutions-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
$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.
-
1
Dev Browser
A Claude Skill to give your agent the ability to use a web browser
Dev Browser is a browser automation skill/plugin that enables an AI agent to control a real browser for verification and testing during development. Its purpose is to close the gap between “code was written” and “the UI actually works,” by letting the agent navigate, interact with pages, and validate behavior in a live environment. A key idea is persistence: the browser can keep pages open so the agent can navigate once and then perform multiple interactions across scripts without losing state each time. ... -
2
Jev Ultrafast
A browser agent with a dynamic, indexed action space
...A small language model is invoked only when text must actually be generated for a typing action. The agent connects to Chrome through Browser Harness and provides an inspector showing elements, probabilities, decisions, and executed actions. Its design avoids site-specific scripts and instead relies on fresh observations of the live page. -
3
OpenMuse
A personal agent with a browser, terminal, files, and work
OpenMuse is an open-source personal agent application that combines chat with its own browser, terminal, files, and persistent task execution. It runs separate server, task-worker, and browser-worker components while exposing the agent's activity to the user. Persistent Chromium profiles let tasks continue across authenticated browsing sessions, while an optional Linux workspace provides command execution and editable files. -
4
Telegraf
The plugin-driven server agent for collecting and reporting metrics
Telegraf is an agent for collecting, processing, aggregating, and writing metrics. Design goals are to have a minimal memory footprint with a plugin system so that developers in the community can easily add support for collecting metrics. Telegraf is plugin-driven and has the concept of 4 distinct plugin types. Input Plugins collect metrics from the system, services, or 3rd party APIs. -
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.
-
5
terminal-browser
A browser that runs directly inside your existing terminal
...A Rust graphics engine draws the browser shell, while React and TypeScript define its interface through a custom renderer. The CLI can open URLs, create split panes, list browser instances, and expose agent-compatible actions. It is designed for coding agents, remote SSH previews, and terminal-centered web development workflows. -
6
Chromium
The official GitHub mirror of the Chromium source
...This directory is currently in a prototyping state and may be removed in the future. As we add support for multiple coding IDE/agents, we will likely pull common prompts and instructions into a central directory with stubs for bespoke IDE/agent integration. Please check with your organization before using GitHub Copilot. copilot-intructions.md is typically a single instruction file that contains default instructions for a workspace. These instructions are automatically included in every chat request. -
7
dsh-ops
A toolkit for low-level operations in DSH
...It supports reading and discovering files while preserving line numbers and limiting excessive output. Additional tools handle CSV, TSV, DOCX, and supported PDF text extraction operations. Developers can access functionality through native agent tools or a programmatic TypeScript interface. Its modular architecture supports independent component configuration, permission checks, and integration with desktop, web, and terminal-based DSH environments. -
8
CloakBrowser
Stealth Chromium for developers and browser automation.
CloakBrowser is a stealth Chromium browser for developers and automation teams using Playwright, Puppeteer, Selenium, or CDP. It supports public web data, QA, monitoring, scraping, and AI-agent workflows while preserving familiar automation APIs. Run CloakBrowser locally or self-hosted on Windows, macOS, Linux, Docker, and VPS infrastructure. Features include persistent profiles, reproducible browser identities, proxy-aware configuration, human-like interaction timing, and CDP server mode. This repository contains the MIT-licensed Python, JavaScript, and .NET wrappers. ... -
9
camofox-browser
Headless browser automation server for AI agents to visit sites
camofox-browser is a headless browser automation server built specifically for AI agents that need to interact with websites that often block standard automation stacks. It wraps Camoufox, a Firefox fork that performs fingerprint spoofing at the C++ level, which means many browser characteristics are altered before page scripts can inspect them, rather than relying on JavaScript-layer stealth patches. The project is designed around a REST API, making it easier for agents and external tools... -
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.
-
10
Gemma 4 Browser Assistant
On-device AI agent Chrome extension powered by Transformers.js
...It also supports tool-calling capabilities, allowing the AI to perform actions such as navigating tabs or highlighting elements. Overall, it demonstrates how to build fully local, agent-based assistants inside web browsers. -
11
BrowserOS
Agentic browser; privacy-first alternative to ChatGPT Atlas
...The interface remains familiar to users of Chrome (including support for Chrome extensions), but adds new capabilities: the browser can automate tasks for you, help you research by extracting and summarizing content, and enable agent-based workflows (e.g., “go fetch this info,” “fill this form,” “monitor this site”). The project is community-driven and entirely open source under the AGPL-3.0 license, which means you can inspect, fork, and contribute to the codebase. -
12
Pinchtab
High-performance browser automation bridge and orchestrator
Pinchtab is a lightweight browser automation backend built specifically for AI agents that need efficient, programmatic web control. Implemented as a small standalone HTTP server, it allows any agent or script to interact with web pages using simple API calls instead of heavyweight browser frameworks. The tool emphasizes accessibility-first snapshots that dramatically reduce token usage compared to screenshot-based approaches, making it cost-effective for large-scale automation. It launches and manages its own Chrome instance while remaining framework-agnostic, so it can be used with any language or agent system. ... -
13
Open ChatGPT Atlas
Open Source and Free Alternative to ChatGPT Atlas
...Unlike a fixed chat app, Atlas is designed as a foundation that can be extended with plugins, external APIs, and custom logic to support domain-specific assistants, agent-like behaviors, and multi-task workflows. The project includes utilities for session management to preserve context across interactions, structured interfaces for streaming responses, and integration layers that let you plug in third-party tools and services. It often forms the basis for research, prototyping, or production systems where the default ChatGPT interface isn’t flexible enough. -
14
Eruda
Console for mobile browsers
With Eruda you can display JavaScript logs, check dom state, show requests status, show localStorage, cookie information, show url, user agent info, include snippets used most often, Html, js, css source viewer, and install. The JavaScript file size is quite huge(about 100kb gzipped) and therefore not suitable to include in mobile pages. It's recommended to make sure eruda is loaded only when eruda is set to true. When initialization, a configuration object can be passed in. -
15
Kubernetes plugin for Jenkins
Jenkins plugin to run dynamic agents in a Kubernetes environment
Jenkins plugin to run dynamic agents in a Kubernetes cluster. Based on the Scaling Docker with Kubernetes article, automates the scaling of Jenkins agents running in Kubernetes. The plugin creates a Kubernetes Pod for each agent started and stops it after each build. Agents are launched as inbound agents, so it is expected that the container connects automatically to the Jenkins controller. -
16
Playwright Skill for Claude Code
Claude Code Skill for browser automation with Playwright
Playwright Skill is an open-source plugin designed for Claude Code that enables dynamic browser automation using Playwright through natural language instructions. The tool allows an AI agent to generate, execute, and manage browser automation scripts on demand, rather than relying on predefined workflows or static test scripts. It is structured as a modular skill within the Claude ecosystem, meaning it can be installed as a plugin and invoked automatically when browser automation tasks are required. The system supports a wide range of use cases, including testing web applications, validating user interfaces, automating workflows, and extracting data from websites. ... -
17
Browserless
Deploy headless browsers in Docker
...The project also provides REST APIs for common automation tasks such as screenshots, PDF generation, scraping, crawling, and content export. Browserless is useful for teams that need scalable browser execution for testing, data collection, rendering, or AI-agent browsing workflows. Its deployment model supports self-hosting, private infrastructure, queues, concurrency controls, and enterprise-oriented configuration. The project’s main value is turning browser automation into a managed service layer that can be reused across applications and workflows. -
18
Polyfill.io
Automatic polyfill service
Polyfill.io is a service which makes web development less frustrating by selectively polyfilling just what the browser needs. Polyfill.io reads the User-Agent header of each request and returns polyfills that are suitable for the requesting browser. There are lots of differing browsers and browser versions in use throughout the world, each one has a slightly different set of features to the rest. This can make developing for browsers a difficult task. The latest versions of the popular browsers can do lots of things which older browsers can not – but you may still have to support the older browsers. ... -
19
galacteek
Multi-platform browser for the distributed web
galacteek is a multi-platform Qt5-based browser and semantic agent for the distributed web. Be sure to install all the gstreamer packages on your system to be able to use the mediaplayer. After opening/mounting the DMG image, hold Control and click on the galacteek icon, and select Open and accept. You probably need to allow the system to install applications from anywhere in the security settings. -
20
MvvmCross Plugins UserAgent
Provides a cross-platform functionality to get the current User-Agent
A MvvmCross plugin that retrieves and parses user-agent strings, enabling device and platform detection in cross-platform apps. -
21
googler
Google Search, Google Site Search, Google News from the terminal
googler is a power tool to Google (Web & News) and Google Site Search from the command-line. It shows the title, URL and abstract for each result, which can be directly opened in a browser from the terminal. Results are fetched in pages (with page navigation). Supports sequential searches in a single googler instance. googler was initially written to cater to headless servers without X. You can integrate it with a text-based browser. However, it has grown into a very handy and flexible... -
22
Surf
Stateful programmatic web browsing in Go
Surf is a Go library that implements a virtual web browser, allowing developers to programmatically interact with web pages as a real browser would. -
23
webStraktor is a programmable World Wide Web data extraction client. Its purpose is to scrape HTML based content via the HTTP protocol and extract relevant information. webStraktor features a scripting language to facilitate the collection, the extraction and the storage of information available on the web, including images. The scripting language uses elements of the Regular Expression and xPath syntax. The webStraktor scripting language has a small instruction set and its syntax is easy...
-
24
BlueLightCat
A web browser free, simple and clear.
BlueLightCat is a simple browser whose feature list includes things like "History", "Bookmarks" and "QuickView", that is a page to see the most visited hosts. It is small, less then 10,000 lines of code and very fast. Note: BlueLightCat is a fork of Zeromus Browser. -
25
Zeromus Browser
Zeromus Browser is free, simple and lightweight.
Zeromus Browser is a simple browser whose feature list includes things like "History", "Bookmarks" and "zLink", that is a page to see the most visited hosts. It is small, less then 10,000 lines of code and very fast. The SpringSun 2.0.0 update includes a new homepage, a new zLink page, new keyboard shortcuts, a new button to the download manager, a streamlined interface, and a major modification of the search engines. The SpringSun 2.1.0 update use Qt 4.8.3 for more stability. The...
