Awesome AI Agents › Web Agents
Ash Agents attacks web tracking by removing the persistent identity rather than concealing it. The user never touches a site directly; instead they state an intent in plain language, an orchestrator decomposes it into tasks and fans those tasks across agents, and each agent carries them out in its own browser context with a distinct fingerprint, device profile and network egress. When a task finishes the identity is destroyed together with its state, so a site sees a series of unrelated one-time visitors and cannot join today's visit to anything earlier. The README contrasts this with VPNs, which change where you connect from but not who you appear to be on arrival, private browsing, which clears local state but leaves fingerprinting and behavioural correlation intact, and blocking extensions, which cut some third-party collection while first-party identification continues. The codebase is organised as Python services matching four concerns named in the documentation: isolation, which gives every agent a separable browser environment; reasoning, where a planner reads each page as it loads and chooses the next action instead of replaying a brittle script; orchestration, which splits the task, distributes it and reconciles the results entirely inside the user's trust boundary so the coordinating layer is never exposed; and identity, scoped to a single task with creation and erasure as one lifecycle. The repository ships the orchestrator and reasoning services with tests, a Docker Compose deployment, a demo console with a sample target application, a whitepaper and a vision document. The stated properties are non-attribution, non-linkability and no persistent profile. It targets privacy-focused users and researchers, and the project notes that users remain responsible for compliance with service terms and local law.
https://github.com/EthanXiang777/ash-agents
LaVague is an open-source Large Action Model framework for developing AI Web Agents that automate web-based tasks using components like a World Model and Action Engine with support for Selenium, Playwright, and Chrome extension drivers.
Index is an advanced open-source browser agent that autonomously performs complex web tasks using AI models, offering hosted and self-hosted options with strong observability features.
Tarsier is a vision utility that enhances web interaction agents by tagging webpage elements and converting screenshots into text representations to enable effective LLM-based web automation.
A curated list of tools, frameworks, and resources for building AI web agents that autonomously browse and interact with the web.
WebVoyager is an end-to-end web agent powered by Large Multimodal Models that interacts with real-world websites to complete diverse user tasks using textual and visual information.
Python SDK for the Oxylabs AI Studio scrape agent, which extracts data from a single web page using a natural language prompt and returns structured JSON or Markdown without CSS or XPath selectors.
AgentLab is an open-source framework for developing, testing, and benchmarking scalable and reproducible web agents across diverse tasks using BrowserGym benchmarks and large-scale parallel experiments.
WebShop is a simulated e-commerce environment designed to train and evaluate grounded language agents for complex real-world web interaction tasks involving product search and purchase based on natural language instructions.