Awesome Ai Agents 2026
Section: Developer Infrastructure · OSS browser agent library. Used by Manus.
ActiveScore 74
Entry
browser-use
Appears in 10 awesome lists
Minimal browser-automation agent harness with clean separation of tool registration, DOM state injection, action loop, and error recovery. Small codebase, clear structure — the best "minimal viable harness" reference for understanding core loop mechanics.
Open github.combrowser-use/browser-use
Found in these lists
awesome-ChatGPT-repositories
Section: Browser-extensions · Make websites accessible for AI agents
FreshScore 87
Awesome Data Analysis
Section: Tools · A library for browser automation and web scraping.
FreshScore 80
Awesome Harness Engineering
Section: Demo Harnesses · Minimal browser-automation agent harness with clean separation of tool registration, DOM state injection, action loop, and error recovery. Small codebase, clear structure — the best "minimal viable harness" reference for understanding core loop mechanics.
FreshScore 88
Awesome LangGraph & LangChain Ecosystem
Section: Web Automation & Scraping · Library for AI agents to control websites and automate tasks
ActiveScore 77
Awesome local LLM
Section: Browser Automation · make websites accessible for AI agents
FreshScore 87
Awesome Open Source AI
Section: 4. Agentic AI & Multi-Agent Systems · Makes websites accessible for AI agents. Enables autonomous web automation, data extraction, and task completion with natural language instructions. MIT licensed.
FreshScore 89
Awesome Prompts
Section: Frameworks · OSS
FreshScore 90
Awesome Python
Section: Web Scraping · Make websites accessible for AI agents with easy browser automation.
FreshScore 94
awesome-python
Section: Scraping and Crawling · Agents that use the browser.
FreshScore 81
Often listed next to it
Dify
February 2026 release making human oversight a native workflow primitive: suspend execution at critical decision points, expose review-and-edit UI mid-flow, and route subsequent execution based on human action (approve/reject/escalate). Demonstrates how HITL transitions from bolt-on approval gates…
In 14 listsDetails
Selenium
Portable software testing framework for web applications. License: Apache 2 , .
In 9 listsDetails
Continue
Continue is an open-source autopilot plugin for VS Code and JetBrains, enhancing coding with LLMs through features like task and tab autocomplete, natural language edits, file generation, and customization options, available under the Apache 2.0 license github | website
In 10 listsDetails
AgentGPT
AgentGPT allows users to configure and deploy autonomous AI agents, enabling them to name their own custom AI and guide it towards any desired goal through task execution and learning github | github profile
In 9 listsDetails
playwright-python
Python version of the Playwright testing and automation library.
In 6 listsDetails
Agent-S
Open agentic framework that uses computers like a human. SOTA on OSWorld benchmark (72.6%) for GUI automation and computer control.
In 6 listsDetails
Crawl4AI
Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key.
In 5 listsDetails
Playwright MCP
Browser automation via accessibility tree snapshots rather than screenshots, dramatically reducing token cost. The canonical example of structured tool output design in an MCP server.
In 5 listsDetails