Urgent.News

What's breaking now, across thousands of outlets.

Tech

OpenHands vs SWE-Agent vs AutoGen: Best Autonomous Dev Tool for Real T

Updated June 3, 2026. Current GitHub stars, licenses, official product pages, and community reports were checked before writing this expanded comparison. At a glance Tool GitHub stars License Best for Pricing OpenHands 74,372 NOASSERTION Cloud coding agents and autonomous task execution Open source; check the site for current commercial options SWE-agent 19,258 MIT Turning GitHub issues into…

OpenHands, SWE-agent, and AutoGen are three autonomous development tools designed for different developer needs. OpenHands is the most polished option, tuned for end-to-end cloud coding tasks. It runs agents inside a sandboxed Docker environment with access to a shell, browser, and editor, allowing the AI to perform iterative software engineering work. With over 74,000 GitHub stars, OpenHands leads in mindshare and community adoption.

SWE-agent specializes in fixing GitHub issues automatically. Built by Princeton researchers, it gives an LLM a terminal, file editor, and browser in a controlled loop to turn issue reports into patches. The tool has a clean pipeline from issue to patch and powers the SWE-bench benchmark for measuring AI coding performance. It has a dedicated following with 19,258 stars, showing strong specialization.

AutoGen is the most flexible framework, providing a toolkit to build multi-agent systems rather than a single coding agent. Developed by Microsoft Research, it lets developers define multiple agents (assistants, users, tools) and specify how they communicate and delegate tasks. AutoGen's modular architecture supports function calling, human-in-the-loop approval, and dynamic agent management, making it ideal for complex orchestration scenarios. The framework has 58,247 stars, indicating broad developer adoption beyond pure coding use cases.

While AutoGen requires the most architectural thinking and manual agent wiring, it shines in orchestrated workflows. SWE-agent has the shortest setup time and is best for issue-to-fix automation within existing GitHub workflows. OpenHands has a longer setup involving Docker, but it offers an out-of-the-box sandboxed environment with web browsing and file access for complex engineering tasks.

Choosing the right tool depends on priorities: OpenHands for complete autonomous workflow, SWE-agent for issue-based automation, and AutoGen for custom multi-agent orchestration.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

The context cliff: 200K, 272K, and the line that doubles your prompt bill

Most LLM price tables are read as one number per model. That number is a floor, and the ceiling is printed next to it in smaller type. Take a 250,000-token prompt.

  • 200K tokens trigger cost doubling on GPT-6.1 Sol
  • 272K tokens mark long-context rate on Gemini 3.1 Pro
  • Cache discounts vary by provider, not always disclosed

Extract the audio from a video with ffmpeg from command line

You have a recording of a call or a talk, and you only want the audio. How do you do it? You ask an AI, and it gives you the classic line: ffmpeg -i "Team call.mp4" -vn -acodec copy out.mp3 It fails…

  • Use ffmpeg command-line tool to extract audio from video
  • Script queries ffprobe for audio stream, selects output format
  • Handles errors, outputs audio file with same name, different extension

Marketplace Webhook Signature Check After Deploy With Raw Body Admission Controls

The page a marketplace team should rehearse is painfully specific: a webhook signature check starts failing after a deploy, platform events stop entering the backend, and the on-call must decide how…

  • Preserve raw request bytes before JSON middleware processes them
  • Verify original bytes before parsing to maintain signed representation
  • Reject verification failures with non-retryable status

More from Saturday 21 November →