coding agent
14 stories and discussions about coding agent, aggregated from every source we track.
The next-generation social coding platform.
Most developers already know this rule: Don't run code from a repository you don't...
AI coding agents are getting very good at finishing tasks. They modify files. Fix errors. Write...
An AI coding agent deleted two main branches. See how Git safety, branch protection, pre-push hooks, and agent guardrails can prevent similar failures.
Cotyper: The modern devtool for vibe coders
Your coding agent says it's done. WTF checks. Contribute to LinusInnovator/wtf development by creating an account on GitHub.
Share one HTML or Markdown file as an unlisted link that lives 30 days. Ask your AI agent, or run one command. No deploy.
Most of my coding agent work now runs through more than one agent. A manager agent brainstorms with me, starts an executor, checks on it, and later brings in a reviewer. Sometimes I resume a sessio…
Talk to Claude Code while it works. A full-duplex voice companion powered by GPT Live 1. - CakeCrusher/full_duplex_code
Your coding agent records a polished demo of what it just built: animated zoom, a human cursor and motion blur, exported locally to MP4. - half144/cutaway
A green test suite can preserve the same mistake as the code. Ask an agent to show a bug its tests catch, then check where the expected answer came from.
Names the page, file or tool result that told your AI coding agent to run that command — and stops it because of it. Local, open source, no telemetry. - AGGIB/Stroq
Errors are deduplicated and queued straight to your own coding agent, closing the loop from detection to a fix - ask "what's breaking in checkout" over MCP, or run it unattended via REST. It claims the error, writes…
Why yet another agent? There are a couple of key assumptions I have: Coding agents are surprisingly simple Especially the agentic part They tend to be while loops with a small number of tools There seems to be very…