Show HN: Turri – a coding agent with the power of regenerative software
What happened
Turri is a new open-source coding agent that uses a 'regenerative software' approach to help developers maintain control over their projects. Instead of patching code with individual prompts, it captures user intent into a durable system definition using plain text files. The agent then generates code from this definition and regenerates affected parts when requirements change. It runs on macOS, Linux, and WSL, requiring Git, Bash, and Node.js. The tool uses a capable model for planning and a smaller, cheaper model for writing the actual code.
Why it matters
This tool addresses the growing problem of developers becoming accountable for complex software they do not fully understand. By keeping a clear, reviewable record of system decisions, it helps prevent the accumulation of misunderstandings in codebases built by AI.
Reality check
An automated, sceptical read of the sourceNotable. It introduces a distinct architectural shift from prompt-based patching to definition-based regeneration, which offers a concrete solution to the maintainability issues common in current AI coding workflows.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More AI news
Every Way to Get 192GB for Local AI (Without a $9,500 Mac) [video]Industry news · 14 Nov 2026DeepSeek V4 Pro 0813DeepSeek · 14 Nov 2026DeepSeek V4 Pro 0813DeepSeek · 14 Nov 2026Show HN: Portal2Bench – Can AI agents solve Portal 2?Industry news · 14 Nov 2026Anthropic Upgrades Claude Code Projects to Run Parallel AI Workers Hands-FreeAnthropic · 14 Nov 2026This page was collected from github.com and summarised automatically by AIPulsee's pipeline. See how it runs.