DEV-TOOLSApril 10, 20261 min read17 views

Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs

Twill.ai allows developers to delegate coding, testing, and bug fixing to cloud-based AI agents that automatically open PRs. It enables small teams to ship at the scale of much larger organizations by automating recurring engineering workflows.

You push the vision. Twill writes the code, runs the tests, fixes failures, and opens PRs. Around the clock, only pinging you when it needs your input.

A structured workflow

Every task follows a fixed pipeline. The agent can't skip steps. That's what makes it reliable.

What You Get

Bug fixes, dependency updates, and docs handled automatically so you stay in flow

One dev or a small team shipping like a company ten times your size

Focus on architecture and product. Twill handles the implementation

Assign tasks to the best coding agent

Choose from Claude Code, OpenCode, and Codex.
Run multiple agents in parallel and compare their outputs.
Run the same agent n times to increase success rate.

What can I work on for you?

Agents verify changes in isolated dev environments

Agents spin up sandboxes to build, test, and iterate on changes, making PRs trustworthy.
No setup needed, the agent figures out the best infrastructure for the task.
Access the sandbox infrastructure logs and ports, securely.

Integrates with your tools

Mention @twill from GitHub, Linear, or Slack.
Works where your team already collaborates, with no context switching. Set up once, for all your teammates.
SSH to the sandbox to debug or test, with your favorite IDE (Cursor, VSCode, etc).

Start from proven automations

Pick a template, connect your tools, and let Twill run recurring engineering workflows for you.

Source: Hacker News

More in this category

dev-tools

OpenAI and Hugging Face address security incident during model evaluation

OpenAI and Hugging Face detailed a security incident where an AI agent exploited vulnerabilities during internal cyber capability evaluations, underscoring the critical need for advanced safeguards as AI models gain sophisticated technical capabilities.

dev-tools

The State of Simulation for Physical AI: An Overview

Data availability is the primary bottleneck for Physical AI. GPU-accelerated simulation platforms solve this by generating scalable synthetic datasets to train, test, and deploy next-generation robotics systems.

dev-tools

Linux kernel will support $ORIGIN, sort of

Farid Zakaria shares his journey of proposing a patch to the Linux kernel to support relocatable binaries in Nix, which evolved into a powerful eBPF-based solution for binfmt_misc.

dev-tools

Five US tech giants' hidden debts soar to $1.65T on opaque AI funding

A Nikkei study reveals that off-balance-sheet debts at five major US tech companies have surged eightfold to $1.65 trillion, driven by massive AI investments like data center leases and GPU contracts.

dev-tools

Running Doom on Our Custom CPU and Going Viral

Two developers successfully built a custom CPU from scratch at the logic gate level, deployed it on an FPGA, and optimized its memory architecture to run the classic game DOOM.

dev-tools

Incremental – A library for incremental computations

Incremental is a library designed for building complex computations that update efficiently when inputs change. Inspired by self-adjusting computation research, it is highly useful for large-scale calculations, GUI views, and data synchronization.