A free coding agent that writes, tests, and ships code, Lemon Code lets you describe a task and then shows the finished result running in a browser preview while also committing the edited files and new tests. It runs the commands, displays terminal output and passing tests, and keeps a change panel with edited files and commit history - for example, fixing a cart total, adding a test, running four tests and showing a corrected $66.00 total. It can run in a cloud workspace in-browser or as a Mac app on your machine, and you can choose to use built-in models or bring your own (Claude Code, Codex, Gemini CLI) with your own API key.
Lemon Code also automates workflows by connecting to over 1,500 apps (GitHub, Slack, Notion, Linear, Gmail, Jira, and many more). Once connected it can review pull requests, turn ready issues into pull requests and tests, post daily standups to Slack, triage and label new issues, prepare meeting briefs from calendar and email threads, and draft incident write-ups in Notion. Connectors are managed from a single screen for sign-in and keys, automations can run once or on a schedule, and the tool is offered free on Mac and in the browser with no required API key.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Natural language programming is criticized for not reducing the complexity and care needed in coding, as machines still require precise instructions. Switching to native language interfaces would likely increase the workload for both humans and machines, rather than simplifying programming tasks. (cs.utexas.edu)
Jank is a Clojure dialect that offers seamless C++ interop, allowing developers to include C++ code directly and leverage its features without boilerplate. It features a Clang-based JIT compiler, native build system, and is optimized for game development and native performance tasks. (jank-lang.org)
Impossible Machines is a prototype that allows users to declaratively program physical mechanisms by describing desired outcomes. It generates mechanisms based on user instructions, enabling interactive design of physical systems. (impossiblemachines.xyz)
Zig uses two main approaches for polymorphism: runtime interfaces with dynamic dispatch and compile-time duck typing for static polymorphism. These methods offer different tradeoffs in performance and safety, with Zig emphasizing simplicity and compile-time checks over complex abstractions. (axelmagn.com)
AI can automate simple coding tasks, but it cannot replace the decision-making and understanding that software engineers provide. Building software still fundamentally involves determining what to create, which remains a complex human challenge. (thelastsoftwareengineer.substack.com)
CATT 0.2.1 is a testing tool for consumer agents and services, allowing for CI-based testing against Muse/Instinct-like systems. It performs service-side outcome checks and provides sealed evidence for MCP servers, apps, browsers, and APIs. (github.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.