Agents In UseBuilding, testing, debugging and maintaining software or infrastructure, with code review and checks before changes reach users.
424 use casesShowing 121–144
Preparing search…
news.ycombinator.comnexdrew used Claude for requirements and scaffolding, then OpenClaw agents connected to Slack and GitHub issues to build mkdnsite and a hosted service, with AI writing almost all code.
Added
OpenClawnews.ycombinator.comInteguru evolved from replaying observed requests to combining blocked-request exploration with frontend source analysis, reporting broader coverage while acknowledging anti-bot and UX limits.
Added Integurunews.ycombinator.comreactordev used Codex to build a Bun and React management plane for Linux GPU machines, with privileged Docker agents, WebSocket reporting and project-based delegation.
Added
Codexnews.ycombinator.comA developer used mostly Claude Opus 4.5 in agent mode to build Krypto Markets in under 48 hours, directing and reviewing work on live prices, charts, authentication and debugging.
Added
Claudenews.ycombinator.comA DevOps engineer reports building Artifact Keeper in about three weeks with Claude Code, keeping architectural control and running the resulting open-source registry at home.
AddedClaudevia Claude Codenews.ycombinator.comThe author reports around 13,000 lines of generated Go in just over two weeks, roughly 300 PRs, good unit-test coverage and learning idiomatic Go along the way.
AddedCodexnews.ycombinator.comBoth implementations remained incomplete. After reviewing four earlier reports, Astra and Opus both preferred the Opus implementation as the basis for further work.
AddedClaudevia Opus 5.5The author reports 562 merged PRs in two weeks, mostly for Sightline, and a custom-roles goal that ran for over a day with periodic check-ins.
AddedClaude
openai.comThe team reports a shipped internal beta with daily internal users and external alpha testers, roughly 1,500 merged pull requests and about a million lines of agent-written material.
AddedCodex
cockroachlabs.comThe source reports Db2 support completed in less than two days with twenty-seven merged PRs and test coverage equivalent to PostgreSQL; two escalations required a human.
Added MOLT Sinainews.ycombinator.comThe author produced ebookaloud, an ebook narration product targeting m4b output, and shared a free sample demonstrating its voice and format.
Added OpenCode with DeepSeek v4news.ycombinator.comGeistlib was built in C with heavy Claude Code pair-programming and packages BitNet 2B for offline use on a Raspberry Pi 5. The author published performance measurements, methodology and a local benchmark command.
AddedClaudevia Claude Codenews.ycombinator.comA Claude Code CLI agent uses a host-issued token to create or modify apps in a prototyping lab. A reload rebuilds backend and UI components, after which the agent tests through browser or API and the author inspects the running result.
AddedClaudevia Claude Codenews.ycombinator.comA SaaS owner used Claude with a shared Git plan, custom ESLint feedback, Bash approval rules and deterministic workflow generation. They reported lower token spending and shorter workflows while continuing code and UI review.
AddedClaudenews.ycombinator.comBothy packages a Zellij and Yazi terminal workspace into a one-command setup. Claude wrote most of it under the author’s decisions and rules, with portable configuration and verified official tool downloads.
AddedClaudenews.ycombinator.comThe author built a multi-target compiler, used it with Claude for a WASM client and server sharing classes and data formats, and began a cross-platform UI framework.
AddedClaudenews.ycombinator.comConfig-drift-checker generated Claude Code evaluation cases and ran comparisons with and without project setup. The author found hook and skill effects, misleading pass reasons, grader errors and a real Docker teardown from an eval workspace.
AddedClaudevia Claude Codenews.ycombinator.comThe author tested local Qwen through OpenCode on three coding tasks. An MCP feature completed without human input, a Nix package port looped on a hash, and a harder task was stopped after repeated discovery and context compactions.
Added OpenCode with Qwen 3.8-27Bnews.ycombinator.comUsing Claude Code, the author built an xc compiler, extended FreeRTOS into XTOS and integrated an Atari emulator. They report a Linux-built signed iPhone binary, fast OS startup and a passing Acid 800 emulation test.
AddedClaudevia Claude Codenews.ycombinator.comProgressCove’s maker used Claude Code under detailed human guidance to build a family task app with offline mobile storage. The workflow included iterative code review, tests, security review and adversarial subagent checks.
AddedClaudevia Claude Codenews.ycombinator.comThe author reports that urlx passes 1,300 of 1,300 applicable curl tests and provides a libcurl-compatible C ABI, while some features remain unfinished.
AddedClaudevia Claude Codenews.ycombinator.comTool calls decreased from 15 to 13 to 8 across three runs. The third proposed nothing new; repeated TTL suggestions exposed a routing issue requiring a code change.
Added chat.betterdb.com agentnews.ycombinator.comAn experienced compiler author directed Claude over more than half a year to build a language with DWARF imports and shared CPU/GPU execution.
AddedClaudenews.ycombinator.comClaude Code used original MacPaint source and a Gemini feasibility plan to produce a port, recover legacy icons and get the application running on iPad.
AddedClaudevia Claude Code