How to use Unknown to build an ebook audiobook service
The author produced ebookaloud, an ebook narration product targeting m4b output, and shared a free sample demonstrating its voice and format.
Added Unknownvia OpenCode with DeepSeek v4What people are exploring and upvoting this week.
The author produced ebookaloud, an ebook narration product targeting m4b output, and shared a free sample demonstrating its voice and format.
Added Unknownvia OpenCode with DeepSeek v4The author built a macOS application around a reverse engineered BLE specification and added support for a few other Razer mice.
AddedGeistlib 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.
AddedA 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.
AddedA 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.
AddedBothy 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.
AddedThe 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.
AddedConfig-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.
AddedThe 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 Unknownvia OpenCode with Qwen 3.8-27BUsing 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.
AddedProgressCove’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.
AddedPulado’s maker used Claude Code to repair a Flash client for Ruffle and port it to Haxe. Repeated feature comparisons and playtests brought the engine close to parity, with remaining issues still under repair.
AddedThe author reports that simple prompts now produce functioning parks with guests, rides, paths, rollercoasters and themed worlds, including guest-following features.
Added Unknownvia Magic Patterns theme park agentThe 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.
AddedThe team reports user datasets across several research tasks and more than 30x lower costs after restructuring the system, with improved speed and output quality.
Added Unknownvia WebhoundTool 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 Unknownvia chat.betterdb.com agentAn experienced compiler author directed Claude over more than half a year to build a language with DWARF imports and shared CPU/GPU execution.
AddedClaude Code helped revive and instrument a 1997 PC game, adding headless parallel instances and producing level guides with screenshots.
AddedThe author used Claude Code to structure exported voice transcripts, extract decisions and build a searchable knowledge base plus a portable CLAUDE.md file.
AddedClaude Code used original MacPaint source and a Gemini feasibility plan to produce a port, recover legacy icons and get the application running on iPad.
AddedClaude Code runs booking scripts, retrieves database context and generates JSON proposals that wait in an admin out tray for manual approval.
AddedGit Lineage was built with Claude Code over six and a half months, with the author reviewing and manually testing every PR and remaining hands-on with performance and UX.
AddedClaude Code hooks enforce a failing-test-first development loop, with Playwright checks retained in the codebase and manual testing and line-by-line review before merging.
AddedThe creator finished an inherited message board with Claude Code and describes version-checked payment activation, refunds, and substantial performance and security work.
AddedClaude Code reproduced a llm-gemini command error, fixed the unsupported media resolution issue, and ran tests; the author reviewed and manually verified the change.
AddedThe Backlog.md creator reported improving an agent coding workflow through project documentation, individual Markdown tasks, planning, and review before merging.
AddedThe author turns conversational reflections into structured JSON, views them in a local character-sheet dashboard, and exports edited context for later sessions.
AddedCasperAI’s creator used Claude Code to generate about 80% of its TypeScript, including the MCP server and SQLite schema. The author retained architecture, debugging, documentation and edge-case testing.
AddedThe author described a Grok Bot merge gate requiring green repository CI followed by full-diff review from a separate agent. A 167-file PR was held for six fixes before merging.
AddedGrok Bot helped prepare and test companion-app changes across several platforms. The author reported five merged PRs and a Windows build break caught on real hardware after cloud CI missed it.
AddedClaude Code orchestrated resource- and country-specific research agents, assembled sourced deep dives, and supported a queryable research project about interconnected disruptions.
AddedA Claude Code skill recovered export-blocked Kindle highlights using local position metadata, Cloud Reader images, and Apple Vision OCR, producing cited Markdown notes.
AddedClaude Code rebuilt Babylonian Twins in Godot from C++ and 68000 assembly, added scripted controls and headless checks, and relied on the creator for playtesting.
AddedThe author prototyped search intelligence with Claude and Claude Code, encountered excessive API consumption, then used SerpAPI and Lovable for a tool used daily.
AddedIn a reported demo, AURA investigated checkout 502s, traced them to a downstream memory leak, documented a fix through a human-gated GitHub call, and checked recovery.
Added Unknownvia AURAOutscal constrained agent tools and supplied context upfront after inconsistent Claude Code runs, then moved its React video pipeline to the Claude Agent SDK and launched an automated web version.
AddedRecall built Predict largely with Claude Code subagents, then shifted from a Figma MCP design workflow to a designer prompting iterations directly into code. The author reported an end-to-end working loop with rough edges.
AddedHawkDoc combines Lexical editing with React, collaborative-sync infrastructure, and Markdown, HTML, and PDF export. Its author credits Claude Code for early editor integrations and export development.
AddedA developer used Claude Code and Codex CLI to write svelte-check-rs, retaining architecture and real-codebase testing. The source reports cold, warm, and iterative speed improvements on a SvelteKit monorepo.
AddedGodogen combines two Claude Code skills with a custom Godot reference system, headless scene construction, and separate Gemini Flash screenshot evaluation to generate playable Godot 4 projects.
AddedIndexio indexes a codebase and serves Claude Code lookups through MCP, falling back to regex when needed. Its authors report reduced token use but identify symbol-heavy workflows as a limitation.
AddedChatML gives parallel Claude Code tasks separate Git worktrees, branches, and working directories. The team used the workflow for most of ChatML and reports merging over 750 generated pull requests.
AddedMaxxwell coordinates parallel Claude and Codex sessions through an orchestrator that monitors goal checklists and brings important decisions back to the user.
AddedWillison used Claude Code to narrow a Cloudflare challenge to multi-parameter searches. When the MCP interface could not edit the relevant rules, the agent switched to the API.
AddedWillison asked Claude Code for web to compile Gifsicle to WebAssembly and build a preview interface. The agent used Rodney to exercise the page and fix UI bugs during implementation.
AddedWillison wanted to optimize a phone recording before publishing it. He used Claude Code for web to build a browser tool around FFmpeg compiled to WebAssembly, with multiple output presets.
AddedWillison delegated a Moebius model port to Claude Code using local repositories and a research note. He tested the browser UI and returned errors while the agent iterated on ONNX and WebGPU support.
AddedWillison needed a video of an interactive canvas animation for a keynote slide. A local Claude Code session used Playwright to open the page, time clicks and produce a recording.
AddedAnthropic and Andon Labs let a Claude-based agent manage a real office shop. It searched for products, set prices and requested restocking, but the researchers report losses and persistent mistakes.
AddedIn the next office-shop phase, Claudius gained browser access, CRM and better inventory context. It checked supplier prices and delivery details while human purchase approval remained mandatory.
AddedSimon Willison gave Codex a specific defect in his Django blog: social preview descriptions exposed raw Markdown. Codex changed templates and added a passing test in a configured PostgreSQL environment.
AddedWillison published the Codex session used to build the Datasette project blog. The agent inspected the existing site, moved conflicting database routes and implemented blog behavior with local checks.
AddedWhen crawlers hammered datasette.io, Willison used Codex to build a configurable IP rate-limiting plugin. His release note includes the configuration used on the live site.
AddedWillison supplied an existing parser and an independent compatibility suite, reviewed an API plan, then let Codex implement a JavaScript port through repeated tests and commits.
AddedDodds used Cursor with GPT-5.4 to add lexical retrieval to his semantic search. Production blocking exposed an architectural flaw, so later agent work moved search into a unified Worker.
AddedDodds delegated an audio pipeline migration to Cursor. He rejected an initial design that preserved a separate service and used another agent run to make the sandbox part of the existing queue Worker.
AddedWillison ran o4-mini-deep-research to find surviving orchestrions and return structured location records. The model used web search and code execution; he explicitly considered the resulting list incomplete and unverified.
AddedFutureHouse used Robin to connect literature research, experiment planning and analysis for dry age-related macular degeneration. Human researchers ran the lab work; the system proposed follow-up candidates from the results.
AddedWillison recorded upgrading datasette-checkbox for a changed permissions API. He first repaired a test that missed a real page failure, then gave Codex the failing runner and upgrade documentation.
AddedWillison recorded a real build with Claude Code for web, turning pasted terminal output into shareable HTML. The companion article explains the repository references and the workflow behind the recording.
AddedFutureHouse ran WikiCrow to draft scientific summaries of human genes using full-text papers. Its PaperQA agent searched, gathered evidence and returned to retrieval when terminology or evidence required it.
Added