Canary watches any URL and alerts you when something changes — competitor pricing, API endpoints, docs, job boards, status pages. Changes are scored 1-10 by signal strength and summarised by AI. Built solo. Landing page live today. Automated crawler running on GitHub Actions posting real detected changes to Bluesky hourly and X daily. canary-landing-one.vercel.app Happy to answer questions about the architecture — particularly proud of the URL deduplication approach where one crawl serves multiple subscribers.

Knuth Claude's Cycles note update: problem now fully solved, by LLMs - https://news.ycombinator.com/item?id=47306926 - March 2026 (2 comments)

https://chatgpt.com/share/69aaab4b-888c-8003-9a02-d1df80f9c7...

Claude's Cycles [pdf] - https://news.ycombinator.com/item?id=47230710 - March 2026 (362 comments)

I've been building Pneuma, a desktop computing environment where software doesn't need to exist before you need it. There are no pre-installed applications. You boot to a blank screen with a prompt. You describe what you want: a CPU monitor, a game, a notes app, a data visualizer and a working program materializes in seconds. Once generated, agents persist. You can reuse them, they can communicate with each other through IPC, and you can share them through a community agent store. The idea isn't that everything is disposable. It's that creation is instant and the barrier to having exactly the tool you need is just describing it.

Under the hood: your input goes to an LLM, which generates a self-contained Rust module. That gets compiled to WebAssembly in under a second, then JIT-compiled and executed in a sandboxed Wasmtime instance. Everything is GPU-rendered via wgpu (Vulkan/Metal/DX12). If compilation fails, the error is automatically fed back for correction. ~90% first-attempt success rate.

The architecture is a microkernel: agents run in isolated WASM sandboxes with a typed ABI for drawing, input, storage, and networking. An agent crash can't bring down the system. Agents can run side by side, persist to a local store, and be shared or downloaded from the community store.

Currently it runs as a desktop app on Linux, macOS, and Windows. The longer-term goal is to run on bare metal and support existing ARM64 binaries alongside generated agents. A full computing environment where AI-generated software and traditional applications coexist.

Built entirely in Rust.

I built this because I think the traditional software model of find an app, install it, learn it, configure it; is unnecessary friction. If a computer can generate exactly the tool you need in the moment you need it, and then keep it around when it's useful, why maintain a library of pre-built software at all?

Free tier available (no credit card). There's a video on the landing page showing it in action.

Interested in feedback on the concept, the UX, and whether this is something you'd actually use.

Garry Tan's gstack proved you can give Claude Code a full engineering team via the SKILL.md standard. I asked: what about the PM layer?

One command (/pm-run) runs the full planning cycle inside your terminal — audit → objectives → strategy → roadmap → PRD. Each skill writes a markdown artifact, the next one reads it. Context compounds across the whole pipeline.

The part I find most useful: it builds persistent memory of your product in ~/.nanopm/memory/. Re-run /pm-audit six months later and it knows what you tried before. No other PM tool does this because no other PM tool lives in your editor.

/pm-breakdown creates tickets directly in Linear or GitHub Issues from the PRD.

https://github.com/nmrtn/nanopm

Early days, would love to know: does running PM work inside your editor feel right, or does it belong in a separate tool?

Its not super fancy, but I have found it useful from small emails to larger design docs so thought I would share.