931–940 of 1001 posts
I've been searching, posting, chatting on various platforms for more than a decade now. context-use allows me to turn all those years of data into context that I can bring to my favorite agents.
Stack is React frontend, Node.js backend, Claude as the primary AI layer for orchestration.
The most interesting engineering problem has been the orchestration layer. Getting an agent to handle multi-step outbound workflows with real judgment, not just automation, takes a lot of iteration on the prompting and state management side. Also feedback from users on the best workflows to collaborate with agents.
I'm also publishing a hackernews daily digest.
This story was included in the March 9th issue (https://hn.alcazarsec.com/daily?date=2026-03-09).
Hacker News users are currently developing a diverse range of projects, from a retro-inspired city builder game [0] and an award-winning daily word puzzle [4] to a European-based search engine alternative [2] and a NSFW filter for the Marginalia search engine [8]. Several developers are focusing on practical tools for family and personal life, including an educational site to help relatives identify AI-generated content [1], a "statphone" for emergency family alerts [3], and a local-first financial tracking app using double-entry accounting [6]. Others are experimenting with advanced technical implementations, such as using LLM agents to backtest stock trading strategies [5], "vibe-coding" CLI tools, and designing a new language for bare-metal embedded devices [7].My hobby x86 kernel. I'm targeting my 80486DX2-66 PC with 32MB of RAM. This project has had a few false starts over the years, where I lacked the prerequisite knowledge to be able to properly debug things. So while the initial commit is from 2020, most of the progress is from the ~180 or so commits I've done in the last month since I picked it up again in early February. A month ago it booted from a floppy and printe…
I'm working on Tech Talks Weekly which is a free weekly email with all the recently published Software Engineering conference talks in the past 7 days.
Every week I pull all the new talk recordings from hundreds of conferences (Devoxx, KubeCon, PyCon, QCon, LeadDev, JSNation, and many more). I feature the ones I think are must-watch with short summaries written by me, then include a list of everything else uploaded that week.
It started as a personal project to fix my own messy YT subscriptions and RSS feeds and now 8,700+ people read it.
I also publish extra editions from time to time like “The Most Watched Talks of 2024” which made it to the HN front page. Currently, I'm working on 2025 edition that will be published very soon.
If you watch software engineering conference talks, you might find it useful.
I’d love to know what you think!
ChatShell ( https://github.com/chatshellapp/chatshell-desktop ) — open-source desktop AI agent built with Tauri 2 + Rust. Ships with 9 built-in tools (web search, bash, file read/write, grep, etc.) so the AI can take real actions from the first conversation. No plugins, no config. Supports 40+ providers, MCP with OAuth, and a skills system. Apache 2.0. Today working on adding chat history search (FTS5) and OpenRouter…
The interesting engineering problem was ChEMBL: most phytochemical names don't have direct ChEMBL entries, so the pipeline first tries a name match, then falls back to PubChem for CID → InChIKey resolution before hitting ChEMBL's molecule API. Full enrichment with Aho-Corasick string matching took ~24 seconds for 24,771 compounds.
Building the commercial layer on top: Rust/Actix-Web API, 97K static pSEO pages on Cloudflare Workers/R2, Stripe for one-time purchases. Solo founder, bootstrapped, based in Germany.