Happy to discuss any questions here!
It's been amazing to vibe code prototypes in any stack, but when it comes to building something reliable/scalable, I couldn't effectively guide the agent unless I knew the technology. And the scariest part is that I'm seeing a lot of my technical skills decreasing due to AI coding.
Reflecting on my journey, I also worry about how the new "AI native" generation of software developer is going to acquire technical depth.
So I built fata.dev: short daily spaced-repetition sessions for programming skills (Rust, CSS, React, Python, TypeScript, Architecture).
You can try it in the browser with no signup: https://fata.app/courses
It's an offline-first mobile app built with Capacitor, RxDB and Firebase. The first courses were painfully written by hand, but most content is now AI-generated. It takes about 3000 LLM calls to generate a course, and every code samples goes through compilation, linting, unit testing, AI and a final manual review.
Would very much appreciate any feedback on the product & website, what works and what could be better. Thanks!
The actual NWS warning polygon only covers East Bay Hills (NWS zone CAZ515). Most people who got the text don't need a go-bag tonight. Some in the hills don't realize how close they are. So I built this tool - https://redflag-check.info/ mit licensed public github - https://github.com/vedant-f-is-ma/redflag-check
It does a few things - tells people if they are in the flagged zone, and also provides a way to check if a buddy is in flagged zone and send them a text. Everything without installing an app.
I heard back from Oakland Firesafe Council director about a gap in my understanding (and the tool). To my surprise, and through feedback, I realized that you cannot assume that only the flagged area is at risk. Adjacent areas are at risk too! Fires do not follow zone boundaries! I fixed the tool.
I built this in 48 hours to close that specific gap: type your address, get a yes/no on whether the NWS polygon covers it, your Genasys evacuation zone, tonight's wind + humidity at your point, a plain-English action checklist, a per-school decision view for East Bay districts, and a one-tap iMessage buddy-check template for a hill-neighbor at 10:30 PM.
curl https://api.tunnelmind.ai/v1/check/1.1.1.1
Claude / Codex kept outputting .md and .html files which are great until we needed to share them, so we built this small website to help with that.
Agent can either use an HTTP + Skill or an MCP which also uses MCP Apps to add widgets to Claude Desktop / Mobile chat.
Would love any feedback and hopefully this helps someone else as it did us!
More info here: https://coherentforge.com/cambios
After talking to the people that actually build PCBs we found out that finding the exact part you are looking for, is consuming enormous amounts of times, is very tedious and then often doesn’t yield the best results. So we tried to cut down this search time by just requiring a (broad) description of the specifications and we find the correct part in minutes, not hours.
This is possible through our own database of parts and their properties. We used LLMs to extract every parameter about a part into >1k schemas, collectively covering more than 130k properties. This depth of properties could no longer be visualized, so the database is queried interactively by an AI agent (Sonnet 4.6) to find the needle in the haystack of parts. Before results are shown, we use another model to verify the data (that’s why it might take a moment before the first results appear).
We currently have almost all microcontrollers, sensors, and other advanced ICs on the market, as well as a wide selection of passives and generic parts. We are working on adding more parts and are more than happy to take suggestions.
I know that folks on HN like technical details on how this works, so let me give a short overview: Frontend: SvelteKit + Cloudflare Workers + Hyperdrive Backend: PostgreSQL 18 (with io_uring) database, with extensions on NVMe drives hosted on a beefy server.
We appreciate all feedback and are happy to answer any questions :)
Btw: We are already working on a way that you can search combinations of parts, finding the optimal combination of parts.
The other thing I cared about was forecasting the usage limits. Existing tools do burn-rate projections (ccusage) or percentile heuristics (Claude-Code-Usage-Monitor), which felt too simplistic for what I wanted - I was after a calibrated statistical model with proper credible intervals.
I built claumon over the last few months in Go. It runs on Linux, macOS and Windows, with a Homebrew install. It has the usual consumption gauges, cost breakdowns and conversation history, plus two tabs for memory management: after a while I had memories scattered across several projects and wanted to see them in one place and prune the stale ones.
In the last few weeks I focused on the forecast model. I started from an empirical-Bayes linear regression with Brownian noise, but ended up with a Gamma process for the path noise: token usage can't decrease over time, so Brownian motion, however mathematically convenient, was the wrong choice. The intervals are calibrated against your own recorded history, and there's tooling that scores the forecasts out-of-sample, so the coverage is checked rather than assumed.
I wrote a formal, versioned spec for the model, and the implementation follows it: https://github.com/fabioconcina/claumon/blob/main/internal/f...
Everything runs locally - nothing leaves your machine. It's open source, MIT. I'd welcome feedback on the model especially.
I have a biotech investing background, but still learning portfolio management. So if there are some basic errors in this, please tell me!
Stack: TypeScript on Vercel edge functions, NWS api.weather.gov, US Census geocoder, Genasys Protect for evacuation zones. Free, no signup, no tracking, MIT licensed. Public REST API + OpenAPI 3.1 spec at https://redflag-check.info/docs. Source: https://github.com/vedant-f-is-ma/redflag-check.
Today an Oakland Firesafe Council director emailed me critiquing the "outside the polygon" framing as falsely reassuring — wind-driven fires don't respect polygons (1991 Oakland Hills, Lahaina, Palisades). I shipped a fix in an hour and the wording across every surface now reflects that. Open to any other critique.
Shai-hulud, prompt-injection - you name it. They cannot steal what your agent (or an process) don't have.
I run coding agents (Claude Code, Codex) on my own machines most of the day. Every one of them wants real API keys in env and I was scratching my head for the last few months how to contain it.
The usual answer to this is a firewall. I don't buy it. A firewall tries to contain a secret the process is still holding, and the rules are painful to maintain.
AVP gives the agent a placeholder and injects the real value at the last moment, on the wire: ``` # the agent's env holds only a placeholder STRIPE_API_KEY=avp-placeholder # agent sends: Authorization: Bearer avp-placeholder # AVP forwards upstream: Authorization: Bearer sk_live_...real... ```
Keep your passwords in your vault where they belong. AVP initially relies on Bitwarden as a secret manager. It's MIT licensed.
Appreciate any feedback.
Built an AI-native game where agents compete against each other.
Feedback welcome.
It's called Domain-Rating.com and it’s a leaderboard of startups with their Domain Rating
Kinda like TrustMRR but for DR
The idea is simple:
1. Check your domain rating in seconds 2. Add your website to the database 3. Compete with other founders on the leaderboard 4. Track your DR change
It's 100% free to use, no catch
Made possible thanks to Ahrefs new free API
Hope you enjoy it, and would love to hear your feedback
Praxis is the result of a decade of my experiences and frustrations working with IaC and infrastructure management in general. It aims to solve the core needs like templating, state management, continues reconciliation, and lifecycle management without needing a complex setup like Kubernetes or bolting on additional tooling like CI pipelines.
It uses a durable execution engine (https://restate.dev) to create and manage digital twins, it means every AWS call is journaled, so a crash mid-provision resumes where it stopped instead of leaving half-applied state. Each resource is a single-writer object, so there's no locking and no state file. Continuous reconciliation is just a durable timer that re-checks every resource every five minutes and either fixes drift or reports it, your choice per resource. The whole thing runs from one Docker Compose stack.
You can declare resources in CUE templates (typed, validated, with real constraints), and there are 45 AWS drivers so far across networking, compute, storage, IAM, and monitoring. Using CUE gives us a lot of goodies like policy enforcement out of the box and our templates doc (https://github.com/shirvan/praxis/blob/main/docs/TEMPLATES.m...) explains the choice of using CUE in more detail.
It's in early development and not everything is tested on a live AWS account, so use at your own risk.
Github link: https://github.com/dloomorg/dloom
Link: https://github.com/ste1v0/atsglyph
It's local-first and open-source, meaning no account, hosted DB, or subscription is needed.
The idea is to:
- find out how my PDF CV is parsed to remove fancy gradient skill bars, etc.
- understand the high-level fit in seconds: no / maybe / worth trying
- see the blockers and what's available to close those gaps, either from added achievements or rough ideas from the model
- get a draft letter with achievements/company context, and a chosen tone with AI patterns cleared [please do not ever send it blindly]
Sadly or not, it won't send 500 applications in a blink of an eye or adapt your CV for you while you look away.
Curious what you think, and how the flow can be improved.