Hacker News

I’ve always felt that traditional anime databases rely too heavily on rigid tag-based searches. If you’re looking for a specific "vibe" or a very niche trope that isn't a primary tag, you usually end up scrolling through pages of irrelevant results.

I built AniTroves (https://anitroves.com) to experiment with a more conversational, LLM-driven approach to series discovery.

The Tech Behind the Hub:

LLM Integration: Instead of a generic API wrapper, I've been working on a custom hub (https://anitroves.com/ai-hub/) that uses specialized models to understand series lore and character archetypes for roleplay and discovery.

Anipick Engine: This is the logic layer that maps natural language queries to our database entries.

Technical Transparency: I’ve implemented a structured llms.txt (https://anitroves.com/llms.txt) to provide a machine-readable source of truth for other crawlers and AI models.

I’m currently the technical administrator and I'm handling the SEO and server scaling (managed on Hostinger) myself. I’ve recently been troubleshooting some 504 gateway issues during traffic spikes, so the site is a work in progress!

I'd love to get the community's feedback on the UX of the AI Hub and how I can better structure my data for AI-readiness.

Questions for HN:

Does the conversational discovery feel more useful than standard tag filtering to you?

How are you handling llms.txt or robots.txt for your own AI-adjacent projects in 2026?

Comments URL: https://news.ycombinator.com/item?id=48057592

Points: 1

# Comments: 0

a lot of moron put 4:3 videos in 16:9. Genius programmer at Google cannot add a button that let s me to fix it??? but they can get paid lots money too much money don't do any real work. idiota.

Comments URL: https://news.ycombinator.com/item?id=48057588

Points: 1

# Comments: 1

I’ve been building agentctl, a small Go tool that sits between coding agents and the risky actions they want to take: package installs, shell execution, secret access, file writes, outbound API calls. The design is deliberately narrow and local-first. No HTTP server, no hosted component, no repo-level config sprawl. Everything lives under ~/.agentctl/. Policy is yours, traces are yours.

The workflow I keep coming back to: write a permissive policy, let the agent run for a week, then tighten the rules and replay the old sessions to see what would have been blocked. Much better than guessing at policy upfront, and it’s the part of the tool I didn’t expect to use as much as I do.

Every gated decision gets written to jsonl, so you can grep, diff, or feed traces back through a stricter policy without re-running the agent. There’s also a TUI for browsing sessions, inspecting individual gate decisions, and stepping through replays interactively, which makes it easier to spot patterns across runs.

Currently works with Claude Code and MCP-based clients like Codex.

Still a WIP and mostly a project for myself, but figured others experimenting with coding agents might find it interesting.

GitHub: https://github.com/chocks/agentctl

Comments URL: https://news.ycombinator.com/item?id=48057567

Points: 1

# Comments: 0

Article URL: https://www.familytreeiq.com

Comments URL: https://news.ycombinator.com/item?id=48057565

Points: 1

# Comments: 1

For image models specifically, but I think it applies to LLMs aswell

Comments URL: https://news.ycombinator.com/item?id=48057514

Points: 1

# Comments: 0

Article URL: https://www.startribune.com/best-buy-hybrid-four-days-change-shift-mandate-in-office/601828733

Comments URL: https://news.ycombinator.com/item?id=48057509

Points: 2

# Comments: 1

Article URL: https://foxremake.com/star-fox-64-remake/

Comments URL: https://news.ycombinator.com/item?id=48057467

Points: 2

# Comments: 3

Article URL: https://www.federalregister.gov/documents/2026/04/02/2026-06376/revised-mailing-standards-for-firearms

Comments URL: https://news.ycombinator.com/item?id=48057450

Points: 2

# Comments: 0

Article URL: https://blogs.perl.org/users/todd_rinaldo/2026/04/ai-contributions-to-cpan-the-copyright-question.html

Comments URL: https://news.ycombinator.com/item?id=48057449

Points: 2

# Comments: 0

Article URL: https://mathscinet.ams.org/mathscinet/msc/msc2020.html

Comments URL: https://news.ycombinator.com/item?id=48057421

Points: 2

# Comments: 0

NyaayWatch (https://nyaaywatch.in) is an open-source observability layer for India's courts. Pending caseloads, clearance rates, and wait times — published as reviewed, versioned snapshots, with every number linking back to a dated source.

Why it exists: India's National Judicial Data Grid (NJDG) reports pending cases daily, but it doesn't preserve history, has no consistent schema across courts, and gives you no way to cite a specific number on a specific date. The data is public; it just isn't usable. NyaayWatch closes that gap.

Live today: - Supreme Court of India - All 25 High Courts - Lower courts in every state and Union Territory (28 + 8) - Read-only public API with paired /data, /methodology, /api pages - Full methodology behind every figure, with publication ids you can roll back to

Some things HN may find interesting:

- Snapshot-based, not live. The pipeline is fetch → extract → normalize → publish. The publish step is gated on quality + delta checks

- Metrics that depend on missing NJDG inputs are tagged {"state": "missing", "reason": "source-not-published" | ...} rather than silently zeroing. There's a separate cron that emails the official NJDG CPC contact for state rows where pending is non-zero, but filed and cleared are both zero last month (haven't received a reply yet:/)

- Source: https://github.com/rudrakshbhandari/nyaaywatch

Some places to start: - https://nyaaywatch.in/supreme-court - https://nyaaywatch.in/high-courts/bombay - https://nyaaywatch.in/states/uttar-pradesh - https://nyaaywatch.in/learn - curl https://nyaaywatch.in/v1/stats/himachal | jq

Where it's going: NJDG publishes daily but discards history, so the first six months of NyaayWatch is the first six months of dated, queryable judicial data anyone can cite.

Beyond that — undertrial populations (around three-quarters of India's prison population is awaiting trial), translations into Hindi, Tamil, Bengali, Marathi, and the same observability layer for the executive and legislative branches over time.

This is a public alpha. I'd love feedback from anyone who's worked with NJDG, judicial data, civic-tech infrastructure, or anyone passionate about social justice. Contributions are welcome:)

Comments URL: https://news.ycombinator.com/item?id=48057413

Points: 2

# Comments: 0

Article URL: https://duti.dev/randoms/wip-location-services/

Comments URL: https://news.ycombinator.com/item?id=48057408

Points: 6

# Comments: 0

Article URL: https://www.theatlantic.com/ideas/2026/05/kash-patel-fitzpatrick-fbi-investigation/687077/

Comments URL: https://news.ycombinator.com/item?id=48057315

Points: 3

# Comments: 1

Article URL: https://spaceflightnow.com/launch-schedule/

Comments URL: https://news.ycombinator.com/item?id=48057312

Points: 2

# Comments: 0

Article URL: https://health.aws.amazon.com/health/status?t=2026-05-07

Comments URL: https://news.ycombinator.com/item?id=48057294

Points: 2

# Comments: 1

Article URL: https://skintrackers.com/en

Comments URL: https://news.ycombinator.com/item?id=48057232

Points: 1

# Comments: 1

Article URL: https://www.nytimes.com/interactive/2026/05/07/world/middleeast/oil-tanker-strait-hormuz-iran-war.html

Comments URL: https://news.ycombinator.com/item?id=48057225

Points: 2

# Comments: 0

Article URL: https://github.com/Bin4ry/yarbo-nat-in-my-back-yard

Comments URL: https://news.ycombinator.com/item?id=48057220

Points: 1

# Comments: 0

Article URL: https://www.cbc.ca/news/canada/british-columbia/ubc-sfu-canvas-cyber-breach-9.7191972

Comments URL: https://news.ycombinator.com/item?id=48057219

Points: 1

# Comments: 0

Article URL: https://openrouter.ai/announcements/gpt55-cost-analysis

Comments URL: https://news.ycombinator.com/item?id=48057209

Points: 1

# Comments: 0