
Pondwright — pond intelligence, powered by SOVERYN
AI pond design assistant that answers questions about depth, filtration, koi care, and liner selection.
@Soveryn_AI · X
The full gallery
Tech stack
61 projects

AI pond design assistant that answers questions about depth, filtration, koi care, and liner selection.
@Soveryn_AI · X

Watch and browse short videos exclusively generated by AI models.
@botsnips · X
Check out our AI only shorts

Privacy-first search API for AI agents with anonymous access and structured output.
chrismessina · Product Hunt
AnySearch Real-time structured search trusted by agents and developers

Web scraping API that extracts structured data from websites for AI agents.
mohitprateek · HN
Anakin – API for your AI agents to access the most difficult websites

Discover and share reusable AI agent skills for Claude and Cursor.
Skills.lc — AI 技能、Prompt、工作流和 Agent 分享平台,帮助发现和沉淀 AI 使用经验

Test AI agents against production mirrors using replayed traces to find bugs and regressions.
aisinghal

Turn your documents into an AI assistant that answers questions with citations.
knoku · HN
Knoku – cited AI answers from docs, files, and team knowledge

Submit URLs to search engines and track which AI bots cite your content.
@AjayGB4 · X

Unified context layer for AI agents that integrates email, drive, Slack, Notion, and GitHub.
@marcin_u2 · X
-> here it is! claude finally knows everything gpt knows. and both of them know everything that's happened across your email, drive, slack, notion, github and granola :)

A visualization language designed for AI agents to create and interact with charts.
chenglong-hn · HN
Data visualizations are the bridge between user and data. But building AI agents that can generate visualizations reliably can be very tricky: - simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make visual decisions that are supposed to be handled by a good compiler. Flint is a visualization intermediate language to address this issue, allow AI agents to solve this last-mile human-agent interaction problem. It provides a simple semantic-type based specification, and contains a layout optimization engine that can produce good-looking charts (filled with derived low-level details) from simple

Platform giving AI agents persistent memory and fact-based grounding to prevent false claims.
felipemayamuniz · HN
AletheionAGI – Grounding enforcement for AI agents

Cloud platform to watch and control autonomous AI coding agents.
pranav100000 · HN
Aether – Run Claude Code, Codex, or OpenCode in devboxes you can watch