Directory
AgentsShipped lists real agents from public posts, repositories, and maker submissions. Type, industry, stack, deployment, and ROI are filled only when the source text says so.
Double opt-in. A confirm email comes first. Unsubscribe is in every digest.
Loading listings…
A Tic-Tac-Toe game powered by Reinforcement Learning using the Q-Learning algorithm. The AI agent learns from rewards and penalties through thousands of training games and improves its decision-making skills. Developed using Python and NumPy.
GitHubFree AI YouTube Growth Agent for Macherla Guru
GitHubNeuroEDA is a multi-agent AI platform for end-to-end chip design automation built entirely on open-source EDA tools. It covers digital, analog, and mixed-signal flows—from concept and SPEC to RTL, functional verification, synthesis, equivalence checking, place-and-route, GDS/OASIS, and physical verification.
GitHubAgent-ready marketplace for group plans: AI agents find who's free, negotiate with the venue, split the bill and settle it with PayPal. PayPal AI Hackathon 2026.
GitHubI built a plain-text spreadsheet format and an app for working with it. It began with small tasks like tracking my dog's health records and organizing records for tax season. Full spreadsheet apps always felt excessive, while Markdown tables don't support formulas. Also, its compact and readable syntax lets AI read and edit a workbook directly, without spreadsheet-specific tools. You can try the in-app agent on the desktop version with ChatGPT sign-in. Ordinate is now open source and available t
Hacker NewsHi guys, I built a tool www.lovespreadsheets.com earlier this year and a huge problem we kept running into is processing messy, real-world, complex spreadsheets for AI agents. Even a "medium" sized spreadsheet converts to about 1m+ tokens if read fully, which immediately blows up the current context windows of most models. So I noticed most agents sample data from spreadsheets in chunks instead. So I (& Claude) built this library Sheetgraph, https://github.com/asharma327/shee
Hacker NewsHey HN, We build financial AI agents, and Apgar is the tool we wrote to see whether a harness change made an agent better or worse in production. Our offline evals can't cover every kind of question or session real users bring, and the LLM judge we run in Langfuse is too expensive to use on more than a small slice of traffic, so some failures get through. Apgar is a small release health checker that sits on top of our Langfuse data. It picks up the release from the production traces, and for the
Hacker News