OpenRobots β free, open-source robots.txt generator for AI crawlers Comments URL: https://news.ycombinator.com/item?id=49579305 Points: 1 # Comments: 0
Hello HN! I built a pipeline which fetches SEC EDGAR 10k and 10qs for more than 600 companies, maps xbrl-tags onto around 35 financial concepts and computes growth- , fundamental- and valuation-multiples (prices provided by yfinance). This project originated bc I wanted clean, non-third-party financial data in order to judge a trading thesis of mine. I could not find any app providing such data (for free), let alone being open source. Turns out there are no data providers because xbrl of 10ks and 10qs SUCKS(!!!!). It is messy, unregulated and devastated. Its the wild west of finance. A projecβ¦
#hackernews #showhn #projects #10qs #edgar #opensource #10ks #data
built a self-hosted WhatsApp/Discord bridge that keeps conversations synced between both platforms. It supports messages, media, replies, edits, reactions, pins, and more. The Meta is not triggered for human paced convos and hence a normal number can be used, have been using it successfully for a decent time now. The project is open source, so feel free to check it out, try it, report issues, or contribute. Would love to hear your feedback and suggestions! https://github.com/Karvy-Singh/OSdc-wa Comments URL: https://news.ycombinator.com/item?id=49577432 Points: 3 # Comments: 0
Hey yβall! This is a repost[0], itβs been one month since weβve launched and have plenty[1] to show for it. Weβve grown to 600+ users so far, became part of Open Collective under Open Source Europe and weβve just started. For those who donβt know, the project is open-source[2] under the AGPL. Come over and join the community! [0]: https://news.ycombinator.com/item?id=49208458 [1]: https://textlog.cc/blog/recap-v2 [2]: https://github.com/stagas/textlog Comments URL: https://news.ycombinator.com/item?id=49577048 Points: 1 # Comments: 0

I had astra build a DOOM 64 clone where you play as elizier fighting hordes of misaligned AI demons β’ the goal is to reach the shutdown button β’ it's actually really hard to beat at the highest p(doom) levels β’ sama appears as a miniboss open source here: https://github.com/transitive-bullshit/ai-safety-doom Comments URL: https://news.ycombinator.com/item?id=49575532 Points: 1 # Comments: 0

Article URL: https://github.com/antonyrag/ragleap-core Comments URL: https://news.ycombinator.com/item?id=49573630 Points: 1 # Comments: 1
Why can't we get an agent scheduler that supports all of the following: - git compatible - agent agnostic - 100% open source - os and system-agnostic - multi-runner support - support mcp/ui/http - unlimited routines/crons So I built one, moadim.io is a local Rust daemon you install in the target machine, give it a name and manage its routines via a Git repository, wants a new routine that send you a daily message from this machine? Create a pr and merge, have another routine that run every hour to pull the latest changes to the ~/.config/moadim folder. With more than 1,000 users, I define thiβ¦
Why can't we get an agent scheduler that supports all of the following: - git compatible - agent agnostic - 100% open source - os and system-agnostic - multi-runner support - support mcp/ui/http - unlimited routines/crons So I built one, moadim.io is a local Rust daemon you install in the target machine, give it a name and manage its routines via a Git repository, wants a new routine that send you a daily message from this machine? Create a pr and merge, have another routine that run every hour to pull the latest changes to the ~/.config/moadim folder. With more than 1,000 users, I define thiβ¦
How scalably can we cheaply fine-tune small models for well-defined tasks? Frontier models are bad at clock reading. I fine-tuned a tiny 450M model from Liquid AI to match GPT-5.6 Sol and beat Fable 5.1 on this task. Hereβs my fine-tuned open model called Time Wizard. Comments URL: https://news.ycombinator.com/item?id=49570829 Points: 1 # Comments: 0