News for hackers. Stuff that matters.

junhoyeo

junhoyeo on Hacker News

Show HN: Contrabass – Go and Charm Stack Implementation of OpenAI's Symphony

Posted by junhoyeo on Saturday March 07, 2026 @01:01AM
from the show-hn dept.

https://github.com/junhoyeo/contrabass

OpenAI released Symphony — a project-level orchestrator that watches your Linear board, spawns isolated coding agents per task, and lands PRs automatically. Engineers manage work at a higher level instead of supervising agents one by one.They shipped an Elixir reference implementation and explicitly said "implement it in any language you want." So I built the Go version — with multi-agent team...

( Read More... | 1 comment | on HN )

Show HN: Tokscale – See who's burning the most tokens across all platforms

Posted by junhoyeo on Tuesday December 23, 2025 @10:21AM
from the show-hn dept.

https://github.com/junhoyeo/tokscale

I've been through all of them. Claude Code, Codex CLI, Gemini CLI, Cursor. Finally settled on OpenCode.But I had billions of token data scattered across 5 different tools with no unified view. So I built Tokscale.The problem:- Token usage scattered across multiple AI coding tools- Each stores data in different formats and locations- Claude Code deletes your history after 30 days by default (!)-...

( Read More... | no comments | 2 points | on HN )
Re:Show HN: BetterOCR combines and corrects multiple OCR engines with ... on Sunday October 29, 2023 @02:26AM (#38056243)
Yup! But I'm still exploring options. (any recommendations would be welcomed!) Here are some candidates I'm considering:

- https://github.com/mindee/doctr

- https://github.com/open-mmlab/mmocr

- https://github.com/PaddlePaddle/PaddleOCR (honestly I don't know Mandarin so I'm a bit stuck)

- https://github.com/clovaai/donut -- While it's primarily an "OCR-free document understanding transformer," I think it's worth experimenting with. Think I can sort this out by letting the LLM reason through it multiple times (although this will impact performance)

- yesterday got a suggestion to consider https://github.com/kakaobrain/pororo -- don't think development is still active but the results are pretty great on Korean text

Re:Show HN: BetterOCR combines and corrects multiple OCR engines with ... on Sunday October 29, 2023 @01:06AM (#38055933)
My pleasure
Re:Show HN: BetterOCR combines and corrects multiple OCR engines with ... on Sunday October 29, 2023 @01:05AM (#38055925)
Thanks!
Re:Show HN: BetterOCR combines and corrects multiple OCR engines with ... on Sunday October 29, 2023 @01:05AM (#38055924)
Super -- I'm thrilled you enjoyed it!
Re:Show HN: BetterOCR combines and corrects multiple OCR engines with ... on Sunday October 29, 2023 @01:04AM (#38055920)
Thanks!

PDF -> Markdown looks like a pretty great use case

Just added box detection support -- maybe I'll start from here https://github.com/junhoyeo/BetterOCR#-box-detection

Re:Show HN: BetterOCR combines and corrects multiple OCR engines with ... on Sunday October 29, 2023 @01:01AM (#38055902)
Thinking to add LLaMA or other OSS LLM models soon
Re:The Web Standard Mini App Problem (2022) on Friday September 23, 2022 @08:01PM (#32958497)
But is there a meaningful "Super App" company in the US?
Re:Decentralized Web3 Cross-Chain Payment Protocol on Wednesday September 14, 2022 @01:38AM (#32833663)
it'll look better with number formatting: $9696865.84 -> $9,696,865.84