Started as my MA thesis in 2022, kept building since, mostly solo with a little funding. Fully open source, self-hosted, AGPL-3.0, Next.js + Deck.gl on the frontend, Strapi backend, Python ETL pulling from museum open-access APIs. Currently indexing over 100k artifacts from all over the world, across 8 collections (Met, V&A, SMB Berlin). Recently added an md export so researchers can download provenance data for a filtered set of artifacts.
The infrastructure is conceptualized as an indexer, not a hoster. Even images are kept as URLs pointing to the source institutions. It's connective tissue between archives that were never designed to speak to each other, with an origin-first search UI concept. The data model is on purpose flat, to avoid encoding problematic taxonomies, and routes researchers directly to the source giving responsibility to the source institutions rather than duplicating institutional data. It indexes the relationship between origin sites and destination collections.
Coming from a design background, taking this project from prototype to production app has been incredibly rewarding, but honestly it\u2019s getting a little bit overwhelming to scale alone. I would love community\u2019s feedback on performance scaling, any code contributions, data pipelines for missing museum apis or general feedback.
Repo: https://github.com/hburakyel/ex-situ
Live: https://exsitu.app"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Ex Situ \u2013 Open-source spatial index of displaced cultural artifacts"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://exsitu.app/map"}},"_tags":["story","author_hbyel","story_48988158","show_hn"],"author":"hbyel","children":[48988677,48988753,48988960,48988995,48989035,48989268,48989317,48989522,48989530,48989919,48990114,48991281,48992302,48992673,48992779,48995536,48995708,48996086],"created_at":"2026-07-21T04:48:32Z","created_at_i":1784609312,"num_comments":41,"objectID":"48988158","points":51,"story_id":48988158,"story_text":"Hi, I designed and developed a spatial index that maps museum artefacts as connecting arcs/hyperlinks from their origin site to institutional location/sources. The Index specifically looks at western/euro-american institutions and maps their collection categorised by them under Islamic art, Asian/African art, ethnological collections, Middle East, South America etc.
Started as my MA thesis in 2022, kept building since, mostly solo with a little funding. Fully open source, self-hosted, AGPL-3.0, Next.js + Deck.gl on the frontend, Strapi backend, Python ETL pulling from museum open-access APIs. Currently indexing over 100k artifacts from all over the world, across 8 collections (Met, V&A, SMB Berlin). Recently added an md export so researchers can download provenance data for a filtered set of artifacts.
The infrastructure is conceptualized as an indexer, not a hoster. Even images are kept as URLs pointing to the source institutions. It's connective tissue between archives that were never designed to speak to each other, with an origin-first search UI concept. The data model is on purpose flat, to avoid encoding problematic taxonomies, and routes researchers directly to the source giving responsibility to the source institutions rather than duplicating institutional data. It indexes the relationship between origin sites and destination collections.
Coming from a design background, taking this project from prototype to production app has been incredibly rewarding, but honestly it\u2019s getting a little bit overwhelming to scale alone. I would love community\u2019s feedback on performance scaling, any code contributions, data pipelines for missing museum apis or general feedback.
Repo: https://github.com/hburakyel/ex-situ
Live: https://exsitu.app","title":"Show HN: Ex Situ \u2013 Open-source spatial index of displaced cultural artifacts","updated_at":"2026-07-24T10:59:51Z","url":"https://exsitu.app/map"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"adi1"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["arc","institute"],"value":"Hi HN! We\u2019re Adi and Alex, founders of Bullet, a faster coding agent.
Bullet started in a senior year dorm. We were fresh out of working at AppLovin and Citadel, and naturally thought we were on a sure path to startup success. We were going to use our skills optimizing stock pricing calculation speeds and agent document context to take over the world. So, Bullet started as an AI hedge fund, a browser-use agent, synthetic financial data (oof), a mobile IDE, and a bunch of other things. We wanted to build something people wanted, but it seemed like everything we built was just terrible, useless, or both.
So, we decided to do something completely different, something completely out of the blue, something that no one had ever done before. Solve a problem we actually had.
Over the course of six pivots, we suffered. Throughout all of our adventures, one final boss kept getting in our way. Claude Code and his little brother Codex. We were spending hours waiting for coding agents like Claude Code and Codex, and got so frustrated to the point that I downloaded the Claude Code whip. We had spent months of time waiting for six codebases-worth of useless coding agent work.
Lightbulb moment. There\u2019s nothing more noble than destroying the institutions! Let\u2019s take on Claude Code and Codex, we can do it! Piece of cake!
And so, Bullet started off as a side project. We used the Claude Code to improve the Claude Code:
1. Model routing. Do you regret giving a task to Fable when it could have literally been done by Sonnet?
2. Targeted code + context search. We think embedding the whole repo is dumb. We also think sticking the whole context (or compressed context) in chat is dumb. So we do faster and better greps over both.
3. Aggressive context hygiene. Tool output is bounded, stale screenshots disappear, we don\u2019t re-read files\u2026the garbage never floods the model.
4. Efficient turns. Batch independent investigation, make one surgical edit, then perform one focused verification. Internal measurement showed 16% fewer round trips and 27% lower cost.
5. The Flash. We prayed to Barry Allen for speed.
And thank the Flash, he gave us speed! On SWE-bench Verified, Bullet resolved 479/500 (95.8%) in one attempt, averaging 119s per task, 35\u201367% faster than mini-SWE-agent + Fable/Sol depending on task. Full results and methodology here (https://www.codewithbullet.com/blog/benchmark-results.html)
Eventually we started using it every day and never went back.
Listed above were just some of the things about Claude Code that frustrated us the most, but we are constantly optimizing every day (look at that, maybe we did learn something from our jobs).
In our development, the biggest insight was that model speed matters less than reducing round trips. Independent searches, reads, and commands should happen in parallel, while dependent editing and verification stay sequential. One surprising obstacle was code search, small issues like regex-dialect mismatches caused silent misses and sent agents down completely wrong paths, so we built targeted search with fallbacks and bounded context. The most interesting use case so far has been long iterative work (like benchmarks, data pipelines, and evaluation loops), where each step depends on the last and running multiple agents can\u2019t help as much.
Here\u2019s the video demo (https://www.youtube.com/watch?v=rWVmG5fRKgE)
We hope that you guys try out Bullet if you are suffering with speed as much as we were, and we hope it brings you joy, rainbows, and faster responses. And if it\u2019s terrible, let us know it\u2019s terrible (we\u2019re masochists btw)! We'll be in the comments all day, you can also contact us at bullet@davidhf.com.
You can try it at https://codewithbullet.com.
P.S: we hid a code on the website, see if you can unlock the secret page at the footer, all built with Bullet"},"title":{"matchLevel":"none","matchedWords":[],"value":"Launch HN: Bullet (YC S26) \u2013 A Faster Coding Agent"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.codewithbullet.com"}},"_tags":["story","author_adi1","story_49283063","launch_hn"],"author":"adi1","children":[49283583,49287458,49287633,49288295,49288442,49288856,49289059,49289151,49289588,49290178,49291345,49291928,49292123,49292215,49292937,49293202,49293372,49293672,49293755,49293804,49294720,49294779,49294820,49295173,49295348,49295451,49295975,49300096,49300101,49304230,49306130,49353111],"created_at":"2026-08-13T08:14:30Z","created_at_i":1786608870,"num_comments":89,"objectID":"49283063","points":121,"story_id":49283063,"story_text":"Hi HN! We\u2019re Adi and Alex, founders of Bullet, a faster coding agent.
Bullet started in a senior year dorm. We were fresh out of working at AppLovin and Citadel, and naturally thought we were on a sure path to startup success. We were going to use our skills optimizing stock pricing calculation speeds and agent document context to take over the world. So, Bullet started as an AI hedge fund, a browser-use agent, synthetic financial data (oof), a mobile IDE, and a bunch of other things. We wanted to build something people wanted, but it seemed like everything we built was just terrible, useless, or both.
So, we decided to do something completely different, something completely out of the blue, something that no one had ever done before. Solve a problem we actually had.
Over the course of six pivots, we suffered. Throughout all of our adventures, one final boss kept getting in our way. Claude Code and his little brother Codex. We were spending hours waiting for coding agents like Claude Code and Codex, and got so frustrated to the point that I downloaded the Claude Code whip. We had spent months of time waiting for six codebases-worth of useless coding agent work.
Lightbulb moment. There\u2019s nothing more noble than destroying the institutions! Let\u2019s take on Claude Code and Codex, we can do it! Piece of cake!
And so, Bullet started off as a side project. We used the Claude Code to improve the Claude Code:
1. Model routing. Do you regret giving a task to Fable when it could have literally been done by Sonnet?
2. Targeted code + context search. We think embedding the whole repo is dumb. We also think sticking the whole context (or compressed context) in chat is dumb. So we do faster and better greps over both.
3. Aggressive context hygiene. Tool output is bounded, stale screenshots disappear, we don\u2019t re-read files\u2026the garbage never floods the model.
4. Efficient turns. Batch independent investigation, make one surgical edit, then perform one focused verification. Internal measurement showed 16% fewer round trips and 27% lower cost.
5. The Flash. We prayed to Barry Allen for speed.
And thank the Flash, he gave us speed! On SWE-bench Verified, Bullet resolved 479/500 (95.8%) in one attempt, averaging 119s per task, 35\u201367% faster than mini-SWE-agent + Fable/Sol depending on task. Full results and methodology here (https://www.codewithbullet.com/blog/benchmark-results.html)
Eventually we started using it every day and never went back.
Listed above were just some of the things about Claude Code that frustrated us the most, but we are constantly optimizing every day (look at that, maybe we did learn something from our jobs).
In our development, the biggest insight was that model speed matters less than reducing round trips. Independent searches, reads, and commands should happen in parallel, while dependent editing and verification stay sequential. One surprising obstacle was code search, small issues like regex-dialect mismatches caused silent misses and sent agents down completely wrong paths, so we built targeted search with fallbacks and bounded context. The most interesting use case so far has been long iterative work (like benchmarks, data pipelines, and evaluation loops), where each step depends on the last and running multiple agents can\u2019t help as much.
Here\u2019s the video demo (https://www.youtube.com/watch?v=rWVmG5fRKgE)
We hope that you guys try out Bullet if you are suffering with speed as much as we were, and we hope it brings you joy, rainbows, and faster responses. And if it\u2019s terrible, let us know it\u2019s terrible (we\u2019re masochists btw)! We'll be in the comments all day, you can also contact us at bullet@davidhf.com.
You can try it at https://codewithbullet.com.
P.S: we hid a code on the website, see if you can unlock the secret page at the footer, all built with Bullet","title":"Launch HN: Bullet (YC S26) \u2013 A Faster Coding Agent","updated_at":"2026-09-07T04:00:12Z","url":"https://www.codewithbullet.com"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"fedecaccia"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["arc","institute"],"value":"Hi HN, I'm a nuclear engineer and tech entrepreneur. After working for 3 years in the National Atomic Energy Commision (CNEA) in HPC software for nuclear simulations, I co-founded ratherlabs.com, a software company providing blockchain solutions for startups. Rather Labs business reached ~6 million usd in annual revenue in 2024; now demand is decreasing as our niche clients are using AI to launch their MVPs.
Now I'm joining my scientific background with my entrepreneurial inclinations to think of problems related to the energy industry. Nuclear is experiencing a renaissance now (it was in a dark age when I was studying after the Fukushima event) so I think this is the right moment for me to jump again into the field.
Reactor atlas is an interactive nuclear reactor map and an intelligence layer on top of it. The basic layer indexes:
- power reactors\n - research reactors\n - fuel facilities\nAs an engineer, I used to code in fortran and c++ when I was working at CNEA, and later I participated in the first Rather Labs projects architecting complex async systems, mostly using MERN stack. I'm no longer coding anymore. I'm focused on designing robust systems with AI agents.
I mainly used Claude Fable 5.1 to develop reactoratlas.com, deploying on vercel and using mostly nextjs, threejs, postgreSQL and some cron jobs to query and update data. I miss coding as in the old days, but I haven't code a single line in this project. And I strongly believe we humans shouldn't code anymore: our responsibility is now on designing and supervising AI systems.
Thanks for your attention!"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Reactor Atlas"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://reactoratlas.com"}},"_tags":["story","author_fedecaccia","story_49549148","show_hn"],"author":"fedecaccia","children":[49549149,49561143,49561169,49561251,49561710,49562107,49562226,49563318,49578036],"created_at":"2026-09-03T12:33:01Z","created_at_i":1788438781,"num_comments":25,"objectID":"49549148","points":77,"story_id":49549148,"story_text":"Hi HN, I'm a nuclear engineer and tech entrepreneur. After working for 3 years in the National Atomic Energy Commision (CNEA) in HPC software for nuclear simulations, I co-founded ratherlabs.com, a software company providing blockchain solutions for startups. Rather Labs business reached ~6 million usd in annual revenue in 2024; now demand is decreasing as our niche clients are using AI to launch their MVPs.
Now I'm joining my scientific background with my entrepreneurial inclinations to think of problems related to the energy industry. Nuclear is experiencing a renaissance now (it was in a dark age when I was studying after the Fukushima event) so I think this is the right moment for me to jump again into the field.
Reactor atlas is an interactive nuclear reactor map and an intelligence layer on top of it. The basic layer indexes:
- power reactors\n - research reactors\n - fuel facilities\nAs an engineer, I used to code in fortran and c++ when I was working at CNEA, and later I participated in the first Rather Labs projects architecting complex async systems, mostly using MERN stack. I'm no longer coding anymore. I'm focused on designing robust systems with AI agents.
I mainly used Claude Fable 5.1 to develop reactoratlas.com, deploying on vercel and using mostly nextjs, threejs, postgreSQL and some cron jobs to query and update data. I miss coding as in the old days, but I haven't code a single line in this project. And I strongly believe we humans shouldn't code anymore: our responsibility is now on designing and supervising AI systems.
Thanks for your attention!","title":"Show HN: Reactor Atlas","updated_at":"2026-09-06T21:18:42Z","url":"https://reactoratlas.com"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"KnoxProtocol"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["arc","institute"],"value":"https://giganticresearch.com
Yo whats up everyone?\nSo let me drop right into it and not waste your time if you are reading this. I instantly grew a dislike for arXiv when I spent days writing up a research paper and then came to find out I need an endorsement to post at all. No pun intended, I should have done research but it was a slap in the face, especially since that same paper was accepted to ICTAI 2026 by someone who did the research for fun, 0 financial backing, 0 institutional backing, 0 affiliation. Research shouldn't be gated like that. Research is research and I can't imagine the amount of good, ground breaking research from everyday people that never sees the light of day because of this. Sure there is Zenodo, but you still have enough options to tell your lifes story which certainly effects viewership. And they have their own gates mechanism which is communities, want to post to a specific community where your audience is present? hold on there buster, needs to be reviewed before you can post.\nSo i thought to myself, this is dumb, research is research and there should be a place for just that. and that might exist but I wanted to make my own version of it. So I did, giganticresearch.com. Its aim isn't to compete, its aim is to aggregate research from anyone who has something they want to share, no preferential treatment, the only research on display is the most recently uploaded research. You want your research shown? upload more! you want one of my 7 tiered badges that mean absolutely nothing but a cool little something next to your name that shows how much you've contributed? then make an account! and here is the wonderful part, you dont need to make an account to upload, anonymous is the default. I store 0 data on where it came from. The only thing an account does is ties you to the research, gets you a badge that means nothing really, and the ability to show you what you've uploaded and what you have favorited. The option to delete your account is there as well, and all the research you uploaded if you choose that option. Anon uploads stay uploaded. I wouldn't have a way to track an anon upload anyway because I store no data but the upload itself and the sha 256 tied to that research. There are two hard no go research topics that I will not allow to be uploaded, and you can read about on the About page. Other than that, push it, thats the point. I want us to have a research depot where you can find just about anything. Big or small. And it doesnt need to be YOUR research, it can be any research you want to share, on pretty much any topic you want to share. Also I implemented a forum, where anon is the default too, but feel free to use your account if you want there as well. The account is also just there to give you a handle to go by. No data is stored on that either in terms of identifying you. The anon part isn't there to be evasive per se, its also there because in this day and age, it seems privacy is less and less a thing, so if I can provide that in some way, then I will. I've been trying to promote this all day and I haven't had one person upload anything. It is just some of my research that I used to seed the site a little bit and thats it. So if any of this sounds interesting to anyone reading it and if you have any research you would like to share, if you could take a few mins and upload to my website I'd appreciate that and I thank you in advance my friend. I made the site as frictionless as possible, time is the only currency that matters in this world, the most valuable currency and the one currency we can not acquire more of, and I value your time so I made sure to make the process take up as little of it as possible. Again, I thank you for reading this even if you dont upload anything, and I double thank you if you do, either way, you get a thank you from me."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Gigantic Research, Friend"}},"_tags":["story","author_KnoxProtocol","story_49593113","show_hn"],"author":"KnoxProtocol","children":[49593114,49593769],"created_at":"2026-09-07T02:22:02Z","created_at_i":1788747722,"num_comments":3,"objectID":"49593113","points":1,"story_id":49593113,"story_text":"https://giganticresearch.com
Yo whats up everyone?\nSo let me drop right into it and not waste your time if you are reading this. I instantly grew a dislike for arXiv when I spent days writing up a research paper and then came to find out I need an endorsement to post at all. No pun intended, I should have done research but it was a slap in the face, especially since that same paper was accepted to ICTAI 2026 by someone who did the research for fun, 0 financial backing, 0 institutional backing, 0 affiliation. Research shouldn't be gated like that. Research is research and I can't imagine the amount of good, ground breaking research from everyday people that never sees the light of day because of this. Sure there is Zenodo, but you still have enough options to tell your lifes story which certainly effects viewership. And they have their own gates mechanism which is communities, want to post to a specific community where your audience is present? hold on there buster, needs to be reviewed before you can post.\nSo i thought to myself, this is dumb, research is research and there should be a place for just that. and that might exist but I wanted to make my own version of it. So I did, giganticresearch.com. Its aim isn't to compete, its aim is to aggregate research from anyone who has something they want to share, no preferential treatment, the only research on display is the most recently uploaded research. You want your research shown? upload more! you want one of my 7 tiered badges that mean absolutely nothing but a cool little something next to your name that shows how much you've contributed? then make an account! and here is the wonderful part, you dont need to make an account to upload, anonymous is the default. I store 0 data on where it came from. The only thing an account does is ties you to the research, gets you a badge that means nothing really, and the ability to show you what you've uploaded and what you have favorited. The option to delete your account is there as well, and all the research you uploaded if you choose that option. Anon uploads stay uploaded. I wouldn't have a way to track an anon upload anyway because I store no data but the upload itself and the sha 256 tied to that research. There are two hard no go research topics that I will not allow to be uploaded, and you can read about on the About page. Other than that, push it, thats the point. I want us to have a research depot where you can find just about anything. Big or small. And it doesnt need to be YOUR research, it can be any research you want to share, on pretty much any topic you want to share. Also I implemented a forum, where anon is the default too, but feel free to use your account if you want there as well. The account is also just there to give you a handle to go by. No data is stored on that either in terms of identifying you. The anon part isn't there to be evasive per se, its also there because in this day and age, it seems privacy is less and less a thing, so if I can provide that in some way, then I will. I've been trying to promote this all day and I haven't had one person upload anything. It is just some of my research that I used to seed the site a little bit and thats it. So if any of this sounds interesting to anyone reading it and if you have any research you would like to share, if you could take a few mins and upload to my website I'd appreciate that and I thank you in advance my friend. I made the site as frictionless as possible, time is the only currency that matters in this world, the most valuable currency and the one currency we can not acquire more of, and I value your time so I made sure to make the process take up as little of it as possible. Again, I thank you for reading this even if you dont upload anything, and I double thank you if you do, either way, you get a thank you from me.","title":"Show HN: Gigantic Research, Friend","updated_at":"2026-09-07T08:04:58Z"}],"hitsPerPage":50,"nbHits":27,"nbPages":1,"page":0,"params":"query=Arc+Institute&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":13,"processingTimingsMS":{"_request":{"roundTrip":14},"afterFetch":{"format":{"highlighting":1,"total":1}},"fetch":{"query":9,"scanning":2,"total":12},"total":13},"query":"Arc Institute","serverTimeMS":15}