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":"2026-08-22T22:55:52Z","url":"https://www.codewithbullet.com"}],"hitsPerPage":50,"nbHits":25,"nbPages":1,"page":0,"params":"query=Arc+Institute&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":16,"processingTimingsMS":{"_request":{"roundTrip":14},"afterFetch":{"format":{"total":1}},"fetch":{"query":10,"scanning":4,"total":15},"total":16},"query":"Arc Institute","serverTimeMS":18}