Google DeepMind and their new startup Isomorphic Labs, are expanding into drug discovery. They developed AlphaFold3 as their model to accelerate drug discovery and create demand from big pharma. They already signed Novartis and Eli Lilly for $3 billion - Google\u2019s becoming a pharma company! (https://www.isomorphiclabs.com/articles/isomorphic-labs-kick...)
AlphaFold3 is a biomolecular structure prediction model that can do three main things: (1) Predict the structure of proteins; (2) Predict the structure of drug-protein interactions; (3) Predict nucleic acid - protein complex structure.
AlphaFold3 is incredibly important for science because it vastly accelerates the mapping of protein structures. It takes one PhD student their entire PhD to do one structure. With AlphaFold3, you get a prediction in minutes on par with experimental accuracy.
There\u2019s just one problem: when DeepMind published AlphaFold3 in May (https://www.nature.com/articles/s41586-024-07487-w), there was no code. This \nbrought up questions about reproducibility (https://www.nature.com/articles/d41586-024-01463-0) as well as complaints from the scientific community (https://undark.org/2024/06/06/opinion-alphafold-3-open-sourc...).
AlphaFold3 is a fundamental advance in structure modeling technology that the entire biotech industry deserves to be able to reap the benefits from. Its applications are vast, including:
- CRISPR gene editing technologies, where scientists can see exactly how the DNA interacts with the scissor Cas protein;
- Cancer research - predicting how a potential drug binds to the cancer target. One of the highlights in DeepMind\u2019s paper is the prediction of a clinical KRAS inhibitor in complex with its target.
- Antibody / nanobody to target predictions. AlphaFold3 improves accuracy on this class of molecules 2 fold compared to the next best tool.
Unfortunately, no companies can use it since it is under a non-commercial license!
Today we are releasing the full model trained on single chain proteins (capability 1 above), with the other two capabilities to be trained and released soon. We also include the training code. Weights will be released once training and benchmarking is complete. We wanted this to be truly open source so we used the Apache 2.0 license.
Deepmind published the full structure of the model, along with each components\u2019 pseudocode in their paper. We translated this fully into PyTorch, which required more reverse engineering than we thought!
When building the initial version, we discovered multiple issues in DeepMind\u2019s paper that would interfere with the training - we think the deep learning community might find these especially interesting. (Diffusion folks, we would love feedback on this!) These include:
- MSE loss scaling differs from Karras et al. (2022). The weighting provided in the paper does not downweigh the loss at high noise levels.
- Omission of residual layers in the paper - we add these back and see benefits in gradient flow and convergence. Anyone have any idea why Deepmind may have omitted the residual connections in the DiT blocks?
- The MSA module, in its current form, has dead layers. The last pair weighted averaging and transition layers cannot contribute to the pair representation, hence no grads. We swap the order to the one in the ExtraMsaStack in AlphaFold2. An alternative solution would be to use weight sharing, but whether this is done is ambiguous in the paper.
More about those issues here: https://github.com/Ligo-Biosciences/AlphaFold3
How this came about: we are building Ligo (YC S24), where we are using ideas from AlphaFold3 for enzyme design. We thought open sourcing it was a nice side quest to benefit the community.
For those on Twitter, there was a good thread a few days ago that has more information: \nhttps://twitter.com/ArdaGoreci/status/1830744265007480934.
A few shoutouts: \nA huge thanks to OpenFold for pioneering the previous open source implementation of AlphaFold\nWe did a lot of our early prototyping with proteinFlow developed by Lisa at AdaptyvBio we also look forward to partnering with them to bring you the next versions!\nWe are also partnering with Basecamp Research to supply this model with the best sequence data known to science. \nMatthew Clark (https://batisio.co.uk) for his amazing animations!
We\u2019re around to answer questions and look forward to hearing from you!"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: An open-source implementation of AlphaFold3"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/Ligo-Biosciences/AlphaFold3"}},"_tags":["story","author_EdHarris","story_41448439","show_hn"],"author":"EdHarris","children":[41448800,41448948,41448989,41449014,41449322,41449933,41450513,41450570,41451243,41453870,41454999,41457339],"created_at":"2024-09-04T17:44:17Z","created_at_i":1725471857,"num_comments":37,"objectID":"41448439","points":314,"story_id":41448439,"story_text":"Hi HN - we\u2019re the founders of Ligo Biosciences and are excited to share an open-source implementation of AlphaFold3, the frontier model for protein structure prediction.
Google DeepMind and their new startup Isomorphic Labs, are expanding into drug discovery. They developed AlphaFold3 as their model to accelerate drug discovery and create demand from big pharma. They already signed Novartis and Eli Lilly for $3 billion - Google\u2019s becoming a pharma company! (https://www.isomorphiclabs.com/articles/isomorphic-labs-kick...)
AlphaFold3 is a biomolecular structure prediction model that can do three main things: (1) Predict the structure of proteins; (2) Predict the structure of drug-protein interactions; (3) Predict nucleic acid - protein complex structure.
AlphaFold3 is incredibly important for science because it vastly accelerates the mapping of protein structures. It takes one PhD student their entire PhD to do one structure. With AlphaFold3, you get a prediction in minutes on par with experimental accuracy.
There\u2019s just one problem: when DeepMind published AlphaFold3 in May (https://www.nature.com/articles/s41586-024-07487-w), there was no code. This \nbrought up questions about reproducibility (https://www.nature.com/articles/d41586-024-01463-0) as well as complaints from the scientific community (https://undark.org/2024/06/06/opinion-alphafold-3-open-sourc...).
AlphaFold3 is a fundamental advance in structure modeling technology that the entire biotech industry deserves to be able to reap the benefits from. Its applications are vast, including:
- CRISPR gene editing technologies, where scientists can see exactly how the DNA interacts with the scissor Cas protein;
- Cancer research - predicting how a potential drug binds to the cancer target. One of the highlights in DeepMind\u2019s paper is the prediction of a clinical KRAS inhibitor in complex with its target.
- Antibody / nanobody to target predictions. AlphaFold3 improves accuracy on this class of molecules 2 fold compared to the next best tool.
Unfortunately, no companies can use it since it is under a non-commercial license!
Today we are releasing the full model trained on single chain proteins (capability 1 above), with the other two capabilities to be trained and released soon. We also include the training code. Weights will be released once training and benchmarking is complete. We wanted this to be truly open source so we used the Apache 2.0 license.
Deepmind published the full structure of the model, along with each components\u2019 pseudocode in their paper. We translated this fully into PyTorch, which required more reverse engineering than we thought!
When building the initial version, we discovered multiple issues in DeepMind\u2019s paper that would interfere with the training - we think the deep learning community might find these especially interesting. (Diffusion folks, we would love feedback on this!) These include:
- MSE loss scaling differs from Karras et al. (2022). The weighting provided in the paper does not downweigh the loss at high noise levels.
- Omission of residual layers in the paper - we add these back and see benefits in gradient flow and convergence. Anyone have any idea why Deepmind may have omitted the residual connections in the DiT blocks?
- The MSA module, in its current form, has dead layers. The last pair weighted averaging and transition layers cannot contribute to the pair representation, hence no grads. We swap the order to the one in the ExtraMsaStack in AlphaFold2. An alternative solution would be to use weight sharing, but whether this is done is ambiguous in the paper.
More about those issues here: https://github.com/Ligo-Biosciences/AlphaFold3
How this came about: we are building Ligo (YC S24), where we are using ideas from AlphaFold3 for enzyme design. We thought open sourcing it was a nice side quest to benefit the community.
For those on Twitter, there was a good thread a few days ago that has more information: \nhttps://twitter.com/ArdaGoreci/status/1830744265007480934.
A few shoutouts: \nA huge thanks to OpenFold for pioneering the previous open source implementation of AlphaFold\nWe did a lot of our early prototyping with proteinFlow developed by Lisa at AdaptyvBio we also look forward to partnering with them to bring you the next versions!\nWe are also partnering with Basecamp Research to supply this model with the best sequence data known to science. \nMatthew Clark (https://batisio.co.uk) for his amazing animations!
We\u2019re around to answer questions and look forward to hearing from you!","title":"Show HN: An open-source implementation of AlphaFold3","updated_at":"2024-10-14T00:18:58Z","url":"https://github.com/Ligo-Biosciences/AlphaFold3"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Brajeshwar"},"title":{"matchLevel":"none","matchedWords":[],"value":"Google DeepMind has grand ambitions to 'cure all diseases' with AI"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"https://fortune.com/2025/07/06/deepmind-isomorphic-labs-cure-all-diseases-ai-now-first-human-trials/"}},"_tags":["story","author_Brajeshwar","story_44491783"],"author":"Brajeshwar","children":[44491832,44500956],"created_at":"2025-07-07T16:08:23Z","created_at_i":1751904503,"num_comments":1,"objectID":"44491783","points":4,"story_id":44491783,"title":"Google DeepMind has grand ambitions to 'cure all diseases' with AI","updated_at":"2025-07-08T15:31:45Z","url":"https://fortune.com/2025/07/06/deepmind-isomorphic-labs-cure-all-diseases-ai-now-first-human-trials/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"insin"},"story_text":{"matchLevel":"none","matchedWords":[],"value":""},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: React and react-router: forms which work without client-side JavaScript"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"https://isomorphic-lab.herokuapp.com"}},"_tags":["story","author_insin","story_8791536","show_hn"],"author":"insin","created_at":"2014-12-24T04:27:46Z","created_at_i":1419395266,"num_comments":0,"objectID":"8791536","points":4,"story_id":8791536,"story_text":"","title":"Show HN: React and react-router: forms which work without client-side JavaScript","updated_at":"2024-09-19T21:29:58Z","url":"https://isomorphic-lab.herokuapp.com"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"artiver"},"title":{"matchLevel":"none","matchedWords":[],"value":"Deep\u00adMind\u2019s Demis Has\u00ads\u00adabis un\u00adveils his vi\u00adsion for AI\u2019s fu\u00adture in biotech"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"https://endpts.com/exclusive-deepmind-ceo-demis-hassabis-talks-secretive-new-ai-biotech-isomorphic-labs/"}},"_tags":["story","author_artiver","story_37668026"],"author":"artiver","children":[37668033],"created_at":"2023-09-27T00:33:28Z","created_at_i":1695774808,"num_comments":1,"objectID":"37668026","points":3,"story_id":37668026,"title":"Deep\u00adMind\u2019s Demis Has\u00ads\u00adabis un\u00adveils his vi\u00adsion for AI\u2019s fu\u00adture in biotech","updated_at":"2024-09-20T15:15:09Z","url":"https://endpts.com/exclusive-deepmind-ceo-demis-hassabis-talks-secretive-new-ai-biotech-isomorphic-labs/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"nceqs3"},"title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["isomorphic"],"value":"Isomorphic Laboratories"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"https://www.isomorphiclabs.com/"}},"_tags":["story","author_nceqs3","story_29118188"],"author":"nceqs3","created_at":"2021-11-05T12:24:07Z","created_at_i":1636115047,"num_comments":0,"objectID":"29118188","points":2,"story_id":29118188,"title":"Isomorphic Laboratories","updated_at":"2024-09-20T09:44:56Z","url":"https://www.isomorphiclabs.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"lysozyme"},"title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["isomorphic"],"value":"Isomorphic unlocks a new frontier in AI drug design"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"https://www.isomorphiclabs.com/articles/the-isomorphic-labs-drug-design-engine-unlocks-a-new-frontier"}},"_tags":["story","author_lysozyme","story_46997316"],"author":"lysozyme","created_at":"2026-02-13T00:30:45Z","created_at_i":1770942645,"num_comments":0,"objectID":"46997316","points":1,"story_id":46997316,"title":"Isomorphic unlocks a new frontier in AI drug design","updated_at":"2026-03-05T23:35:53Z","url":"https://www.isomorphiclabs.com/articles/the-isomorphic-labs-drug-design-engine-unlocks-a-new-frontier"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"lpage"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"Hi HN\u2014we're Kelly and Steve, co-founders of OneChronos (https://www.onechronos.com). OneChronos is a "Smart Market" for US equities\u2014meaning we match counterparties using mathematical optimization instead of classical human auctioneer mechanics [1]. Our flavor of Smart Market\u2014combinatorial auctions\u2014lets users enter orders spanning multiple securities and specify matching preferences way beyond just price and quantity.
We didn't invent Smart Markets or combinatorial auctions. Roughly $1T/year flows through them in industries ranging from display advertising to telecommunications. The underlying theory was the subject of the 2020 Nobel Prize in Economic Sciences [2]. We're bringing them to capital markets, and we have both the customers and the regulatory clearance to do so. Our initial user base contains the household names cumulatively responsible for \u224870% of US equities trading volume.
Today's market structure costs institutional investors at least a trillion dollars annually. We'll go into the details below, but the big thing to understand is that mutual/pension/sovereign funds, 401K plans, and ETF managers pay the price, and ultimately it gets passed on to households. Given diverse investment time horizons and risk preferences, capital markets are not a zero-sum game, but the existing market structure makes it one. Any form of market friction that prevents mutually beneficial trades from happening is an economic loss. Our goal is to make a lot more mutually beneficial trades happen.
We started working on OneChronos as experienced traders and auction theorists. Even so, getting here has taken five years of iterating with customers, tackling two deep tech problems, and working through an involved regulatory process. We'll describe what's causing existing market friction, the solution, and why that solution is a significant technical lift.
When people hear about market friction and hidden costs, they usually think about low latency technology, market data, exchange fees, and predatory HFT practices. Those are significant, and yet they are rounding errors compared to others. The principal sources of market friction that we're attacking are bidders' inability to express economic complements (things that are worth more together than separately), substitutes (things with diminishing marginal utility that are replacements for each other) and non-price factors, and game-theoretic incentives against bidding "truthfully"\u2014that is, against specifying how many units of a good you have and the highest price at which you'd buy or the lowest at which you'd sell them (your supply and demand curve). The most commonly proposed market structure "fixes," like single good periodic batch auctions and the IEX speed bump, don't address any of these.
Imagine that a buyer values two goods A and B at $10 for the package, but only $4 for each individually since they're complements. Similarly, a seller might unload the package for $8 while demanding $5 for each good individually. Both agents have "exposure risk" if A and B are bought and sold separately\u2014they might get stuck with an incomplete package. No trade happens if the risk is high enough (buy at $4, sell at $5, no cross). But if they can trade the package atomically, there's a mutual win of $2 in gains from trade. Similar missed opportunities happen if agents only want A XOR B or have different prices for different counterparties (price discrimination). This game of imperfect information and missed opportunities plays out every day in capital markets globally.
The straightforward solution to these problems is called "Expressive Bidding"\u2014the ability to communicate parametric bids to the auctioneer, e.g., buy at most one of {$10 for A and B, $4 for A, $4 for B} or sell at most two units of A, pricing it at $10 for counterparty C_1, $9 for C_2, or $8 for C_3. Given everyone's Expressive Bid and a well-chosen objective function, the auctioneer uses constrained optimization to clear the market and unlock efficiencies. Awesome. So why didn't this happen when markets first started going electronic?
General combinatorial auctions are isomorphic to weighted set packing. Clearing them is an NP-complete optimization problem. Finding feasible and near-optimal solutions at the speed and scale of capital markets is deep tech problem #1. Furthermore, bidding in combinatorial auctions can be challenging in both a computational and UX sense. Making it easy is deep tech problem #2.
We tackle problem #1 similarly to how game AI like AlphaZero and optimizers like AlphaFold work. The combination of deep learning, heuristics, and classical AI search techniques is powerful, and applying them to combinatorial auctions in novel ways is a core part of our IP. Problem #2 involves the magic of formal methods. Expressive Bidding users submit snippets of code (a functionally pure subset of OCaml/ReasonML) called a Proxy Bidder. These proxies are essentially functions mapping "proposals" (allocations of goods) to prices, e.g., f({2A, -B}) \u2192 -5, meaning that the bidder wants $5 for buying two units of A and selling one unit of B. Using formal methods, we turn Proxy Bidders into Expressive Bids that our optimizers can understand. You can see what that looks like here [3]. This approach is dead simple for end users, but it took years of collaborative R&D with our friends and formal methods legends at Imandra [4] to enable.
Not everyone needs to write or use Expressive Bids. For common use cases, we're offering pre-canned/forkable Expressive Bids for things like pairs trades and factor neutral portfolios. That aside, users who don't use Expressive Bidding still benefit from those who use it and create unique liquidity that doesn't exist on other trading venues. Our economic mechanism prevents "dark forest" scenarios in which Expressive Bidding has adversarial uses that detract from overall match quality. "Power users" can only benefit those who treat us like a vanilla trading venue\u2014and each other.
We make money by charging a small commission in line with other venues ($0.0009) on each share traded. Longer-term, we're excited about a pricing model that balances computational resources used against liquidity contributed and compensates OneChronos based on how much value we add. Specifically, we'll measure how much notional dollar price improvement we generate for the market beyond what's generated by a "vanilla" double auction that we run in parallel (a neat trick enabled by Expressive Bidding\u2013we can run an arbitrary number of auctions with different rulesets in parallel to measure relative performance). This approach aligns our incentives with our customers and eliminates fixed costs (which cause market friction) from trading.
Only FINRA registered broker-dealers connect to OneChronos directly. If you work at one, and you're not yet a subscriber, please get in touch. We love talking to both subscribers and their customers, and we'd love to hear from institutional investors looking to leverage OneChronos through their existing broker algo and DMA workflows. Retail customers will eventually access us through brokers that choose to allow it (PFOF is its own thing). In the meantime, stay tuned for other more decentralized asset classes :) You can reach us at info (at) onechronos.com.
And we're hiring! If you're passionate about deeply technical problems ranging from mechanism design to applying ML to combinatorial optimization to writing compilers and engineering sophisticated distributed systems to HFT tolerances, get in touch \u2014 careers (at) onechronos.com.
Steve and I will be online today and would love to talk about our technical challenges, auctions/mechanism design, market structure, and the future of OneChronos.
[1] https://en.wikipedia.org/wiki/Smart_market
[2] https://news.stanford.edu/2020/11/19/bid-picture-nobel-prize... - Paul Milgrom, one of the laureates, is the Chair of OneChronos Labs, our research arm.
[3] https://www.onechronos.com/docs/expressive/bidding-guide/#in...
[4] https://www.imandra.ai/"},"title":{"matchLevel":"none","matchedWords":[],"value":"Launch HN: OneChronos (YC S16) \u2013 Combinatorial auctions market for US equities"}},"_tags":["story","author_lpage","story_30247159","launch_hn"],"author":"lpage","children":[30247296,30247364,30247696,30247919,30247936,30247994,30248135,30248706,30249030,30249058,30249229,30249230,30249360,30249642,30249947,30250057,30250120,30250219,30250260,30250312,30250330,30250964,30250987,30251215,30252407,30253453,30253586,30254530,30254532,30254883,30256171,30256842,30257145,30258292,30263078,30266480,30268479],"created_at":"2022-02-07T16:36:09Z","created_at_i":1644251769,"num_comments":118,"objectID":"30247159","points":231,"story_id":30247159,"story_text":"Hi HN\u2014we're Kelly and Steve, co-founders of OneChronos (https://www.onechronos.com). OneChronos is a "Smart Market" for US equities\u2014meaning we match counterparties using mathematical optimization instead of classical human auctioneer mechanics [1]. Our flavor of Smart Market\u2014combinatorial auctions\u2014lets users enter orders spanning multiple securities and specify matching preferences way beyond just price and quantity.
We didn't invent Smart Markets or combinatorial auctions. Roughly $1T/year flows through them in industries ranging from display advertising to telecommunications. The underlying theory was the subject of the 2020 Nobel Prize in Economic Sciences [2]. We're bringing them to capital markets, and we have both the customers and the regulatory clearance to do so. Our initial user base contains the household names cumulatively responsible for \u224870% of US equities trading volume.
Today's market structure costs institutional investors at least a trillion dollars annually. We'll go into the details below, but the big thing to understand is that mutual/pension/sovereign funds, 401K plans, and ETF managers pay the price, and ultimately it gets passed on to households. Given diverse investment time horizons and risk preferences, capital markets are not a zero-sum game, but the existing market structure makes it one. Any form of market friction that prevents mutually beneficial trades from happening is an economic loss. Our goal is to make a lot more mutually beneficial trades happen.
We started working on OneChronos as experienced traders and auction theorists. Even so, getting here has taken five years of iterating with customers, tackling two deep tech problems, and working through an involved regulatory process. We'll describe what's causing existing market friction, the solution, and why that solution is a significant technical lift.
When people hear about market friction and hidden costs, they usually think about low latency technology, market data, exchange fees, and predatory HFT practices. Those are significant, and yet they are rounding errors compared to others. The principal sources of market friction that we're attacking are bidders' inability to express economic complements (things that are worth more together than separately), substitutes (things with diminishing marginal utility that are replacements for each other) and non-price factors, and game-theoretic incentives against bidding "truthfully"\u2014that is, against specifying how many units of a good you have and the highest price at which you'd buy or the lowest at which you'd sell them (your supply and demand curve). The most commonly proposed market structure "fixes," like single good periodic batch auctions and the IEX speed bump, don't address any of these.
Imagine that a buyer values two goods A and B at $10 for the package, but only $4 for each individually since they're complements. Similarly, a seller might unload the package for $8 while demanding $5 for each good individually. Both agents have "exposure risk" if A and B are bought and sold separately\u2014they might get stuck with an incomplete package. No trade happens if the risk is high enough (buy at $4, sell at $5, no cross). But if they can trade the package atomically, there's a mutual win of $2 in gains from trade. Similar missed opportunities happen if agents only want A XOR B or have different prices for different counterparties (price discrimination). This game of imperfect information and missed opportunities plays out every day in capital markets globally.
The straightforward solution to these problems is called "Expressive Bidding"\u2014the ability to communicate parametric bids to the auctioneer, e.g., buy at most one of {$10 for A and B, $4 for A, $4 for B} or sell at most two units of A, pricing it at $10 for counterparty C_1, $9 for C_2, or $8 for C_3. Given everyone's Expressive Bid and a well-chosen objective function, the auctioneer uses constrained optimization to clear the market and unlock efficiencies. Awesome. So why didn't this happen when markets first started going electronic?
General combinatorial auctions are isomorphic to weighted set packing. Clearing them is an NP-complete optimization problem. Finding feasible and near-optimal solutions at the speed and scale of capital markets is deep tech problem #1. Furthermore, bidding in combinatorial auctions can be challenging in both a computational and UX sense. Making it easy is deep tech problem #2.
We tackle problem #1 similarly to how game AI like AlphaZero and optimizers like AlphaFold work. The combination of deep learning, heuristics, and classical AI search techniques is powerful, and applying them to combinatorial auctions in novel ways is a core part of our IP. Problem #2 involves the magic of formal methods. Expressive Bidding users submit snippets of code (a functionally pure subset of OCaml/ReasonML) called a Proxy Bidder. These proxies are essentially functions mapping "proposals" (allocations of goods) to prices, e.g., f({2A, -B}) \u2192 -5, meaning that the bidder wants $5 for buying two units of A and selling one unit of B. Using formal methods, we turn Proxy Bidders into Expressive Bids that our optimizers can understand. You can see what that looks like here [3]. This approach is dead simple for end users, but it took years of collaborative R&D with our friends and formal methods legends at Imandra [4] to enable.
Not everyone needs to write or use Expressive Bids. For common use cases, we're offering pre-canned/forkable Expressive Bids for things like pairs trades and factor neutral portfolios. That aside, users who don't use Expressive Bidding still benefit from those who use it and create unique liquidity that doesn't exist on other trading venues. Our economic mechanism prevents "dark forest" scenarios in which Expressive Bidding has adversarial uses that detract from overall match quality. "Power users" can only benefit those who treat us like a vanilla trading venue\u2014and each other.
We make money by charging a small commission in line with other venues ($0.0009) on each share traded. Longer-term, we're excited about a pricing model that balances computational resources used against liquidity contributed and compensates OneChronos based on how much value we add. Specifically, we'll measure how much notional dollar price improvement we generate for the market beyond what's generated by a "vanilla" double auction that we run in parallel (a neat trick enabled by Expressive Bidding\u2013we can run an arbitrary number of auctions with different rulesets in parallel to measure relative performance). This approach aligns our incentives with our customers and eliminates fixed costs (which cause market friction) from trading.
Only FINRA registered broker-dealers connect to OneChronos directly. If you work at one, and you're not yet a subscriber, please get in touch. We love talking to both subscribers and their customers, and we'd love to hear from institutional investors looking to leverage OneChronos through their existing broker algo and DMA workflows. Retail customers will eventually access us through brokers that choose to allow it (PFOF is its own thing). In the meantime, stay tuned for other more decentralized asset classes :) You can reach us at info (at) onechronos.com.
And we're hiring! If you're passionate about deeply technical problems ranging from mechanism design to applying ML to combinatorial optimization to writing compilers and engineering sophisticated distributed systems to HFT tolerances, get in touch \u2014 careers (at) onechronos.com.
Steve and I will be online today and would love to talk about our technical challenges, auctions/mechanism design, market structure, and the future of OneChronos.
[1] https://en.wikipedia.org/wiki/Smart_market
[2] https://news.stanford.edu/2020/11/19/bid-picture-nobel-prize... - Paul Milgrom, one of the laureates, is the Chair of OneChronos Labs, our research arm.
[3] https://www.onechronos.com/docs/expressive/bidding-guide/#in...
[4] https://www.imandra.ai/","title":"Launch HN: OneChronos (YC S16) \u2013 Combinatorial auctions market for US equities","updated_at":"2026-03-26T15:10:49Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"swimmingbrain"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"I'm a master's engineering student and a big fan of LaTeX, which I used for my thesis and research articles. I have used Overleaf and that was fine until I wanted to git sync, which unfortunately sits behind a paywall. Since I didn't want to pay subscriptions for things that should simply just work, I built the editor I wanted in my free time, where you open a tab, write LaTeX, get your PDF and the files stay all in one folder on my disk.
TeXbrain is a static site with no backend. pdfTeX is compiled to WebAssembly (SwiftLaTeX) and runs in your browser. The editor can read and write your project folder through the File System Access API, so you can use git, any local TeX install, local AI Agents, or any other editor on the same files. Git is built in through isomorphic-git for anyone who would rather not touch a terminal and clone, branch, commit, push or pull via commands. No account is needed, no analytics, and everything works offline after the first load.
Try it out: https://tex.swimmingbrain.dev/ (Chromium browsers get direct folder access, while Firefox or Safari fall back to a virtual filesystem)
Or for self-hosting/contributing: https://github.com/swimmingbrain/texbrain (MIT, the pdfTeX engine is EPL 2.0 / GPL 2.0 and is listed in the THIRD_PARTY_LICENSES file).
The part I'm most proud of getting to work is the package loading. The engine itself is only 1.8 MB. When it asks for a file it doesn't have, then a service worker intercepts the request and resolves it through Cache Storage first, then a small bundled subset, then a TeX Live tree mirrored on jsDelivr, then a SwiftLaTeX style server as a last resort. Every file is fetched once at most and after the first successful compilation, the core subset is prefetched in the background so that the offline story actually holds. Only file names go over the network, never any document content.
So far, it only supports pdfTeX (no XeTeX or LuaTeX), so fontspec or polyglossia won't work, packages are pinned to the TeX Live 2020 era to stay coherent with the engine's format file and there is no bibtex or biber in the engine yet, which is maybe the roughest edge.
This is should be a good solution for people on a work laptop, a Chromebook, or a university lab PC where installing TeX Live isn't always an option, and people who don't want to maintain a TeX install at all. If you already have a local setup you like, keep it. This isn't necessarily thought as a replacement for that.
Some people have already used it for their thesis in the past months and their bug reports (which I would never have hit on my own) were then most of the summer's work. The first outside PR also landed recently, so if something doesn't compile for you, an issue with the package name or the bug itself is the most useful thing you can send me!"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: TeXbrain, a LaTeX editor that runs pdfTeX in the browser via WASM"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/swimmingbrain/texbrain"}},"_tags":["story","author_swimmingbrain","story_49441375","show_hn"],"author":"swimmingbrain","children":[49441606,49441758,49442109,49442199,49443391,49443601,49444212,49444231,49444380,49447601,49447620,49448266,49448837,49468823,49551675],"created_at":"2026-08-25T22:08:50Z","created_at_i":1787695730,"num_comments":28,"objectID":"49441375","points":118,"story_id":49441375,"story_text":"I'm a master's engineering student and a big fan of LaTeX, which I used for my thesis and research articles. I have used Overleaf and that was fine until I wanted to git sync, which unfortunately sits behind a paywall. Since I didn't want to pay subscriptions for things that should simply just work, I built the editor I wanted in my free time, where you open a tab, write LaTeX, get your PDF and the files stay all in one folder on my disk.
TeXbrain is a static site with no backend. pdfTeX is compiled to WebAssembly (SwiftLaTeX) and runs in your browser. The editor can read and write your project folder through the File System Access API, so you can use git, any local TeX install, local AI Agents, or any other editor on the same files. Git is built in through isomorphic-git for anyone who would rather not touch a terminal and clone, branch, commit, push or pull via commands. No account is needed, no analytics, and everything works offline after the first load.
Try it out: https://tex.swimmingbrain.dev/ (Chromium browsers get direct folder access, while Firefox or Safari fall back to a virtual filesystem)
Or for self-hosting/contributing: https://github.com/swimmingbrain/texbrain (MIT, the pdfTeX engine is EPL 2.0 / GPL 2.0 and is listed in the THIRD_PARTY_LICENSES file).
The part I'm most proud of getting to work is the package loading. The engine itself is only 1.8 MB. When it asks for a file it doesn't have, then a service worker intercepts the request and resolves it through Cache Storage first, then a small bundled subset, then a TeX Live tree mirrored on jsDelivr, then a SwiftLaTeX style server as a last resort. Every file is fetched once at most and after the first successful compilation, the core subset is prefetched in the background so that the offline story actually holds. Only file names go over the network, never any document content.
So far, it only supports pdfTeX (no XeTeX or LuaTeX), so fontspec or polyglossia won't work, packages are pinned to the TeX Live 2020 era to stay coherent with the engine's format file and there is no bibtex or biber in the engine yet, which is maybe the roughest edge.
This is should be a good solution for people on a work laptop, a Chromebook, or a university lab PC where installing TeX Live isn't always an option, and people who don't want to maintain a TeX install at all. If you already have a local setup you like, keep it. This isn't necessarily thought as a replacement for that.
Some people have already used it for their thesis in the past months and their bug reports (which I would never have hit on my own) were then most of the summer's work. The first outside PR also landed recently, so if something doesn't compile for you, an issue with the package name or the bug itself is the most useful thing you can send me!","title":"Show HN: TeXbrain, a LaTeX editor that runs pdfTeX in the browser via WASM","updated_at":"2026-09-07T22:36:46Z","url":"https://github.com/swimmingbrain/texbrain"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"melonbar"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"I went to a good school, comp eng/cyber security major, started early. Got a DoD clearance, worked as a data analyst in a research lab. Ended up hooked to heroin and got involved with onion marketplaces. Long story short, felonies. I threatened someone else involved in a drug sale and went to prison. I continued my studies. A lot. Became a math tutor for those who needed it. Ended up getting a good job a few weeks out, hired on the spot. I can code and I know it. I help lead a team doing some pretty cool work on isomorphic apps. I have some potential job offers in NYC that could be quite promising. I also have multiple projects that I develop in my own time, some that even have customers. As I look toward the future, I want to be candid about this, honesty is the best policy. I also do not want to shoot myself in the foot when filling out YC apps and other grants. I am currently succeeding in the software industry. Do I still have so friggin' much to learn? Yes. But I have been sober for 5 years now, am still in my 20s and haven't looked back. I made amends to all those wronged and am doing what I love. Any sage advice going forward? Thanks!"},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: I am a founder and a felon, what next?"}},"_tags":["story","author_melonbar","story_17763171","ask_hn"],"author":"melonbar","children":[17763316,17763726,17766343,17768853,17772042],"created_at":"2018-08-15T01:17:28Z","created_at_i":1534295848,"num_comments":10,"objectID":"17763171","points":13,"story_id":17763171,"story_text":"I went to a good school, comp eng/cyber security major, started early. Got a DoD clearance, worked as a data analyst in a research lab. Ended up hooked to heroin and got involved with onion marketplaces. Long story short, felonies. I threatened someone else involved in a drug sale and went to prison. I continued my studies. A lot. Became a math tutor for those who needed it. Ended up getting a good job a few weeks out, hired on the spot. I can code and I know it. I help lead a team doing some pretty cool work on isomorphic apps. I have some potential job offers in NYC that could be quite promising. I also have multiple projects that I develop in my own time, some that even have customers. As I look toward the future, I want to be candid about this, honesty is the best policy. I also do not want to shoot myself in the foot when filling out YC apps and other grants. I am currently succeeding in the software industry. Do I still have so friggin' much to learn? Yes. But I have been sober for 5 years now, am still in my 20s and haven't looked back. I made amends to all those wronged and am doing what I love. Any sage advice going forward? Thanks!","title":"Ask HN: I am a founder and a felon, what next?","updated_at":"2024-09-20T02:55:11Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"apetresc"},"title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["labs"],"value":"L\u00e1szl\u00f3 Babai Claims Quasipolynomial Algorithm for Graph Isomorphism"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"http://aperiodical.com/2015/11/laszlo-babai-reckons-he-can-decide-if-two-graphs-are-isomorphic-in-quasipolynomial-time/"}},"_tags":["story","author_apetresc","story_10634234"],"author":"apetresc","created_at":"2015-11-26T19:02:51Z","created_at_i":1448564571,"num_comments":0,"objectID":"10634234","points":3,"story_id":10634234,"title":"L\u00e1szl\u00f3 Babai Claims Quasipolynomial Algorithm for Graph Isomorphism","updated_at":"2024-09-19T22:33:04Z","url":"http://aperiodical.com/2015/11/laszlo-babai-reckons-he-can-decide-if-two-graphs-are-isomorphic-in-quasipolynomial-time/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"goatslacker"},"story_text":{"matchLevel":"none","matchedWords":[],"value":""},"title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["isomorphic"],"value":"Show HN: A React 0.13 isomorphic flux example"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["labs"],"value":"https://github.com/goatslacker/iso/tree/iso-state-last/examples/datetime-flux"}},"_tags":["story","author_goatslacker","story_8961634","show_hn"],"author":"goatslacker","created_at":"2015-01-28T18:39:57Z","created_at_i":1422470397,"num_comments":0,"objectID":"8961634","points":2,"story_id":8961634,"story_text":"","title":"Show HN: A React 0.13 isomorphic flux example","updated_at":"2023-09-06T23:23:05Z","url":"https://github.com/goatslacker/iso/tree/iso-state-last/examples/datetime-flux"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"braden-w"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"Hey HN! Braden here. Some of you might know me from Whispering a while back (https://news.ycombinator.com/item?id=44942731).
Obsidian was one of the biggest inspirations behind the Epicenter project. I used it daily and think it's incredible software. But it's not open source, and Obsidian Sync never quite worked the way I wanted it to. I think any tool that sits this deep in your personal knowledge system should be open source and auditable.
So I built Opensidian as an open-source proof of concept: what happens when you store notes as Yjs CRDTs, sync them across servers, encrypt them end-to-end, and put a POSIX-like filesystem on top?
To do this, I built `@epicenter/filesystem`, which exposes a virtual filesystem interface on top of `@epicenter/workspace`'s CRDT tables. I then wired this into `just-bash`, a bash interpreter implemented entirely in TypeScript, which provided 80+ Unix commands (awk, sed, grep, jq, find, sqlite3, curl, etc.) to run against the same data the editor uses. Shell commands and the UI hit the same underlying CRDTs.
$ echo "# Meeting notes" > /notes/2026-04-06.md
$ mkdir /notes/archive
$ mv /notes/2026-04-06.md /notes/archive/
$ open /notes/archive/2026-04-06.md
Those commands create and move real files that immediately appear in the editor's file tree. The best part is that all of this works in both browser and server-side contexts, since yjs (https://github.com/yjs/yjs) is isomorphic.
Under the hood, metadata (name, parent, timestamps) lives in a versioned CRDT table. Document content lives in a separate Y.Doc per file, so the directory index syncs without pulling every document body. Sync uses the Yjs protocol over WebSocket, with Cloudflare Durable Objects persisting an append-only SQLite update log. Everything is encrypted end-to-end with XChaCha20-Poly1305. Keys derived via HKDF-SHA256; the sync server sees only the ciphertext.
More features: CodeMirror 6 with Yjs collaboration binding, `[[` internal links that store file IDs (renames don't break them), SQLite FTS5 search, AI chat with tool-call approval UI, and Vim mode.
Opensidian itself is a demo. For the last six months, I've been working on the infrastructure underneath: `@epicenter/workspace` (typed CRDT tables with versioning, migrations, encryption, and sync) and `@epicenter/filesystem` (a POSIX filesystem layer over Yjs). I'll be writing more about those APIs separately and integrating them into more apps in the ecosystem (including Whispering). The idea is that anyone can build local-first apps on the same foundation: notes, task managers, knowledge bases, etc., while solving the most difficult problems of local-first sync.
The UI is rough, and the feature set is thin compared to Obsidian; this isn't trying to replace it today. But I'm excited for what the future of personal computing tools could look like!
MIT licensed. Would love feedback, ideas, and roasts.
Source: https://github.com/EpicenterHQ/epicenter/tree/main/apps/open...\nDiscord: https://go.epicenter.so/discord"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Opensidian: Local-first notes in the browser with POSIX shell and sync"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://opensidian.com"}},"_tags":["story","author_braden-w","story_47676461","show_hn"],"author":"braden-w","children":[47677155],"created_at":"2026-04-07T14:59:59Z","created_at_i":1775573999,"num_comments":2,"objectID":"47676461","points":2,"story_id":47676461,"story_text":"Hey HN! Braden here. Some of you might know me from Whispering a while back (https://news.ycombinator.com/item?id=44942731).
Obsidian was one of the biggest inspirations behind the Epicenter project. I used it daily and think it's incredible software. But it's not open source, and Obsidian Sync never quite worked the way I wanted it to. I think any tool that sits this deep in your personal knowledge system should be open source and auditable.
So I built Opensidian as an open-source proof of concept: what happens when you store notes as Yjs CRDTs, sync them across servers, encrypt them end-to-end, and put a POSIX-like filesystem on top?
To do this, I built `@epicenter/filesystem`, which exposes a virtual filesystem interface on top of `@epicenter/workspace`'s CRDT tables. I then wired this into `just-bash`, a bash interpreter implemented entirely in TypeScript, which provided 80+ Unix commands (awk, sed, grep, jq, find, sqlite3, curl, etc.) to run against the same data the editor uses. Shell commands and the UI hit the same underlying CRDTs.
$ echo "# Meeting notes" > /notes/2026-04-06.md
$ mkdir /notes/archive
$ mv /notes/2026-04-06.md /notes/archive/
$ open /notes/archive/2026-04-06.md
Those commands create and move real files that immediately appear in the editor's file tree. The best part is that all of this works in both browser and server-side contexts, since yjs (https://github.com/yjs/yjs) is isomorphic.
Under the hood, metadata (name, parent, timestamps) lives in a versioned CRDT table. Document content lives in a separate Y.Doc per file, so the directory index syncs without pulling every document body. Sync uses the Yjs protocol over WebSocket, with Cloudflare Durable Objects persisting an append-only SQLite update log. Everything is encrypted end-to-end with XChaCha20-Poly1305. Keys derived via HKDF-SHA256; the sync server sees only the ciphertext.
More features: CodeMirror 6 with Yjs collaboration binding, `[[` internal links that store file IDs (renames don't break them), SQLite FTS5 search, AI chat with tool-call approval UI, and Vim mode.
Opensidian itself is a demo. For the last six months, I've been working on the infrastructure underneath: `@epicenter/workspace` (typed CRDT tables with versioning, migrations, encryption, and sync) and `@epicenter/filesystem` (a POSIX filesystem layer over Yjs). I'll be writing more about those APIs separately and integrating them into more apps in the ecosystem (including Whispering). The idea is that anyone can build local-first apps on the same foundation: notes, task managers, knowledge bases, etc., while solving the most difficult problems of local-first sync.
The UI is rough, and the feature set is thin compared to Obsidian; this isn't trying to replace it today. But I'm excited for what the future of personal computing tools could look like!
MIT licensed. Would love feedback, ideas, and roasts.
Source: https://github.com/EpicenterHQ/epicenter/tree/main/apps/open...\nDiscord: https://go.epicenter.so/discord","title":"Show HN: Opensidian: Local-first notes in the browser with POSIX shell and sync","updated_at":"2026-04-10T15:20:52Z","url":"https://opensidian.com"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bodelecta"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"I realise this is a very subjective topic but IMO node.js from a development point of view, is much faster to market for a traditional web app than a Java application.
There's been many blogs and topics over the last few years espousing why it's a more productive environment to work in. I'm sure Amazon and possibly Ebay 3 or so years ago officially blogged the benefits of using node.js for prototyping applications in the sense of agile development. I can't remember exactly but I think Amazon wrote how they were able to reduce their development resource requirements to 10% of what was needed previously by Java developers (for a particular app they wrote), using the same developers after they were retrained.
I love the fact that I can write isomorphic applications and debug them both front and back end in the same environment. For many Java/C# etc developers this loose typing and functional type programming is alien to them but IMO, developers once they understand the language semantics, should be able to cope with that easily.\nI'd like any opinions from others who've worked in the same legacy environment and moved to node.js to discuss the pro's and cons.
For me, there are a few cons. Moving to a weakly/loosely typed language. No precompilation. Functional/callback design. An ever changing world of ECMA compliance. Lack of tooling.\nI can argue all day the opposite of those cons (e.g. typescript) but one of the issues I struggle to defend is the churn rate in any libraries you depend on. \nI wholly support express.js becoming the standardised web framework API in the node.js foundation, however there's huge churn in the number of required libraries you may depend on and which inexperienced devs may add without researching their suitability or how stable they are.
NPM is great but those modules might be useless in 6 month, a year or later depending on how they're supported."},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: How to persuade a traditional Java company to use Node.js"}},"_tags":["story","author_bodelecta","story_11301355","ask_hn"],"author":"bodelecta","children":[11301544,11301614],"created_at":"2016-03-16T23:01:37Z","created_at_i":1458169297,"num_comments":2,"objectID":"11301355","points":1,"story_id":11301355,"story_text":"I realise this is a very subjective topic but IMO node.js from a development point of view, is much faster to market for a traditional web app than a Java application.
There's been many blogs and topics over the last few years espousing why it's a more productive environment to work in. I'm sure Amazon and possibly Ebay 3 or so years ago officially blogged the benefits of using node.js for prototyping applications in the sense of agile development. I can't remember exactly but I think Amazon wrote how they were able to reduce their development resource requirements to 10% of what was needed previously by Java developers (for a particular app they wrote), using the same developers after they were retrained.
I love the fact that I can write isomorphic applications and debug them both front and back end in the same environment. For many Java/C# etc developers this loose typing and functional type programming is alien to them but IMO, developers once they understand the language semantics, should be able to cope with that easily.\nI'd like any opinions from others who've worked in the same legacy environment and moved to node.js to discuss the pro's and cons.
For me, there are a few cons. Moving to a weakly/loosely typed language. No precompilation. Functional/callback design. An ever changing world of ECMA compliance. Lack of tooling.\nI can argue all day the opposite of those cons (e.g. typescript) but one of the issues I struggle to defend is the churn rate in any libraries you depend on. \nI wholly support express.js becoming the standardised web framework API in the node.js foundation, however there's huge churn in the number of required libraries you may depend on and which inexperienced devs may add without researching their suitability or how stable they are.
NPM is great but those modules might be useless in 6 month, a year or later depending on how they're supported.","title":"Ask HN: How to persuade a traditional Java company to use Node.js","updated_at":"2024-09-19T22:54:55Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"reviewpulse"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["isomorphic","labs"],"value":"We built an agentic coding tool that runs on iPad. Claude reads your codebase, plans changes, edits files, and pushes to\nGitHub \u2014 autonomously, in a loop. 7 integrated tools (Read, Write, Edit, Glob, Grep, Bash, Git), all executing locally on\nthe device.
The shell is a JS polyfill (~25 Unix commands with pipes, chaining, and redirection). Git uses isomorphic-git. API calls\nstream token-by-token via SSE.
We used it to develop itself \u2014 dogfooding from day one.
We've hit iPad platform limits: no persistent background processes, no real shell for builds/tests, iOS purges IndexedDB\nafter 7 days. Looking for collaborators to solve the last-mile problem \u2014 especially anyone with experience in iOS hybrid\napps, WebContainers, or keeping background servers alive on iOS.
Repo: https://github.com/M8seven/claude-mobile\nDetailed writeup: https://github.com/M8seven/claude-mobile/issues/1"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Claude Code for iPad \u2013 Agentic AI coding tool with file ops, Git, shell"}},"_tags":["story","author_reviewpulse","story_47272260","show_hn"],"author":"reviewpulse","created_at":"2026-03-06T08:00:47Z","created_at_i":1772784047,"num_comments":0,"objectID":"47272260","points":1,"story_id":47272260,"story_text":"We built an agentic coding tool that runs on iPad. Claude reads your codebase, plans changes, edits files, and pushes to\nGitHub \u2014 autonomously, in a loop. 7 integrated tools (Read, Write, Edit, Glob, Grep, Bash, Git), all executing locally on\nthe device.
The shell is a JS polyfill (~25 Unix commands with pipes, chaining, and redirection). Git uses isomorphic-git. API calls\nstream token-by-token via SSE.
We used it to develop itself \u2014 dogfooding from day one.
We've hit iPad platform limits: no persistent background processes, no real shell for builds/tests, iOS purges IndexedDB\nafter 7 days. Looking for collaborators to solve the last-mile problem \u2014 especially anyone with experience in iOS hybrid\napps, WebContainers, or keeping background servers alive on iOS.
Repo: https://github.com/M8seven/claude-mobile\nDetailed writeup: https://github.com/M8seven/claude-mobile/issues/1","title":"Show HN: Claude Code for iPad \u2013 Agentic AI coding tool with file ops, Git, shell","updated_at":"2026-03-06T08:05:13Z"}],"hitsPerPage":50,"nbHits":29,"nbPages":1,"page":0,"params":"query=Isomorphic+Labs&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":17,"processingTimingsMS":{"_request":{"roundTrip":16},"afterFetch":{"format":{"highlighting":2,"total":2},"merge":{"mergeLoop":{"prepareNextHit":4,"total":4},"total":5},"total":5},"fetch":{"query":7,"scanning":3,"total":11},"total":17},"query":"Isomorphic Labs","serverTimeMS":21}