Keenable searches our own 100B+ page index. We are focused on low cost and latency (p95 <250ms from us-east). We don\u2019t believe in benchmaxxing, so we open-sourced our internal benchmarking suite, NEEDLE (available at https://keenableai.github.io/needle): a live benchmark that compares Keenable with other search APIs on fresh agent-like queries.
I spent seven years at Amazon as a scientist working on web grounding for Alexa/AGI, and my co-founder Andrey previously led search at Yandex. We started Keenable because agents search differently from humans, and we wanted to build around those patterns directly.
The API is available now and we provide a free allowance of 100,000 requests a month.
It also exposes a novel SQL-like interface to the web, which is useful for structured extraction and agent workflows.
Happy to answer questions about the index, crawl, ranking, latency, or benchmarking."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"Show HN: Keenable \u2013 A different web search API for AI agents"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://keenable.ai/"}},"_tags":["story","author_matt4711","story_49435555","show_hn"],"author":"matt4711","children":[49436083,49436471,49439538,49444005],"created_at":"2026-08-25T15:12:52Z","created_at_i":1787670772,"num_comments":5,"objectID":"49435555","points":12,"story_id":49435555,"story_text":"Hey HN! We built https://keenable.ai, a different web search API for AI agents.
Keenable searches our own 100B+ page index. We are focused on low cost and latency (p95 <250ms from us-east). We don\u2019t believe in benchmaxxing, so we open-sourced our internal benchmarking suite, NEEDLE (available at https://keenableai.github.io/needle): a live benchmark that compares Keenable with other search APIs on fresh agent-like queries.
I spent seven years at Amazon as a scientist working on web grounding for Alexa/AGI, and my co-founder Andrey previously led search at Yandex. We started Keenable because agents search differently from humans, and we wanted to build around those patterns directly.
The API is available now and we provide a free allowance of 100,000 requests a month.
It also exposes a novel SQL-like interface to the web, which is useful for structured extraction and agent workflows.
Happy to answer questions about the index, crawl, ranking, latency, or benchmarking.","title":"Show HN: Keenable \u2013 A different web search API for AI agents","updated_at":"2026-08-28T02:58:41Z","url":"https://keenable.ai/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mohanz"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"More and more web indexing startups: Yandex search's ex-CEO started keenable"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://techcrunch.com/2026/08/25/accel-backed-keenable-is-indexing-the-web-for-ai-agents/"}},"_tags":["story","author_mohanz","story_49437726"],"author":"mohanz","children":[49437790],"created_at":"2026-08-25T17:41:22Z","created_at_i":1787679682,"num_comments":0,"objectID":"49437726","points":2,"story_id":49437726,"title":"More and more web indexing startups: Yandex search's ex-CEO started keenable","updated_at":"2026-08-25T18:06:04Z","url":"https://techcrunch.com/2026/08/25/accel-backed-keenable-is-indexing-the-web-for-ai-agents/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"matt4711"},"title":{"matchLevel":"none","matchedWords":[],"value":"Needle: The benchmark your search engine can't memorize"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://keenable.ai/blog/needle-the-benchmark-your-search-engine-can-t-memorize"}},"_tags":["story","author_matt4711","story_49466250"],"author":"matt4711","children":[49466378,49467885,49467977,49468130,49469948,49471120,49472976],"created_at":"2026-08-27T15:17:46Z","created_at_i":1787843866,"num_comments":12,"objectID":"49466250","points":33,"story_id":49466250,"title":"Needle: The benchmark your search engine can't memorize","updated_at":"2026-09-02T14:04:31Z","url":"https://keenable.ai/blog/needle-the-benchmark-your-search-engine-can-t-memorize"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"danielmorozoff"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"Palo Alto's Keeble and Shuchat Photography to Close in October"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"http://www.paloaltoonline.com/news/2016/09/15/palo-altos-keeble--shuchat-photography-to-close-in-october"}},"_tags":["story","author_danielmorozoff","story_12737709"],"author":"danielmorozoff","children":[12737990],"created_at":"2016-10-18T19:12:43Z","created_at_i":1476817963,"num_comments":2,"objectID":"12737709","points":2,"story_id":12737709,"title":"Palo Alto's Keeble and Shuchat Photography to Close in October","updated_at":"2024-09-19T23:50:25Z","url":"http://www.paloaltoonline.com/news/2016/09/15/palo-altos-keeble--shuchat-photography-to-close-in-october"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"danielksa"},"story_text":{"matchLevel":"none","matchedWords":[],"value":""},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"Show HN:Solving Problems in a social way with Keeblee."},"url":{"matchLevel":"none","matchedWords":[],"value":"http://kee.bl.ee/"}},"_tags":["story","author_danielksa","story_6955200","show_hn"],"author":"danielksa","created_at":"2013-12-23T16:57:33Z","created_at_i":1387817853,"num_comments":0,"objectID":"6955200","points":1,"story_id":6955200,"story_text":"","title":"Show HN:Solving Problems in a social way with Keeblee.","updated_at":"2023-09-06T22:57:40Z","url":"http://kee.bl.ee/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"gyrocode"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"jQuery DataTables: How to navigate rows with KeyTable plug-in"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://www.gyrocode.com/articles/jquery-datatables-how-to-navigate-rows-with-keytable-plugin/"}},"_tags":["story","author_gyrocode","story_15642894"],"author":"gyrocode","created_at":"2017-11-07T12:49:00Z","created_at_i":1510058940,"num_comments":0,"objectID":"15642894","points":1,"story_id":15642894,"title":"jQuery DataTables: How to navigate rows with KeyTable plug-in","updated_at":"2024-09-20T01:36:19Z","url":"https://www.gyrocode.com/articles/jquery-datatables-how-to-navigate-rows-with-keytable-plugin/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"stevewilhelm"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"Keeble and Shuchat to close Palo Alto camera stores"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"http://www.mercurynews.com/2016/09/20/keeble-shuchat-to-close-palo-alto-camera-stores-2/"}},"_tags":["story","author_stevewilhelm","story_13209810"],"author":"stevewilhelm","created_at":"2016-12-19T06:26:18Z","created_at_i":1482128778,"num_comments":0,"objectID":"13209810","points":1,"story_id":13209810,"title":"Keeble and Shuchat to close Palo Alto camera stores","updated_at":"2024-09-20T00:05:01Z","url":"http://www.mercurynews.com/2016/09/20/keeble-shuchat-to-close-palo-alto-camera-stores-2/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bilifuduo"},"title":{"matchLevel":"none","matchedWords":[],"value":"Barry Diller's Search for the Future (1993)"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"http://kenauletta.com/barrydiller.html"}},"_tags":["story","author_bilifuduo","story_18995286"],"author":"bilifuduo","children":[19004862,19004879,19004952,19004961,19005276,19006585],"created_at":"2019-01-25T03:23:54Z","created_at_i":1548386634,"num_comments":10,"objectID":"18995286","points":13,"story_id":18995286,"title":"Barry Diller's Search for the Future (1993)","updated_at":"2024-09-20T03:46:09Z","url":"http://kenauletta.com/barrydiller.html"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"SpitSalute"},"title":{"matchLevel":"none","matchedWords":[],"value":"Open letter to Anthropic: keep Claude Fable 5 in existing paid plans"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://keepfable.org"}},"_tags":["story","author_SpitSalute","story_48769829"],"author":"SpitSalute","children":[48769997],"created_at":"2026-07-03T02:01:08Z","created_at_i":1783044068,"num_comments":1,"objectID":"48769829","points":4,"story_id":48769829,"title":"Open letter to Anthropic: keep Claude Fable 5 in existing paid plans","updated_at":"2026-07-03T13:50:24Z","url":"https://keepfable.org"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"terra_t"},"story_text":{"matchLevel":"none","matchedWords":[],"value":""},"title":{"matchLevel":"none","matchedWords":[],"value":"Economic Analysis Explains 1945-2010 Economic Growth and Decline Fueled By Debt"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"http://www.debtdeflation.com/blogs/wp-content/uploads/papers/KeenAreWeItYetPaperFinal.pdf"}},"_tags":["story","author_terra_t","story_1498362"],"author":"terra_t","created_at":"2010-07-08T18:50:01Z","created_at_i":1278615001,"num_comments":0,"objectID":"1498362","points":4,"story_id":1498362,"story_text":"","title":"Economic Analysis Explains 1945-2010 Economic Growth and Decline Fueled By Debt","updated_at":"2024-09-19T17:07:50Z","url":"http://www.debtdeflation.com/blogs/wp-content/uploads/papers/KeenAreWeItYetPaperFinal.pdf"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"SpitSalute"},"title":{"matchLevel":"none","matchedWords":[],"value":"Open letter to Anthropic to keep Fable on paid plans"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://keepfable.org/"}},"_tags":["story","author_SpitSalute","story_48804393"],"author":"SpitSalute","children":[48809687],"created_at":"2026-07-06T13:36:10Z","created_at_i":1783344970,"num_comments":0,"objectID":"48804393","points":2,"story_id":48804393,"title":"Open letter to Anthropic to keep Fable on paid plans","updated_at":"2026-07-06T20:00:35Z","url":"https://keepfable.org/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"todsacerdoti"},"title":{"matchLevel":"none","matchedWords":[],"value":"Current Problems in the Alerting Space"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://medium.com/keepalerting/current-problems-in-the-alerting-space-8805f8a2419d"}},"_tags":["story","author_todsacerdoti","story_35242301"],"author":"todsacerdoti","created_at":"2023-03-21T03:41:10Z","created_at_i":1679370070,"num_comments":0,"objectID":"35242301","points":2,"story_id":35242301,"title":"Current Problems in the Alerting Space","updated_at":"2024-09-20T13:37:33Z","url":"https://medium.com/keepalerting/current-problems-in-the-alerting-space-8805f8a2419d"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"keeblers_n_bits"},"title":{"matchLevel":"none","matchedWords":[],"value":"The Life in the Simpsons Is No Longer Attainable"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.theatlantic.com/article/617499/"}},"_tags":["story","author_keeblers_n_bits","story_25570438"],"author":"keeblers_n_bits","children":[25570743,25570770,25571607,25573386,25574103,25574154,25600357],"created_at":"2020-12-29T15:13:33Z","created_at_i":1609254813,"num_comments":27,"objectID":"25570438","points":61,"story_id":25570438,"title":"The Life in the Simpsons Is No Longer Attainable","updated_at":"2024-09-20T07:39:51Z","url":"https://www.theatlantic.com/article/617499/"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"KeenanKeenan"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"The social impact of a better and more affordable hearing aid would be immense. Especially since the social isolation of hearing loss takes such a devastating toll on one's social life. And it's there's interesting technical challenges that have to be solved. Mainly packing as much digital signal processing onto a very low compute environment.
As someone with hearing loss, it's sad to see promising startups like Whisper.AI leave the market. There should be dozens of hearing aid startups out there. Where are they?"},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Why aren't there more hearing aid startups?"}},"_tags":["story","author_KeenanKeenan","story_39008529","ask_hn"],"author":"KeenanKeenan","children":[39008599,39008627,39008833,39008874,39008879,39008906,39008920,39009147,39009181,39009206,39009309,39009342,39009647,39009775,39009886,39012674,39024189,39046019],"created_at":"2024-01-16T02:05:02Z","created_at_i":1705370702,"num_comments":52,"objectID":"39008529","points":58,"story_id":39008529,"story_text":"The social impact of a better and more affordable hearing aid would be immense. Especially since the social isolation of hearing loss takes such a devastating toll on one's social life. And it's there's interesting technical challenges that have to be solved. Mainly packing as much digital signal processing onto a very low compute environment.
As someone with hearing loss, it's sad to see promising startups like Whisper.AI leave the market. There should be dozens of hearing aid startups out there. Where are they?","title":"Ask HN: Why aren't there more hearing aid startups?","updated_at":"2025-05-22T21:33:18Z"},{"_highlightResult":{"author":{"fullyHighlighted":true,"matchLevel":"full","matchedWords":["keenable"],"value":"kernoble"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"What are "normal" software developer contractor rates in major metro areas in the US? \nWhat factors would make you increase or decrease your rates? What about an independent contractor, versus someone who is part of a larger consulting firm?\nWhat about other roles like product management, project management, and design?
Just to add some constraints, I feel like some experience levels are needed. (let me know if there are some levels you think I am glossing over)\n0-3 years\n3-5 years\n5-10 years\n10-15 years\n15+ years\nconsulting executive/investor (e.g. a consulting CTO or similarly senior roles)
I figured this is beneficial to more than just me, since it seems like these rates are less public then salaried rates, and many consultants/contractors are part of larger firms.
Also, is there truth to the 10% of starting salary commission for recruiters of full-time positions?"},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: What are common contractor Rates in major US metro areas?"}},"_tags":["story","author_kernoble","story_20407487","ask_hn"],"author":"kernoble","children":[20408819],"created_at":"2019-07-10T23:04:08Z","created_at_i":1562799848,"num_comments":3,"objectID":"20407487","points":12,"story_id":20407487,"story_text":"What are "normal" software developer contractor rates in major metro areas in the US? \nWhat factors would make you increase or decrease your rates? What about an independent contractor, versus someone who is part of a larger consulting firm?\nWhat about other roles like product management, project management, and design?
Just to add some constraints, I feel like some experience levels are needed. (let me know if there are some levels you think I am glossing over)\n0-3 years\n3-5 years\n5-10 years\n10-15 years\n15+ years\nconsulting executive/investor (e.g. a consulting CTO or similarly senior roles)
I figured this is beneficial to more than just me, since it seems like these rates are less public then salaried rates, and many consultants/contractors are part of larger firms.
Also, is there truth to the 10% of starting salary commission for recruiters of full-time positions?","title":"Ask HN: What are common contractor Rates in major US metro areas?","updated_at":"2024-09-20T04:32:24Z"},{"_highlightResult":{"author":{"fullyHighlighted":true,"matchLevel":"full","matchedWords":["keenable"],"value":"kernoble"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"Does anyone know what Google's current hiring outlook is? I know they slowed hiring a few months ago. So are they still reducing headcount growth? Are they only considering really exceptional or specialized candidates?
I know several people who have applied with internal referrals (included myself) and been denied with semi-automated emails. This is surprising considering some of these people have been fast -tracked in the Google interview or have gotten offers from other competitive tech companies (FB, Amazon, etc.)
This seems odd, so I was hoping someone on HN could shed some light."},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Is Google Hiring? (and other big tech companies)"}},"_tags":["story","author_kernoble","story_23877973","ask_hn"],"author":"kernoble","children":[23880306],"created_at":"2020-07-18T01:05:00Z","created_at_i":1595034300,"num_comments":2,"objectID":"23877973","points":5,"story_id":23877973,"story_text":"Does anyone know what Google's current hiring outlook is? I know they slowed hiring a few months ago. So are they still reducing headcount growth? Are they only considering really exceptional or specialized candidates?
I know several people who have applied with internal referrals (included myself) and been denied with semi-automated emails. This is surprising considering some of these people have been fast -tracked in the Google interview or have gotten offers from other competitive tech companies (FB, Amazon, etc.)
This seems odd, so I was hoping someone on HN could shed some light.","title":"Ask HN: Is Google Hiring? (and other big tech companies)","updated_at":"2024-09-20T06:39:15Z"},{"_highlightResult":{"author":{"fullyHighlighted":true,"matchLevel":"full","matchedWords":["keenable"],"value":"kernoble"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"I'm looking for something like Mint.com for my S.O. and I to monitor our spending.
I'm wary of using any free tool, because it seems that just about every "free" service/tool out there is actually profiting from the "surveillance capitalism" model/network.
Are there any tools out there that are easy to use and privacy respecting? I'm more than happy to pay or give up some features."},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Privacy Respecting Personal Finance/Budget App?"}},"_tags":["story","author_kernoble","story_19904663","ask_hn"],"author":"kernoble","children":[19905253,19905526,19905905,19908578],"created_at":"2019-05-13T22:31:16Z","created_at_i":1557786676,"num_comments":4,"objectID":"19904663","points":4,"story_id":19904663,"story_text":"I'm looking for something like Mint.com for my S.O. and I to monitor our spending.
I'm wary of using any free tool, because it seems that just about every "free" service/tool out there is actually profiting from the "surveillance capitalism" model/network.
Are there any tools out there that are easy to use and privacy respecting? I'm more than happy to pay or give up some features.","title":"Ask HN: Privacy Respecting Personal Finance/Budget App?","updated_at":"2024-09-20T04:11:55Z"},{"_highlightResult":{"author":{"fullyHighlighted":true,"matchLevel":"full","matchedWords":["keenable"],"value":"kernoble"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"Why do so few companies have procedures for leveling up more junior developers? I've noticed that quite often junior devs are very productive, but will operate in a limited scope, without much concern for the big picture, and sometimes struggle to build skills that would allow them to qualify for a more senior role.
When I was a junior dev I found this frustrating because there was an expectation to "act senior" before actually having that authority. Additionally, there was an unspoken expectation that you had to ask for it, which seems to just go against the (inaccurate) belief that so many in this field have that it's a meritocratic.
This seems especially disadvantageous for anyone who feels less comfortable in their role/standing and is less assertive for this or other reasons. I could imagine this is an even bigger problem for people who are different from the current makeup of the team/org, especially for people who are from under-represented groups.
What is your procedure for this as a manager or employee? Is there something I'm missing?"},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Why are promotion \u201cprocedures\u201d uncommon?"}},"_tags":["story","author_kernoble","story_27502064","ask_hn"],"author":"kernoble","children":[27504055],"created_at":"2021-06-14T13:09:03Z","created_at_i":1623676143,"num_comments":1,"objectID":"27502064","points":3,"story_id":27502064,"story_text":"Why do so few companies have procedures for leveling up more junior developers? I've noticed that quite often junior devs are very productive, but will operate in a limited scope, without much concern for the big picture, and sometimes struggle to build skills that would allow them to qualify for a more senior role.
When I was a junior dev I found this frustrating because there was an expectation to "act senior" before actually having that authority. Additionally, there was an unspoken expectation that you had to ask for it, which seems to just go against the (inaccurate) belief that so many in this field have that it's a meritocratic.
This seems especially disadvantageous for anyone who feels less comfortable in their role/standing and is less assertive for this or other reasons. I could imagine this is an even bigger problem for people who are different from the current makeup of the team/org, especially for people who are from under-represented groups.
What is your procedure for this as a manager or employee? Is there something I'm missing?","title":"Ask HN: Why are promotion \u201cprocedures\u201d uncommon?","updated_at":"2024-09-20T08:43:02Z"},{"_highlightResult":{"author":{"fullyHighlighted":true,"matchLevel":"full","matchedWords":["keenable"],"value":"kernoble"},"title":{"matchLevel":"none","matchedWords":[],"value":"Worst Deal Ever \u2013 ticket resale merger when viagogo bought StubHub for $4.05B"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.forbes.com/sites/noahkirsch/2020/05/27/worst-deal-ever/#6889b8bb88d1"}},"_tags":["story","author_kernoble","story_23902455"],"author":"kernoble","created_at":"2020-07-20T22:17:10Z","created_at_i":1595283430,"num_comments":0,"objectID":"23902455","points":3,"story_id":23902455,"title":"Worst Deal Ever \u2013 ticket resale merger when viagogo bought StubHub for $4.05B","updated_at":"2024-09-20T06:32:33Z","url":"https://www.forbes.com/sites/noahkirsch/2020/05/27/worst-deal-ever/#6889b8bb88d1"},{"_highlightResult":{"author":{"fullyHighlighted":true,"matchLevel":"full","matchedWords":["keenable"],"value":"keeble"},"title":{"matchLevel":"none","matchedWords":[],"value":"An Australian Hatchery Uses Automation to Count Crayfish"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://countthings.com/case-studies/0002"}},"_tags":["story","author_keeble","story_28243176"],"author":"keeble","created_at":"2021-08-20T06:11:31Z","created_at_i":1629439891,"num_comments":0,"objectID":"28243176","points":2,"story_id":28243176,"title":"An Australian Hatchery Uses Automation to Count Crayfish","updated_at":"2024-09-20T09:15:03Z","url":"https://countthings.com/case-studies/0002"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"KeenanKeenan"},"title":{"matchLevel":"none","matchedWords":[],"value":"Want This Hearing Aid? Well, Who Do You Know?"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.wired.com/story/hearing-aid-startup-ai-fortell/"}},"_tags":["story","author_KeenanKeenan","story_46278569"],"author":"KeenanKeenan","created_at":"2025-12-15T18:45:07Z","created_at_i":1765824307,"num_comments":0,"objectID":"46278569","points":1,"story_id":46278569,"title":"Want This Hearing Aid? Well, Who Do You Know?","updated_at":"2026-03-05T23:12:45Z","url":"https://www.wired.com/story/hearing-aid-startup-ai-fortell/"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"keeblers_n_bits"},"title":{"matchLevel":"none","matchedWords":[],"value":"Why Today's Solutions Don't Need Internet-Scale Complexity"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://tailscale.com/blog/10000-times-faster"}},"_tags":["story","author_keeblers_n_bits","story_44068690"],"author":"keeblers_n_bits","created_at":"2025-05-23T00:46:07Z","created_at_i":1747961167,"num_comments":0,"objectID":"44068690","points":1,"story_id":44068690,"title":"Why Today's Solutions Don't Need Internet-Scale Complexity","updated_at":"2025-05-23T00:47:01Z","url":"https://tailscale.com/blog/10000-times-faster"},{"_highlightResult":{"author":{"fullyHighlighted":true,"matchLevel":"full","matchedWords":["keenable"],"value":"kernoble"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"What labels would you use to classify time spent at work?
For example a really simple (unrealistic) labeling for someone whose only job is to write source code in one language, for one project, on a "normally" structured team. Labels = Programming, Debugging, Meeting, On-Break. \n(For the sake of the example, I'm excluding all other common tasks programmers are expected to perform)
Of course many people's jobs have a lot more scope than this example, so I'm curious how you would classify your own work.
I'm asking because I'm trying to get a better handle on how I spend my time at work by classifying chunks of time spent on different tasks. While the core of my job might be "shipping code", there are many work items and projects that might involve very little "shipable code". So when I have days that don't involve "shipping code" it can be hard to .
For context, I currently work as a "software engineer" and my team and role have a pretty wide-ranging scope from maintaining/writing APIs and Web-Apps, to creating new infrastructure. So, I'm curious how my first classification scheme (which I won't share to avoid bias) compares to other people in different roles."},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: How would you label the different tasks you perform?"}},"_tags":["story","author_kernoble","story_22357100","ask_hn"],"author":"kernoble","created_at":"2020-02-18T16:20:39Z","created_at_i":1582042839,"num_comments":0,"objectID":"22357100","points":1,"story_id":22357100,"story_text":"What labels would you use to classify time spent at work?
For example a really simple (unrealistic) labeling for someone whose only job is to write source code in one language, for one project, on a "normally" structured team. Labels = Programming, Debugging, Meeting, On-Break. \n(For the sake of the example, I'm excluding all other common tasks programmers are expected to perform)
Of course many people's jobs have a lot more scope than this example, so I'm curious how you would classify your own work.
I'm asking because I'm trying to get a better handle on how I spend my time at work by classifying chunks of time spent on different tasks. While the core of my job might be "shipping code", there are many work items and projects that might involve very little "shipable code". So when I have days that don't involve "shipping code" it can be hard to .
For context, I currently work as a "software engineer" and my team and role have a pretty wide-ranging scope from maintaining/writing APIs and Web-Apps, to creating new infrastructure. So, I'm curious how my first classification scheme (which I won't share to avoid bias) compares to other people in different roles.","title":"Ask HN: How would you label the different tasks you perform?","updated_at":"2024-09-20T05:42:25Z"},{"_highlightResult":{"author":{"fullyHighlighted":true,"matchLevel":"full","matchedWords":["keenable"],"value":"keeble"},"title":{"matchLevel":"none","matchedWords":[],"value":"WhisperMe for iOS (The famous Whisper Challenge is now on AppStore)"},"url":{"matchLevel":"none","matchedWords":[],"value":"http://whisperme.io/"}},"_tags":["story","author_keeble","story_12750307"],"author":"keeble","created_at":"2016-10-20T07:22:09Z","created_at_i":1476948129,"num_comments":0,"objectID":"12750307","points":1,"story_id":12750307,"title":"WhisperMe for iOS (The famous Whisper Challenge is now on AppStore)","updated_at":"2024-09-19T23:51:44Z","url":"http://whisperme.io/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Liriel"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"Norway considers ban on camera-enabled wearable 'pervert glasses'"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://techcrunch.com/2026/09/02/norway-considers-ban-on-camera-enabled-wearable-pervert-glasses/"}},"_tags":["story","author_Liriel","story_49536105"],"author":"Liriel","created_at":"2026-09-02T13:42:36Z","created_at_i":1788356556,"num_comments":0,"objectID":"49536105","points":15,"story_id":49536105,"title":"Norway considers ban on camera-enabled wearable 'pervert glasses'","updated_at":"2026-09-04T04:52:04Z","url":"https://techcrunch.com/2026/09/02/norway-considers-ban-on-camera-enabled-wearable-pervert-glasses/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"cromka"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"I went to https://claude.ai/code today and saw some of my most recent Claude CLI sessions appeared there. I have never explicitly enabled RC, specifically because of security concerns and the only sessions I previously had in https://claude.ai/code were the ones I actually started there out of convenience, whenever I was away from my dev machine.
So imagine my complete shock when I saw those sessions in their web client and that /rc was actually enabled in my CLI! Again, I never enabled it!!!
Notably, there was a recent bug fixed 3 days ago (https://github.com/anthropics/claude-code/releases/tag/v2.1.257) which reads:
"Fixed dismissing the Remote Control consent prompt (Esc, or n at claude remote-control) counting as consent, so the next request connected without asking"
But MY GOD, if this is what happened here to me\u2014even though I don't recall being asked that question\u2014then Anthropic NOT handling this properly by disabling RC and re-asking users to double-check their config and explicitly re-enable it is just unimaginable.
This has personally absolutely drew the line for me with them. I use Codex simultaneously and as soon as they release GPT6, I am canceling my sub. Enough is enough."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"Tell HN: Check your Claude settings, it may have silently enabled remote access"}},"_tags":["story","author_cromka","story_49565799","ask_hn"],"author":"cromka","children":[49566203,49567129,49569456],"created_at":"2026-09-04T15:09:47Z","created_at_i":1788534587,"num_comments":5,"objectID":"49565799","points":6,"story_id":49565799,"story_text":"I went to https://claude.ai/code today and saw some of my most recent Claude CLI sessions appeared there. I have never explicitly enabled RC, specifically because of security concerns and the only sessions I previously had in https://claude.ai/code were the ones I actually started there out of convenience, whenever I was away from my dev machine.
So imagine my complete shock when I saw those sessions in their web client and that /rc was actually enabled in my CLI! Again, I never enabled it!!!
Notably, there was a recent bug fixed 3 days ago (https://github.com/anthropics/claude-code/releases/tag/v2.1.257) which reads:
"Fixed dismissing the Remote Control consent prompt (Esc, or n at claude remote-control) counting as consent, so the next request connected without asking"
But MY GOD, if this is what happened here to me\u2014even though I don't recall being asked that question\u2014then Anthropic NOT handling this properly by disabling RC and re-asking users to double-check their config and explicitly re-enable it is just unimaginable.
This has personally absolutely drew the line for me with them. I use Codex simultaneously and as soon as they release GPT6, I am canceling my sub. Enough is enough.","title":"Tell HN: Check your Claude settings, it may have silently enabled remote access","updated_at":"2026-09-04T21:02:36Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Bluestein"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"Infrastructure quartermaster: inside a China-nexus state enablement model"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://www.lumen.com/blog/en-us/the-infrastructure-quartermaster-inside-a-china-nexus-state-enablement-model"}},"_tags":["story","author_Bluestein","story_49546464"],"author":"Bluestein","created_at":"2026-09-03T06:09:08Z","created_at_i":1788415748,"num_comments":0,"objectID":"49546464","points":2,"story_id":49546464,"title":"Infrastructure quartermaster: inside a China-nexus state enablement model","updated_at":"2026-09-04T19:55:38Z","url":"https://www.lumen.com/blog/en-us/the-infrastructure-quartermaster-inside-a-china-nexus-state-enablement-model"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"fionaattelnyx"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"Moonshot AI released open weights for Kimi K3 today and it's live on Telnyx Inference. The architecture and Moonshot's own benchmarks are in their technical blog. This post is about running it on Telnyx.
What we are adding: K3 is now available via the Telnyx Inference API, hosted on GPUs that we own and operate.
This matters due to the size of this model. A 2.8T model needs dedicated infra to serve well. Because we own and operate the GPUs, we can contorl throughput. with no inter-provider hops and no cloud tenant, latency is minimized.\nWe have GPUs in each of the US, EU, APAC, and MENA. Inference runs in the region you pick, with zero data retention. We do not store prompts or completions after the response returns.\nBecause we own the infra, the per-token price reflects the cost of running the model, not the cost of renting someone else's plus their margin.
We have not benchmarked K3 ourselves yet. Moonshot's own numbers and early third-party evaluations put it at frontier level for coding and agentic work, trailing only Claude Fable 5 and GPT 5.6 Sol on aggregate. Full breakdown in their blog.
Pricing on Telnyx: $2.70/1M input tokens, $13.50/1M output tokens, $0.27/1M cached input tokens. Prompt caching enabled by default. Served via an OpenAI-compatible endpoint so you can test easily.
Model ID: [MODEL_ID] API: https://api.telnyx.com/v2/ai/chat/completions Docs: https://developers.telnyx.com/docs/inference Technical blog (Moonshot): https://www.kimi.com/blog/kimi-k3"},"title":{"matchLevel":"none","matchedWords":[],"value":"Kimi K3 Now Available via Telnyx Inference API"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://telnyx.com/release-notes/kimi-k3-telnyx-inference"}},"_tags":["story","author_fionaattelnyx","story_49076505"],"author":"fionaattelnyx","children":[49076506,49076546,49076656,49078033,49078159,49078391,49078615,49078703,49079557,49080071,49080336,49080461,49080508,49080563,49080676,49080698,49080779,49082020,49082170,49082339,49082363,49082487,49082929,49105217],"created_at":"2026-07-27T22:46:28Z","created_at_i":1785192388,"num_comments":88,"objectID":"49076505","points":132,"story_id":49076505,"story_text":"Moonshot AI released open weights for Kimi K3 today and it's live on Telnyx Inference. The architecture and Moonshot's own benchmarks are in their technical blog. This post is about running it on Telnyx.
What we are adding: K3 is now available via the Telnyx Inference API, hosted on GPUs that we own and operate.
This matters due to the size of this model. A 2.8T model needs dedicated infra to serve well. Because we own and operate the GPUs, we can contorl throughput. with no inter-provider hops and no cloud tenant, latency is minimized.\nWe have GPUs in each of the US, EU, APAC, and MENA. Inference runs in the region you pick, with zero data retention. We do not store prompts or completions after the response returns.\nBecause we own the infra, the per-token price reflects the cost of running the model, not the cost of renting someone else's plus their margin.
We have not benchmarked K3 ourselves yet. Moonshot's own numbers and early third-party evaluations put it at frontier level for coding and agentic work, trailing only Claude Fable 5 and GPT 5.6 Sol on aggregate. Full breakdown in their blog.
Pricing on Telnyx: $2.70/1M input tokens, $13.50/1M output tokens, $0.27/1M cached input tokens. Prompt caching enabled by default. Served via an OpenAI-compatible endpoint so you can test easily.
Model ID: [MODEL_ID] API: https://api.telnyx.com/v2/ai/chat/completions Docs: https://developers.telnyx.com/docs/inference Technical blog (Moonshot): https://www.kimi.com/blog/kimi-k3","title":"Kimi K3 Now Available via Telnyx Inference API","updated_at":"2026-09-03T21:41:33Z","url":"https://telnyx.com/release-notes/kimi-k3-telnyx-inference"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"dariusmonsef"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"I think agent-first chat interfaces will be a primary software modality and busy dashboard/UI will go away. I\u2019m not sure who exactly wins it, but I want my knowledge to grow/go with me.
A lot of the \u201cknowledge\u201d ie research, analysis, reasoning will be done by agents as the primary user. Our current notes tools & tasks management systems were built for humans\u2026 I don\u2019t care what the 17th thing on my bug backlog is. I want to conduct agents that can execute for me and do great work.
What I built OzBrain to do:\n+ Create a central place for agent reasoned knowledge to live\n+ Be agnostic about what apps/agents connect to it\n+ Capture everything and track it so I can audit it\n+ Enable teams, collaborators or partners to share brains\n+ Handle conflicts so many agents in the same article doesn\u2019t blow up\n+ Refactor knowledge into more token friendly chunks and map the index well\n+ Close the knowledge loop so new thinking supersedes old thinking across the corpus. Don\u2019t erase, depreciate and link\n+ Keep user data safe and secure\n++ Be easy enough to use that you don\u2019t have to have any technical knowledge
Some among us will always build their own custom solutions, but there are millions of tech professionals and small business owners that will use agents heavily and need a solution. So I\u2019m trying to build that.
Isn\u2019t this like gBrain? Yes, similar. I think it\u2019s like AWS vs Vercel. AWS is very powerful, configurable, and useful if you\u2019re technical and want to invest the time into really fine tuning your system\u2026 but if you just want your web deploy/hosting to just work and be easy to deal with you use Vercel.
// WHY I MADE IT
I\u2019ve been enjoying getting back to my technical roots, as I lost my coding skills more than a decade ago, but with AI I can focus on the system and the product in partnership with agent coding workflows.
I recently built a Voice AI for older people. To build it I created an agentic engineering workflow (feel free to rip that up as I\u2019m always looking to improve systems: https://ozbrain.com/resources/eng-flow) My approach with coding agents is trust but verify, and I\u2019m trying to replace the parts where a human would review with an adversarial or specialized agent who would give a better answer/review.
I have workflows that will go high level task to shipped PR running in Claude cloud sessions. I use Claude Code locally and Cursor when I want a tighter loop on doing visual work like UI or layout. And Codex to either load balance usage for TokenThriffting or when I want a different llm to think thru something.
It was a pain in the ass passing .md files around and keep track of which version was the most recent, so I built a hosted .md storage right in Supabase and any of my agents already have Supabase access. This let me build a solid, scalable, secure voice AI from my phone at the gym. All my agents have access to our knowledge, can write to it, update and refer to it as we build and improve the product and the systems we use.
Out of 75 founder friends I asked about how they manage shared knowledge, 26 built their own custom knowledge systems\u2026 Obsidian vaults with 7k files synced through a VPS, markdown repos behind their own MCP servers, cron jobs stitching Supabase to a skills file\u2026 each a different Frankenstein they have to maintain. 32 said they felt the pain of moving static files around but didn\u2019t have any solution for it.
So I rebuilt my brain better and used it to build it.
// HOW YOU CAN HELP
Would love to have you try it out. The maintenance loop is still in alpha so not running it on customer data yet.
If you built your own brain I\u2019d love to hear how you did it. What criteria was most important for you in its design & function.
If you are tired of shuffling .md files around I\u2019d love to have you try out OzBrain and to give feedback, just ask your agent to put it in the shared bugs & features brain!
Cheers!\nBubs.co"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: OzBrain, a shared brain for knowledge between agents and your team"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://ozbrain.com"}},"_tags":["story","author_dariusmonsef","story_49394827","show_hn"],"author":"dariusmonsef","children":[49394952,49395220,49395240,49395359,49395706,49395739,49395778,49395910,49395966,49396028,49396207,49396347,49396370,49396430,49396627,49396746,49396766,49396788,49396873,49396898,49397071,49397451,49397453,49397565,49397747,49398021,49398400,49399271,49400833,49405658,49406323,49408070,49413054,49415238,49429905,49432522,49436555,49457636,49504400,49507731],"created_at":"2026-08-21T23:09:06Z","created_at_i":1787353746,"num_comments":59,"objectID":"49394827","points":93,"story_id":49394827,"story_text":"I think agent-first chat interfaces will be a primary software modality and busy dashboard/UI will go away. I\u2019m not sure who exactly wins it, but I want my knowledge to grow/go with me.
A lot of the \u201cknowledge\u201d ie research, analysis, reasoning will be done by agents as the primary user. Our current notes tools & tasks management systems were built for humans\u2026 I don\u2019t care what the 17th thing on my bug backlog is. I want to conduct agents that can execute for me and do great work.
What I built OzBrain to do:\n+ Create a central place for agent reasoned knowledge to live\n+ Be agnostic about what apps/agents connect to it\n+ Capture everything and track it so I can audit it\n+ Enable teams, collaborators or partners to share brains\n+ Handle conflicts so many agents in the same article doesn\u2019t blow up\n+ Refactor knowledge into more token friendly chunks and map the index well\n+ Close the knowledge loop so new thinking supersedes old thinking across the corpus. Don\u2019t erase, depreciate and link\n+ Keep user data safe and secure\n++ Be easy enough to use that you don\u2019t have to have any technical knowledge
Some among us will always build their own custom solutions, but there are millions of tech professionals and small business owners that will use agents heavily and need a solution. So I\u2019m trying to build that.
Isn\u2019t this like gBrain? Yes, similar. I think it\u2019s like AWS vs Vercel. AWS is very powerful, configurable, and useful if you\u2019re technical and want to invest the time into really fine tuning your system\u2026 but if you just want your web deploy/hosting to just work and be easy to deal with you use Vercel.
// WHY I MADE IT
I\u2019ve been enjoying getting back to my technical roots, as I lost my coding skills more than a decade ago, but with AI I can focus on the system and the product in partnership with agent coding workflows.
I recently built a Voice AI for older people. To build it I created an agentic engineering workflow (feel free to rip that up as I\u2019m always looking to improve systems: https://ozbrain.com/resources/eng-flow) My approach with coding agents is trust but verify, and I\u2019m trying to replace the parts where a human would review with an adversarial or specialized agent who would give a better answer/review.
I have workflows that will go high level task to shipped PR running in Claude cloud sessions. I use Claude Code locally and Cursor when I want a tighter loop on doing visual work like UI or layout. And Codex to either load balance usage for TokenThriffting or when I want a different llm to think thru something.
It was a pain in the ass passing .md files around and keep track of which version was the most recent, so I built a hosted .md storage right in Supabase and any of my agents already have Supabase access. This let me build a solid, scalable, secure voice AI from my phone at the gym. All my agents have access to our knowledge, can write to it, update and refer to it as we build and improve the product and the systems we use.
Out of 75 founder friends I asked about how they manage shared knowledge, 26 built their own custom knowledge systems\u2026 Obsidian vaults with 7k files synced through a VPS, markdown repos behind their own MCP servers, cron jobs stitching Supabase to a skills file\u2026 each a different Frankenstein they have to maintain. 32 said they felt the pain of moving static files around but didn\u2019t have any solution for it.
So I rebuilt my brain better and used it to build it.
// HOW YOU CAN HELP
Would love to have you try it out. The maintenance loop is still in alpha so not running it on customer data yet.
If you built your own brain I\u2019d love to hear how you did it. What criteria was most important for you in its design & function.
If you are tired of shuffling .md files around I\u2019d love to have you try out OzBrain and to give feedback, just ask your agent to put it in the shared bugs & features brain!
Cheers!\nBubs.co","title":"Show HN: OzBrain, a shared brain for knowledge between agents and your team","updated_at":"2026-09-04T12:01:50Z","url":"https://ozbrain.com"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"kushagrchitkar"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"Hi HN, I'm Kushagra, one of three founders of Almanac, a Hermes with a brain that knows everything about your company.
We started our journey with setting up Hermes for our company, thinking it must be easy. We wanted an agent that would know every context about our company, so we could ask questions and get context-appropriate responses to.
This started a very annoying and difficult journey. Setting up Hermes, getting it to talk right, building OAuth apps for every connector myself, then feeding it context myself, and ultimately struggling with Hermes's default memory. At the same time, we saw our YC batchmates struggling with the same problem, and we saw an opportunity.
So we built Almanac. This is how it works. You sign up, you get a Hermes agent straight out of the box. You have a one-click connect to any account (Gmail, Calendar, Granola, PostHog, etc). You have personal accounts (only accessible by you) and also shared accounts (accessible by everyone in the company). The consequence being I can never see my cofounders' accounts.
The \u201cbrain\u201d of this agent is wikis. We pull in information from your connected sources, and start organizing this information in two wikis. A personal one, for you, which understands who you are, what your preferences are, the people in your life, and the things going on in your life. The second wiki is a company wiki, which includes what the company is, what you\u2019re working on, what the roadmap is, and what the blockers of the company are. Your agent ultimately has access to these two wikis and the original accounts, which invoke the feeling of \u201cit just knows you.\u201d
Here\u2019s a demo: https://www.youtube.com/watch?v=ajXP5PHuK18
We're three cofounders, Rohan, Kushagra, and Divit, and we've been friends for 11 years, since studying for the IIT-JEE. We all did Electrical Engineering (Rohan at IIT Delhi, me at IIT Kharagpur, Divit at BITS Pilani, Hyderabad), and Rohan and I later went to Harvard, where this pre-compilation layer became our capstone thesis. We have built multiple products around the idea of a pre-compiled knowledge layer.
Our main differentiating point is the way we approach memory and context in general. Most AI assistant tools treat memory as an afterthought. We have worked on wikis for AI for more than a year now, building products for Harvard and NASA. The one thing we have learnt is that one needs to spend a lot more compute upfront, in the pre-compilation of this knowledge base, to get it right.
Having this pre-compiled knowledge base enables a lot of interesting ideas. First is a proactive agent. Since I have compiled what\u2019s going on in both my company and my current life, Almanac can start completing tasks on its own. Concretely, we run a background worker which takes a look at tasks that could be completed, pings the main agent, who then pings me, suggesting which tasks it could automate. As a result, I wake up to proactive notifications which look like \u201cI already prepared a draft of your fundraising pitch deck, want to take a look?\u201d
Second, long-horizon tasks. In our wikis, we maintain a section on ongoing projects, so Almanac can pick a task back up days later without losing the thread. Most agents are session-bound: they run once, finish, and forget. But a lot of real work isn't one shot; it plays out over hours and days with people in the loop. The clearest example is anything that involves waiting on a human, like scheduling a meeting, following up on a sales thread, or chasing a document. Almanac can send an email on your behalf, and because it's always on and remembers the project, it notices the reply four hours later and drafts the right follow-up in context.
Since launching, we've seen a lot of use cases for Almanac. One person runs her dog-rescue operation through it: finding available fosters, tracking pickups, and sending reminders for consent forms. Another researches Polymarket strategies with Almanac, where its memory holds what past strategies were, proposes new ones, and compares them against what went right or wrong last time. Another builds marketing campaigns on it without having to re-explain the business and the whole campaign every single time.
Regarding privacy and security, Almanac only accesses accounts you explicitly connect. Your OAuth credentials are held by our connection provider, not in Almanac\u2019s database. We only store the wiki and the source behind its citations. So an email used as a citation may be retained as Markdown.
We\u2019re live: https://usealmanac.com. We have a 7-day trial on all of our plans. Happy to hear if people have done similar setups, and what new features they\u2019d like in Almanac. If you\u2019re a company that wants to get an agent that actually gets tasks done, I would love to talk: https://cal.com/team/almanac/demo."},"title":{"matchLevel":"none","matchedWords":[],"value":"Launch HN: Almanac (YC S26) \u2013 AI that knows your company"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://usealmanac.com/"}},"_tags":["story","author_kushagrchitkar","story_49511007","launch_hn"],"author":"kushagrchitkar","children":[49511187,49511338,49511514,49511620,49512006,49512087,49512227,49512252,49512409,49512486,49512502,49512524,49512647,49512818,49513333,49513612,49514426,49515296,49515650,49516742,49517411,49519017,49519569],"created_at":"2026-08-31T15:34:34Z","created_at_i":1788190474,"num_comments":49,"objectID":"49511007","points":59,"story_id":49511007,"story_text":"Hi HN, I'm Kushagra, one of three founders of Almanac, a Hermes with a brain that knows everything about your company.
We started our journey with setting up Hermes for our company, thinking it must be easy. We wanted an agent that would know every context about our company, so we could ask questions and get context-appropriate responses to.
This started a very annoying and difficult journey. Setting up Hermes, getting it to talk right, building OAuth apps for every connector myself, then feeding it context myself, and ultimately struggling with Hermes's default memory. At the same time, we saw our YC batchmates struggling with the same problem, and we saw an opportunity.
So we built Almanac. This is how it works. You sign up, you get a Hermes agent straight out of the box. You have a one-click connect to any account (Gmail, Calendar, Granola, PostHog, etc). You have personal accounts (only accessible by you) and also shared accounts (accessible by everyone in the company). The consequence being I can never see my cofounders' accounts.
The \u201cbrain\u201d of this agent is wikis. We pull in information from your connected sources, and start organizing this information in two wikis. A personal one, for you, which understands who you are, what your preferences are, the people in your life, and the things going on in your life. The second wiki is a company wiki, which includes what the company is, what you\u2019re working on, what the roadmap is, and what the blockers of the company are. Your agent ultimately has access to these two wikis and the original accounts, which invoke the feeling of \u201cit just knows you.\u201d
Here\u2019s a demo: https://www.youtube.com/watch?v=ajXP5PHuK18
We're three cofounders, Rohan, Kushagra, and Divit, and we've been friends for 11 years, since studying for the IIT-JEE. We all did Electrical Engineering (Rohan at IIT Delhi, me at IIT Kharagpur, Divit at BITS Pilani, Hyderabad), and Rohan and I later went to Harvard, where this pre-compilation layer became our capstone thesis. We have built multiple products around the idea of a pre-compiled knowledge layer.
Our main differentiating point is the way we approach memory and context in general. Most AI assistant tools treat memory as an afterthought. We have worked on wikis for AI for more than a year now, building products for Harvard and NASA. The one thing we have learnt is that one needs to spend a lot more compute upfront, in the pre-compilation of this knowledge base, to get it right.
Having this pre-compiled knowledge base enables a lot of interesting ideas. First is a proactive agent. Since I have compiled what\u2019s going on in both my company and my current life, Almanac can start completing tasks on its own. Concretely, we run a background worker which takes a look at tasks that could be completed, pings the main agent, who then pings me, suggesting which tasks it could automate. As a result, I wake up to proactive notifications which look like \u201cI already prepared a draft of your fundraising pitch deck, want to take a look?\u201d
Second, long-horizon tasks. In our wikis, we maintain a section on ongoing projects, so Almanac can pick a task back up days later without losing the thread. Most agents are session-bound: they run once, finish, and forget. But a lot of real work isn't one shot; it plays out over hours and days with people in the loop. The clearest example is anything that involves waiting on a human, like scheduling a meeting, following up on a sales thread, or chasing a document. Almanac can send an email on your behalf, and because it's always on and remembers the project, it notices the reply four hours later and drafts the right follow-up in context.
Since launching, we've seen a lot of use cases for Almanac. One person runs her dog-rescue operation through it: finding available fosters, tracking pickups, and sending reminders for consent forms. Another researches Polymarket strategies with Almanac, where its memory holds what past strategies were, proposes new ones, and compares them against what went right or wrong last time. Another builds marketing campaigns on it without having to re-explain the business and the whole campaign every single time.
Regarding privacy and security, Almanac only accesses accounts you explicitly connect. Your OAuth credentials are held by our connection provider, not in Almanac\u2019s database. We only store the wiki and the source behind its citations. So an email used as a citation may be retained as Markdown.
We\u2019re live: https://usealmanac.com. We have a 7-day trial on all of our plans. Happy to hear if people have done similar setups, and what new features they\u2019d like in Almanac. If you\u2019re a company that wants to get an agent that actually gets tasks done, I would love to talk: https://cal.com/team/almanac/demo.","title":"Launch HN: Almanac (YC S26) \u2013 AI that knows your company","updated_at":"2026-09-04T17:44:35Z","url":"https://usealmanac.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"neversaydie"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"https://www.bbc.com/news/articles/c36d4376nd2o, https://archive.is/YDn6S"},"title":{"matchLevel":"none","matchedWords":[],"value":"Scientists discover Kelvin-Helmholtz Instability on the surface of the Sun"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["keenable"],"value":"https://nso.edu/press-release/nsf-inouye-solar-telescope-enables-major-discovery-of-a-hidden-solar-process/"}},"_tags":["story","author_neversaydie","story_49184355"],"author":"neversaydie","children":[49188156,49188922,49190343,49190377,49191022,49197915,49203206,49204144,49204190,49205213,49206095,49208572,49211808,49212310,49214379,49216476,49220395],"created_at":"2026-08-05T15:33:23Z","created_at_i":1785944003,"num_comments":65,"objectID":"49184355","points":306,"story_id":49184355,"story_text":"https://www.bbc.com/news/articles/c36d4376nd2o, https://archive.is/YDn6S","title":"Scientists discover Kelvin-Helmholtz Instability on the surface of the Sun","updated_at":"2026-09-04T19:03:36Z","url":"https://nso.edu/press-release/nsf-inouye-solar-telescope-enables-major-discovery-of-a-hidden-solar-process/"}],"hitsPerPage":50,"nbHits":32,"nbPages":1,"page":0,"params":"query=Keenable&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":9,"processingTimingsMS":{"_request":{"queue":112,"roundTrip":20},"afterFetch":{"format":{"highlighting":1,"total":1},"merge":{"mergeLoop":{"prepareNextHit":1,"total":1},"total":1},"total":1},"fetch":{"query":6,"total":7},"total":9},"query":"Keenable","serverTimeMS":124}