15:[[49086639,{"by":"dhruvyads","descendants":3,"id":49086639,"kids":[49087529,49087068,49093385],"score":4,"text":"Hey HN! Been working on a platform that lets you build always-on background AI agents that work with your existing subscriptions/harnesses of choice (Claude Code, Codex, OpenCode, Hermes, OpenClaw).

Works in three steps:

- Choose your agent harness (CC/Codex/OpenCode/Hermes/OpenClaw) and connect your corresponding subscription

- Select the tools across 150+ integrations you want the agent to have access to

- Decide when the agent should run (recurring schedule, app event, webhook, etc)

All the infra behind the scenes (spinning up a sandbox to run the harness, connecting selected tools to it, persisting files across agent cold starts, observability for tool calls, etc) is automatically handled. Happy to answer any questions!","time":1785257296,"title":"Show HN: NoClick – Build always-on agents with your existing AI subscriptions","type":"story","url":"https://www.noclick.com/"}],[49023059,{"by":"dhruvyads","descendants":0,"id":49023059,"kids":[49023060],"score":1,"time":1784820104,"title":"Build a WhatsApp agent with Claude Code in under 5 mins [video]","type":"story","url":"https://www.youtube.com/watch?v=jLXjno0tnHI"}],[48990388,{"by":"thm","descendants":10,"id":48990388,"kids":[48990412],"score":17,"time":1784629550,"title":"Washington blocks Kalshi's sports prediction market over state gambling law","type":"story","url":"https://www.theblock.co/post/409011/washington-kalshi-preliminary-injunction"}],[48990226,{"by":"ndrh","descendants":1,"id":48990226,"kids":[48990340],"score":2,"text":"0.5M was fine in 2010. Now?","time":1784628313,"title":"Will YC ever increase its capital on offer?","type":"story"}],[48924336,{"by":"koobear","descendants":5,"id":48924336,"kids":[48924780,48924452,48924559,48924447],"score":2,"time":1784136839,"title":"What makes life worth living?","type":"story"}],[48924081,{"by":"LordDefender","descendants":1,"id":48924081,"kids":[48924474],"score":3,"time":1784135804,"title":"75% of PlayStation 3 games are now playable on PC","type":"story","url":"https://videocardz.com/newz/rpcs3-says-75-of-playstation-3-games-are-now-playable-on-pc"}],[48924259,{"by":"delduca","descendants":2,"id":48924259,"kids":[48924260,48924286],"score":3,"time":1784136521,"title":"Kbd-1.0-Codex-Micro","type":"story","url":"https://twitter.com/OpenAIDevs/status/2077425991790870644"}],[48923343,{"by":"abduhl","descendants":7,"id":48923343,"kids":[48925366,48923472,48927273,48924466,48924025],"score":39,"time":1784133041,"title":"SpaceX stock sinks below $135 IPO price for the first time","type":"story","url":"https://www.cnbc.com/2026/07/15/spacex-spcx-stock-ipo-price.html"}],[48645072,{"by":"vasko","descendants":23,"id":48645072,"kids":[48645465,48663201,48665079,48662080,48645340,48667902,48652306,48666005,48655426,48645216,48685937,48662249,48645544,48686571,48662544,48654215,48694803,48645421],"score":19,"text":"I constantly hear developers around me talk about how AI has completely changed their life and how they don't even program anymore, they just prompt. But any time I've used it, the output has always been off. And when the output is off I have to go and read through everything, learn how it works and fix it, which at that point I might as well write it myself.

I just don't understand what other people are seeing, I've mainly used Claude and ChatGPT, I got a free trial for premium but it's just underwhelming, their only use so far for me has been as a search engine, but they're a search engine that's wrong 20% of the time so even that use is questionable.","time":1782223043,"title":"Ask HN: Am I missing something with AI","type":"story"}],[48651675,{"by":"tossitawayplz","descendants":12,"id":48651675,"kids":[48654521,48656911,48653582,48651723,48662157,48665551,48680988,48656995,48668098,48654934,48655364],"score":25,"text":"Is it even possible?

I don't completely hate AI, and leverage it to make things better but I don't like to use it for EVERYTHING.

At my current job we have outsourced our thinking, our design, our documentation, our sanity to it and I just can't do it anymore.

I'm considering getting out of tech entirely at this point I've been in it for almost two decades and I've reached my tipping point dealing with the way we're using it but fear basically every company hiring software engineers is doing the same thing (or worse.)

I'm ready to just be poorer at this point.","time":1782249904,"title":"How to find AI-conservative companies to work for?","type":"story"}],[48641160,{"by":"ayi","descendants":94,"id":48641160,"kids":[48641522,48641783,48641373,48641848,48641481,48641667,48641428,48641868,48641452,48641406,48641607,48641647,48641415,48651092,48648699,48641747,48641749,48641675,48641518,48641844,48641597,48649802,48681654,48641692,48641354,48642688,48642570,48641724,48643322,48655347,48641356,48655261,48641644,48649243,48642659,48653038,48645684,48654206,48641865,48641508,48641650,48643013,48642014,48641965,48672941,48648794,48709268,48698911,48660312,48658807,48641440,48641834],"score":82,"text":"After using Claude Code at work for months I wanted to use it on my own projects too. Most probably because my vpn was on I got banned after 1 hour of usage. I got my 120$ back. 1 month later I signed up with vpn off. But this time probably because I used the same credit cart (and that's the only card I can use) they banned me again.

Even after I contacted support I got a generic "we have determined that we cannot reinstate your account at this time due to a violation of our Usage Policy" answer.

I'm not using it for anything unusal. "Summarize that markdown file", "how can i refactor payment module" kind of questions mostly. I couldn't even move to real coding because 1 hour was only enough for investigation.

My last chance is HN to get some visibility on my case. My Boris sees it or some other Anthropic employee.

Do you guys have any tips on getting my account back?","time":1782196432,"title":"Ask HN: Anthropic banned me from using Claude Code and I don't know what to do","type":"story"}],[48622123,{"by":"lkrubner","descendants":8,"id":48622123,"kids":[48624646,48623696,48624152,48622236,48622149,48625952,48724170,48622152],"score":5,"text":"I took over a project that was built by an overseas team. They set up a data ingestion process. They have a step in the ingestion where they use Libre Office (in headless mode) to convert Microsoft Word documents to PDFs. Later we convert all PDFs to Markdown. They felt that it was best to convert everything to a PDF, and then convert all of the PDFs to Markdown.

What I notice is that LibreOffice can create very complex PDFs when the Microsoft Word document has:

1. tables

2. multiple columns

3. strikethrough text

I am thinking we should go straight from Microsoft Word to Markdown.

What is the right software for that?","time":1782072255,"title":"Ask HN: How should I convert Microsoft Word documents to Markdown?","type":"story"}],[48587808,{"by":"agos","descendants":31,"id":48587808,"kids":[48670525,48590836,48601298,48662499,48592520,48642174,48595210,48594687,48593210,48656312,48618369,48594257,48596752,48594249,48606502,48593677,48592498,48620554,48590941,48618049,48602015,48592370,48618434,48653893,48619638,48649494,48626417,48619598,48605816,48599459,48594046,48602731,48602662,48645231,48595303,48595344,48590663,48594236,48608020,48625936,48590402,48597140],"score":26,"text":"My team (around 40 people who write code) is evaluating tools for AI-assisted code review. The market appears to be rife with options, so before starting a series of free trials, I’d like to ask a knowledgeable crowd.\nWhat tools or services are you using? Do you use them just for code review, or for other purposes as well, such as incident response or branch management? Why did you choose them, and what do you like or dislike about them?","time":1781799927,"title":"Ask HN: What tools are you using for AI-assisted code review?","type":"story"}],[48625785,{"by":"akashwadhwani35","descendants":4,"id":48625785,"kids":[48626180,48626058,48626112,48625866],"score":3,"text":"Bubble Sort.

Terrible in practice, but probably the first algorithm that made me understand what “sorting” actually means.

I respect it for that.","time":1782103545,"title":"Ask HN: Favorite Sorting Algorithm?","type":"story"}],[47692043,{"by":"chabons","descendants":367,"id":47692043,"kids":[47693187,47697421,47692789,47692812,47699868,47697800,47697335,47695791,47693857,47696376,47693817,47692081,47693235,47692426,47694347,47692699,47693379,47699443,47692488,47693284,47694180,47692557,47694292,47692629,47693523,47693787,47693700,47693750,47692449,47692937,47695589,47692689,47694834,47693734,47696420,47692856,47694322,47700165,47697268,47699487,47692474,47705615,47692752,47692814,47692467,47703906,47696005,47694251,47697014,47696812,47695551,47694284,47695630,47696205,47692660,47692533,47693353,47700136,47697086,47695861,47704132,47699282,47693958,47694724,47695895,47693480,47695690,47694315,47692401,47694428,47692870,47693151,47700098,47694118,47698965,47698873,47693404,47692659,47693169,47693674,47698571,47700367,47713850,47695242,47703132,47699592,47692521,47694268,47692976,47693194],"score":393,"text":"https://meta.ai/","time":1775664092,"title":"Muse Spark: Scaling towards personal superintelligence","type":"story","url":"https://ai.meta.com/blog/introducing-muse-spark-msl/?_fb_noscript=1"}]]

user:	dhruvyads
created:	March 21, 2026
karma:	5
about:	Building noclick.com

1.	Show HN: SayNow – Let your coding agents speak their questions/updates(github.com) 1 points by dhruvyads 14 days ago \| 0 comments
2.	Show HN: NoClick – Build always-on agents with your existing AI subscriptions(noclick.com) 4 points by dhruvyads 23 days ago \| 3 comments
3.	Build a WhatsApp agent with Claude Code in under 5 mins [video](youtube.com) 1 points by dhruvyads 28 days ago \| 0 comments