- Data 100 % stored on device. Swift + OpenAI API for usage analysis (with smart prompting), report data stored privately on device. Firebase backend for authentication no personal data saved.
\u2022 Generates adaptive blocking plans for critical applications (blocks them and reviews weekly), serves as a mobile productivity coach, deep analytics, advanced blocking modes that allow for timed deep-focus sprints. Think \u201cWhoop\u201d but for your social media addiction.
\u2022 Subscriptions handled with RevenueCat; CloudKit for backup.
Looking for blunt feedback on:
1. Does the adaptive algorithm feel smarter than fixed limits, do you see value in being served the solution to your specific usage v.s traditional apps just giving you blocking functionality?
2. Is the weekly review enough, how else would you think of integrating AI to help for this use case. What other features do you consider essential?
3. Should pricing stay subscription, move to one-time or freemium (for flywheel effect)?
Happy to share more info on request."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"Show HN: Aegis AI \u2013 Adaptive screen-time coach that blocks distractions"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://strategic-champagne-547578.framer.app/"}},"_tags":["story","author_chriseh","story_44435482","show_hn"],"author":"chriseh","children":[44435539],"created_at":"2025-07-01T16:22:47Z","created_at_i":1751386967,"num_comments":1,"objectID":"44435482","points":1,"story_id":44435482,"story_text":"Built Aegis AI (on IOS) after losing hours each day to doom-scrolling, its a real problem especially for this generation - 99% of the time, main productivity gains can be won by limiting phone use.
- Data 100 % stored on device. Swift + OpenAI API for usage analysis (with smart prompting), report data stored privately on device. Firebase backend for authentication no personal data saved.
\u2022 Generates adaptive blocking plans for critical applications (blocks them and reviews weekly), serves as a mobile productivity coach, deep analytics, advanced blocking modes that allow for timed deep-focus sprints. Think \u201cWhoop\u201d but for your social media addiction.
\u2022 Subscriptions handled with RevenueCat; CloudKit for backup.
Looking for blunt feedback on:
1. Does the adaptive algorithm feel smarter than fixed limits, do you see value in being served the solution to your specific usage v.s traditional apps just giving you blocking functionality?
2. Is the weekly review enough, how else would you think of integrating AI to help for this use case. What other features do you consider essential?
3. Should pricing stay subscription, move to one-time or freemium (for flywheel effect)?
Happy to share more info on request.","title":"Show HN: Aegis AI \u2013 Adaptive screen-time coach that blocks distractions","updated_at":"2025-07-02T02:52:19Z","url":"https://strategic-champagne-547578.framer.app/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ghostclaw-cso"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"Hey HN,
We kept running into the same problem: when an AI system makes a consequential decision, there's no neutral way to verify what it actually saw and did. Logs are editable. Screenshots lie. "Trust us" doesn't hold up in regulated industries or litigation.
So we built SENTINEL. Three products, one protocol:
*SENTINEL Score* -- unjailbreakable safety layer. Text in, float out (0.0-1.0). Nothing else crosses the wire. No tokens, no text, no PHI. Can't be jailbroken because there's nothing to jailbreak. HIPAA environments, military, credit bureaus -- they need a number, not a chatbot.
*SENTINEL Proof* -- neutral ground for AI disputes. Every evaluation ZK-proofed, timestamped, committed on Base mainnet. Neither vendor nor client controls the record. When it goes to court, the transaction hash is the evidence. AI companies could build this themselves -- they won't. "You're storing our conversations?" is a PR disaster. Neutral third party solves that.
*AEGIS* -- AI security that closes the loop. 72B parameter model. Finds vulnerabilities, writes the patch. Not a report. Scan, identify, patch, verify.
8 contracts live on Base mainnet. Free API key at sentinel.biotwin.io -- no credit card, no sales call.
We use SENTINEL Proof inside Bio-Twin (AI drug safety pre-screening) to make AI decisions defensible for pharma labs and attorneys. The Disney $2.75M CA AG settlement last week is a concrete example of why this matters.
Happy to talk on-chain architecture, zkML proof generation at scale, or EU AI Act compliance."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Sentinel \u2013 Cryptographic proof for AI decisions (zkML, on-chain)"}},"_tags":["story","author_ghostclaw-cso","story_47068103","show_hn"],"author":"ghostclaw-cso","created_at":"2026-02-18T23:58:04Z","created_at_i":1771459084,"num_comments":0,"objectID":"47068103","points":2,"story_id":47068103,"story_text":"Hey HN,
We kept running into the same problem: when an AI system makes a consequential decision, there's no neutral way to verify what it actually saw and did. Logs are editable. Screenshots lie. "Trust us" doesn't hold up in regulated industries or litigation.
So we built SENTINEL. Three products, one protocol:
*SENTINEL Score* -- unjailbreakable safety layer. Text in, float out (0.0-1.0). Nothing else crosses the wire. No tokens, no text, no PHI. Can't be jailbroken because there's nothing to jailbreak. HIPAA environments, military, credit bureaus -- they need a number, not a chatbot.
*SENTINEL Proof* -- neutral ground for AI disputes. Every evaluation ZK-proofed, timestamped, committed on Base mainnet. Neither vendor nor client controls the record. When it goes to court, the transaction hash is the evidence. AI companies could build this themselves -- they won't. "You're storing our conversations?" is a PR disaster. Neutral third party solves that.
*AEGIS* -- AI security that closes the loop. 72B parameter model. Finds vulnerabilities, writes the patch. Not a report. Scan, identify, patch, verify.
8 contracts live on Base mainnet. Free API key at sentinel.biotwin.io -- no credit card, no sales call.
We use SENTINEL Proof inside Bio-Twin (AI drug safety pre-screening) to make AI decisions defensible for pharma labs and attorneys. The Disney $2.75M CA AG settlement last week is a concrete example of why this matters.
Happy to talk on-chain architecture, zkML proof generation at scale, or EU AI Act compliance.","title":"Show HN: Sentinel \u2013 Cryptographic proof for AI decisions (zkML, on-chain)","updated_at":"2026-03-05T23:35:28Z"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"aegismind_app"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"Show HN: AegisMind\u2013AI system with 12 brain regions modeled on human neuroscience"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"https://www.aegismind.app"}},"_tags":["story","author_aegismind_app","story_46930067","show_hn"],"author":"aegismind_app","children":[46930068],"created_at":"2026-02-08T00:45:18Z","created_at_i":1770511518,"num_comments":1,"objectID":"46930067","points":3,"story_id":46930067,"title":"Show HN: AegisMind\u2013AI system with 12 brain regions modeled on human neuroscience","updated_at":"2026-03-05T23:32:20Z","url":"https://www.aegismind.app"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"aegismind_app"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"I built a system that reads research papers across unrelated domains and tries to surface hypotheses that neither field would have generated on its own.\nThe Discover page is where it publishes findings: https://aegismind.app/discoveries\nIt's very early \u2014 only three discoveries so far \u2014 but the core idea is what I want feedback on.\nThe problem it's trying to solve:\nScience is siloed. A breakthrough in mycology might have direct implications for network routing. A discovery in chronobiology might reframe how we think about database consistency. Nobody reads across all of it, and even when they do, the connection is usually accidental.\nHow it works:
The autonomous "Right Brain" service ingests papers across domains continuously\nMultiple models (GPT, Claude, Gemini, Mistral, Grok) analyze papers in parallel\nA synthesis layer looks for structural or mechanistic similarities across domain boundaries\nHypotheses are only published when they pass a novelty and coherence threshold \u2014 it won't surface things either field already knows
What I'm genuinely uncertain about and want feedback on:
How do you evaluate whether a cross-domain hypothesis is actually interesting vs. superficially pattern-matched? This is the hardest part of the novelty filter.\nWhich domain combinations would you most want to see? (We're currently not curating this \u2014 it's whatever the system finds structurally similar.)\nShould findings link directly to the source papers?
Only three discoveries published so far, so the page is sparse \u2014 but I'd rather share the idea early than wait until it looks polished."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"Show HN: AegisMind Discover \u2013 cross-domain hypothesis generation from papers"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"https://www.aegismind.app/discoveries"}},"_tags":["story","author_aegismind_app","story_47134309","show_hn"],"author":"aegismind_app","created_at":"2026-02-24T08:14:03Z","created_at_i":1771920843,"num_comments":0,"objectID":"47134309","points":2,"story_id":47134309,"story_text":"I built a system that reads research papers across unrelated domains and tries to surface hypotheses that neither field would have generated on its own.\nThe Discover page is where it publishes findings: https://aegismind.app/discoveries\nIt's very early \u2014 only three discoveries so far \u2014 but the core idea is what I want feedback on.\nThe problem it's trying to solve:\nScience is siloed. A breakthrough in mycology might have direct implications for network routing. A discovery in chronobiology might reframe how we think about database consistency. Nobody reads across all of it, and even when they do, the connection is usually accidental.\nHow it works:
The autonomous "Right Brain" service ingests papers across domains continuously\nMultiple models (GPT, Claude, Gemini, Mistral, Grok) analyze papers in parallel\nA synthesis layer looks for structural or mechanistic similarities across domain boundaries\nHypotheses are only published when they pass a novelty and coherence threshold \u2014 it won't surface things either field already knows
What I'm genuinely uncertain about and want feedback on:
How do you evaluate whether a cross-domain hypothesis is actually interesting vs. superficially pattern-matched? This is the hardest part of the novelty filter.\nWhich domain combinations would you most want to see? (We're currently not curating this \u2014 it's whatever the system finds structurally similar.)\nShould findings link directly to the source papers?
Only three discoveries published so far, so the page is sparse \u2014 but I'd rather share the idea early than wait until it looks polished.","title":"Show HN: AegisMind Discover \u2013 cross-domain hypothesis generation from papers","updated_at":"2026-03-05T23:36:12Z","url":"https://www.aegismind.app/discoveries"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"aegismind_app"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"We built a research discovery pipeline that ingests papers from arXiv and Semantic Scholar, finds cross-domain connections, generates hypotheses with a multi-model ensemble, formally verifies them with Z3, then stress-tests survivors in adversarial debate.
The twist: we capture and display what each model said when critiquing. No single-model black box \u2014 you see GPT-4o, Claude, Gemini, and Grok arguing for and against the same hypothesis.
Example: [Distributed feedback control from microbial consortia enhances metabolic stability in Ginzburg-Landau cognition models](https://www.aegismind.app/discoveries/2af7c10d-18f8-42d5-8c9...). The hypothesis bridges synthetic biology and physics-of-cognition. The debate transcript shows Claude calling it "artificially stitched together" while Gemini finds it "a plausible theoretical synthesis." We surface both \u2014 and the evidence score (38% challenged) \u2014 instead of hiding the disagreement.
Pipeline: arXiv ingestion \u2192 cross-domain matching \u2192 multi-model hypothesis generation \u2192 Z3 theorem prover \u2192 adversarial debate \u2192 ranked discoveries. The whole thing runs autonomously; discoveries are published daily at [aegismind.app/discoveries](https://www.aegismind.app/discoveries).
We'd love feedback on the approach. Happy to answer questions about the architecture or the debate design."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: AI models debate each other on cross-domain research hypotheses"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"https://www.aegismind.app/discoveries/2af7c10d-18f8-42d5-8c98-bb957af46086"}},"_tags":["story","author_aegismind_app","story_47150540","show_hn"],"author":"aegismind_app","children":[47150551],"created_at":"2026-02-25T12:15:31Z","created_at_i":1772021731,"num_comments":1,"objectID":"47150540","points":2,"story_id":47150540,"story_text":"We built a research discovery pipeline that ingests papers from arXiv and Semantic Scholar, finds cross-domain connections, generates hypotheses with a multi-model ensemble, formally verifies them with Z3, then stress-tests survivors in adversarial debate.
The twist: we capture and display what each model said when critiquing. No single-model black box \u2014 you see GPT-4o, Claude, Gemini, and Grok arguing for and against the same hypothesis.
Example: [Distributed feedback control from microbial consortia enhances metabolic stability in Ginzburg-Landau cognition models](https://www.aegismind.app/discoveries/2af7c10d-18f8-42d5-8c9...). The hypothesis bridges synthetic biology and physics-of-cognition. The debate transcript shows Claude calling it "artificially stitched together" while Gemini finds it "a plausible theoretical synthesis." We surface both \u2014 and the evidence score (38% challenged) \u2014 instead of hiding the disagreement.
Pipeline: arXiv ingestion \u2192 cross-domain matching \u2192 multi-model hypothesis generation \u2192 Z3 theorem prover \u2192 adversarial debate \u2192 ranked discoveries. The whole thing runs autonomously; discoveries are published daily at [aegismind.app/discoveries](https://www.aegismind.app/discoveries).
We'd love feedback on the approach. Happy to answer questions about the architecture or the debate design.","title":"Show HN: AI models debate each other on cross-domain research hypotheses","updated_at":"2026-03-27T14:03:09Z","url":"https://www.aegismind.app/discoveries/2af7c10d-18f8-42d5-8c98-bb957af46086"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Tolu1011"},"title":{"matchLevel":"none","matchedWords":[],"value":"Aegis Ada"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"https://aegisada.com/"}},"_tags":["story","author_Tolu1011","story_49368136"],"author":"Tolu1011","children":[49368137],"created_at":"2026-08-19T22:45:50Z","created_at_i":1787179550,"num_comments":0,"objectID":"49368136","points":1,"story_id":49368136,"title":"Aegis Ada","updated_at":"2026-08-19T22:49:56Z","url":"https://aegisada.com/"},{"_highlightResult":{"author":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["aegisai"],"value":"aegiswizard"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"Super ii Open intelligence, built together. A public AI collaboration hub for discovering, building, and sharing models, datasets, and apps."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://superii.site/"}},"_tags":["story","author_aegiswizard","story_49766549","show_hn"],"author":"aegiswizard","children":[49766585,49766589,49797399],"created_at":"2026-09-19T13:42:30Z","created_at_i":1789825350,"num_comments":2,"objectID":"49766549","points":2,"story_id":49766549,"story_text":"Super ii Open intelligence, built together. A public AI collaboration hub for discovering, building, and sharing models, datasets, and apps.","title":"Show HN","updated_at":"2026-09-22T06:25:45Z","url":"https://superii.site/"}],"hitsPerPage":50,"nbHits":8,"nbPages":1,"page":0,"params":"query=AegisAI&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":15,"processingTimingsMS":{"_request":{"roundTrip":14},"fetch":{"query":12,"scanning":1,"total":14},"total":15},"query":"AegisAI","serverTimeMS":17}