{"slug": "kagi-assistant", "name": "Kagi Assistant", "category": "ai", "category_name": "AI models and assistants", "description": "AI chat assistant from Kagi combining multiple LLMs with Kagi search results.", "recommenders": 10, "commenters": 14, "warners": 0, "score": 10.045, "rising": 2.04, "first": "2025-11-20", "latest": "2026-10-03", "why": "Liked for grounding LLM answers in Kagi search with footnoted sources, a choice of models such as Qwen3 and Kimi, and reusable custom assistants.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 10, "neutral": 3, "compare": 1, "warn": 0}, "spark": [1, 0, 0, 0, 4, 0, 0, 0, 1, 2, 1, 1], "listed": true, "loved": ["Search grounding", "Model choice"], "caveat": "Limited scope", "short_quote": "I\u2019m a happy user of both Kagi Search and Assistant.", "icon": true, "domain": "kagi.com", "github_repo": null, "official_url": "https://kagi.com/assistant", "pricing": "paid", "aliases": ["Kagi Assistant"], "verdict": [{"text": "Liked for grounding LLM answers in Kagi search with footnoted sources", "cites": [{"id": 796780880, "item_id": 49798805, "url": "https://news.ycombinator.com/item?id=49798805", "by": "o_m", "date": "2026-09-22", "stance": "recommend", "quote": "I use Kagi Assistant. It doesn't just give a summary, it is more like a personal \"Googler\"/web surfer.", "excerpt": "I use Kagi Assistant. It doesn't just give a summary, it is more like a personal \"Googler\"/web surfer. I feel like I'm involved in the process. My coworkers use Google and often quote back the AI summary me instead of checking the source and referring to that. It's scary seeing even those with higher education behave like this.", "context": "", "use_case": "web research", "switched_from": "", "story": "Study: Young users (9 to 18Y) ditch Google for AI, with unknown consequences"}, {"id": 790251632, "item_id": 49390727, "url": "https://news.ycombinator.com/item?id=49390727", "by": "claytongulick", "date": "2026-08-21", "stance": "recommend", "quote": "I'm here to admit I was wrong, it's incredibly useful.", "excerpt": "I remember at the time they were working on it a lot of people (honestly, including me) were pretty critical of them \"wasting\" their limited resources on AI stuff. We saw it as being sort of similar to the t-shirt drama [1]. I'm here to admit I was wrong, it's incredibly useful. It misses the mark frequently, like any LLM, but it's well annotated with footnotes that link to the original material. I use it all the tim", "context": "", "use_case": "AI search answers", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 758948512, "item_id": 47434282, "url": "https://news.ycombinator.com/item?id=47434282", "by": "fxtentacle", "date": "2026-03-18", "stance": "recommend", "quote": "I\u2019m a happy user of both Kagi Search and Assistant.", "excerpt": "I\u2019m a happy user of both Kagi Search and Assistant. I would totally support a \u201ceven more than Pro\u201d subscription for Assistant, but then it should also have its own proper API if I pay for it like a proper product. That said, I wonder how things would work if you subscribe to the assistant but not to search? Because to me, the deep search integration is precisely what makes this specific AI assistant better than, for ", "context": "", "use_case": "AI assistant with search", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 758788528, "item_id": 47424283, "url": "https://news.ycombinator.com/item?id=47424283", "by": "1313ed01", "date": "2026-03-18", "stance": "recommend", "quote": "I use the assistant daily, often instead of search.", "excerpt": "I use the assistant daily, often instead of search. The search is good, but the sad fact is searching www has been getting less interesting fast and there simply isn't much of value to find (maybe if they added an option to search in the Wayback Machine? I would pay extra for that!). Adding a LLM on top of search results and to fire off multiple searches makes it possible to sometimes squeeze a little bit of actually", "context": "", "use_case": "LLM-assisted search", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}]}, {"text": ", a choice of models such as Qwen3 and Kimi, and reusable custom assistants.", "cites": [{"id": 755675058, "item_id": 47229691, "url": "https://news.ycombinator.com/item?id=47229691", "by": "mongrelion", "date": "2026-03-03", "stance": "recommend", "quote": "I prefer to keep everything in Kagi.", "excerpt": "Through my Kagi subscription I get access to quite a few models [1] but I tend to rely on Qwen3 (fast) for quick questions and Qwen3 (reasoning) when I want a more structured approach, for example, when I am researching a topic. I have tried the same approach with Kimi K2.5 and GLM 5 but I keep going back fo Qwen3. I also have access to Perplexity which is quite decent to be honest, but I prefer to keep everything in", "context": "", "use_case": "accessing multiple LLMs", "switched_from": "", "story": "Ask HN: What Online LLM / Chat do you use?"}, {"id": 790229664, "item_id": 49389354, "url": "https://news.ycombinator.com/item?id=49389354", "by": "delis-thumbs-7e", "date": "2026-08-21", "stance": "recommend", "quote": "", "excerpt": "For those wanting to try Kagi does not just have ai search help, but full chat app: https://help.kagi.com/kagi/ai/assistant.html You can get it on at least iOS as well as its own app. You can select from bunch of China-models, I use Kim pretty much always. You can also do a system prompt and bunch of the same stuff you can with Claude etc. But it lies to me hardly ever. I don\u2019t know how they did that.", "context": "", "use_case": "AI chat", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 767920964, "item_id": 47995060, "url": "https://news.ycombinator.com/item?id=47995060", "by": "gherkinnn", "date": "2026-05-03", "stance": "neutral", "quote": "I use Kimi in Kagi's Assistant", "excerpt": "I never looked in to the details of these benchmarks, I live with the assumptions that most benchmarks of any kind are gamed and useless. What I do see in my own work and that of others around me, is that Claude consistently outperforms Gemini and to a lesser extent Codex. With Claude eating tokens with declining return, concessions have to be made and Codex is a usable middle ground. I use Kimi in Kagi's Assistant f", "context": "", "use_case": "chat access to Kimi", "switched_from": "", "story": "Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge"}, {"id": 784112480, "item_id": 49007030, "url": "https://news.ycombinator.com/item?id=49007030", "by": "eloisius", "date": "2026-07-22", "stance": "recommend", "quote": "I use these a lot.", "excerpt": "I use these a lot. If I find I keep front-loading a lot of context I just create an assistant. Like I just created one specific for Qt that includes all the context I kept prefacing questions with. The only thing I wish was a little easier was to change the model of the assistant.", "context": "", "use_case": "custom assistants with context", "switched_from": "", "story": "Back to Kagi"}]}, {"text": " Some see it as mainly a search summarizer rather than a replacement for ChatGPT or Claude", "cites": [{"id": 758787216, "item_id": 47424201, "url": "https://news.ycombinator.com/item?id=47424201", "by": "treesknees", "date": "2026-03-18", "stance": "neutral", "quote": "I\u2019ve used it quite a bit, but just as a natural language frontend to their search engine.", "excerpt": "I\u2019ve used it quite a bit, but just as a natural language frontend to their search engine. I don\u2019t see it as a true alternative to generic chat bots like Claude or ChatGPT, and certainly not a coding tool. I would likely not subscribe to Assistant.", "context": "", "use_case": "natural language search frontend", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 755644960, "item_id": 47227810, "url": "https://news.ycombinator.com/item?id=47227810", "by": "treesknees", "date": "2026-03-02", "stance": "neutral", "quote": "I\u2019ve been using the Kagi Assistant with various models.", "excerpt": "I\u2019ve been using the Kagi Assistant with various models. It\u2019s more of a glorified search summarizer but it\u2019s essentially free with my existing subscription.", "context": "Kagi subscriber", "use_case": "search summarizing and chat", "switched_from": "", "story": "Ask HN: What Online LLM / Chat do you use?"}]}, {"text": ", and others find the interface and model switching awkward.", "cites": [{"id": 758983504, "item_id": 47436469, "url": "https://news.ycombinator.com/item?id=47436469", "by": "entropyie", "date": "2026-03-19", "stance": "recommend", "quote": "Please keep Assistant, it's an easy to use alternative to OpenAI, and is not intrusive.", "excerpt": "Please keep Assistant, it's an easy to use alternative to OpenAI, and is not intrusive. I will say that I find the GUI infuriating though... It's never clear where the cursor is when you start a new chat. Don't understand the low contrast layout with too much whitespace.", "context": "", "use_case": "AI chat assistant", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 784112480, "item_id": 49007030, "url": "https://news.ycombinator.com/item?id=49007030", "by": "eloisius", "date": "2026-07-22", "stance": "recommend", "quote": "I use these a lot.", "excerpt": "I use these a lot. If I find I keep front-loading a lot of context I just create an assistant. Like I just created one specific for Qt that includes all the context I kept prefacing questions with. The only thing I wish was a little easier was to change the model of the assistant.", "context": "", "use_case": "custom assistants with context", "switched_from": "", "story": "Back to Kagi"}]}], "praise": [{"label": "Search grounding", "summary": "Runs searches and annotates answers with footnotes linking to original sources.", "quotes": [{"id": 796780880, "item_id": 49798805, "url": "https://news.ycombinator.com/item?id=49798805", "by": "o_m", "date": "2026-09-22", "stance": "recommend", "quote": "I use Kagi Assistant. It doesn't just give a summary, it is more like a personal \"Googler\"/web surfer.", "excerpt": "I use Kagi Assistant. It doesn't just give a summary, it is more like a personal \"Googler\"/web surfer. I feel like I'm involved in the process. My coworkers use Google and often quote back the AI summary me instead of checking the source and referring to that. It's scary seeing even those with higher education behave like this.", "context": "", "use_case": "web research", "switched_from": "", "story": "Study: Young users (9 to 18Y) ditch Google for AI, with unknown consequences"}, {"id": 790251632, "item_id": 49390727, "url": "https://news.ycombinator.com/item?id=49390727", "by": "claytongulick", "date": "2026-08-21", "stance": "recommend", "quote": "I'm here to admit I was wrong, it's incredibly useful.", "excerpt": "I remember at the time they were working on it a lot of people (honestly, including me) were pretty critical of them \"wasting\" their limited resources on AI stuff. We saw it as being sort of similar to the t-shirt drama [1]. I'm here to admit I was wrong, it's incredibly useful. It misses the mark frequently, like any LLM, but it's well annotated with footnotes that link to the original material. I use it all the tim", "context": "", "use_case": "AI search answers", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 758948512, "item_id": 47434282, "url": "https://news.ycombinator.com/item?id=47434282", "by": "fxtentacle", "date": "2026-03-18", "stance": "recommend", "quote": "I\u2019m a happy user of both Kagi Search and Assistant.", "excerpt": "I\u2019m a happy user of both Kagi Search and Assistant. I would totally support a \u201ceven more than Pro\u201d subscription for Assistant, but then it should also have its own proper API if I pay for it like a proper product. That said, I wonder how things would work if you subscribe to the assistant but not to search? Because to me, the deep search integration is precisely what makes this specific AI assistant better than, for ", "context": "", "use_case": "AI assistant with search", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}]}, {"label": "Model choice", "summary": "Commenters can pick from many models, with Qwen3 and Kimi named as favorites.", "quotes": [{"id": 755675058, "item_id": 47229691, "url": "https://news.ycombinator.com/item?id=47229691", "by": "mongrelion", "date": "2026-03-03", "stance": "recommend", "quote": "I prefer to keep everything in Kagi.", "excerpt": "Through my Kagi subscription I get access to quite a few models [1] but I tend to rely on Qwen3 (fast) for quick questions and Qwen3 (reasoning) when I want a more structured approach, for example, when I am researching a topic. I have tried the same approach with Kimi K2.5 and GLM 5 but I keep going back fo Qwen3. I also have access to Perplexity which is quite decent to be honest, but I prefer to keep everything in", "context": "", "use_case": "accessing multiple LLMs", "switched_from": "", "story": "Ask HN: What Online LLM / Chat do you use?"}, {"id": 790229664, "item_id": 49389354, "url": "https://news.ycombinator.com/item?id=49389354", "by": "delis-thumbs-7e", "date": "2026-08-21", "stance": "recommend", "quote": "", "excerpt": "For those wanting to try Kagi does not just have ai search help, but full chat app: https://help.kagi.com/kagi/ai/assistant.html You can get it on at least iOS as well as its own app. You can select from bunch of China-models, I use Kim pretty much always. You can also do a system prompt and bunch of the same stuff you can with Claude etc. But it lies to me hardly ever. I don\u2019t know how they did that.", "context": "", "use_case": "AI chat", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 790256129, "item_id": 49391008, "url": "https://news.ycombinator.com/item?id=49391008", "by": "cavoirom", "date": "2026-08-21", "stance": "neutral", "quote": "Yes, I use AI assistant a lot.", "excerpt": "Yes, I use AI assistant a lot. I copy the agent definition from Geir Isene to a custom assistant, it works nicely. In my experience, Kimi K2.6 reasoning works best. https://github.com/isene/ClaudeCode/blob/main/agents/web-research-specialist.md", "context": "", "use_case": "web research", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}]}, {"label": "Everyday usefulness", "summary": "Several commenters use it daily or a lot, sometimes instead of search.", "quotes": [{"id": 799086081, "item_id": 49942880, "url": "https://news.ycombinator.com/item?id=49942880", "by": "springtimesun", "date": "2026-10-03", "stance": "recommend", "quote": "I agree on the assistant. It is very capable.", "excerpt": "The way I remember it marketed, and the way I originally found it, was as a workaround to setting the default search on iOS. This was before I was conscious of AI and before I remember it being in any of Kagi\u2019s products. I ended up staying because the Adblock is good (search remains good). The browser is fine. It does have bugs and needs to be hard closed occasionally. I agree on the assistant. It is very capable. I ", "context": "", "use_case": "AI assistant", "switched_from": "", "story": "An Update on Orion for Linux and Windows"}, {"id": 758788528, "item_id": 47424283, "url": "https://news.ycombinator.com/item?id=47424283", "by": "1313ed01", "date": "2026-03-18", "stance": "recommend", "quote": "I use the assistant daily, often instead of search.", "excerpt": "I use the assistant daily, often instead of search. The search is good, but the sad fact is searching www has been getting less interesting fast and there simply isn't much of value to find (maybe if they added an option to search in the Wayback Machine? I would pay extra for that!). Adding a LLM on top of search results and to fire off multiple searches makes it possible to sometimes squeeze a little bit of actually", "context": "", "use_case": "LLM-assisted search", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 790251632, "item_id": 49390727, "url": "https://news.ycombinator.com/item?id=49390727", "by": "claytongulick", "date": "2026-08-21", "stance": "recommend", "quote": "I'm here to admit I was wrong, it's incredibly useful.", "excerpt": "I remember at the time they were working on it a lot of people (honestly, including me) were pretty critical of them \"wasting\" their limited resources on AI stuff. We saw it as being sort of similar to the t-shirt drama [1]. I'm here to admit I was wrong, it's incredibly useful. It misses the mark frequently, like any LLM, but it's well annotated with footnotes that link to the original material. I use it all the tim", "context": "", "use_case": "AI search answers", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}]}, {"label": "Custom assistants", "summary": "Commenters create custom assistants with saved context or system prompts.", "quotes": [{"id": 784112480, "item_id": 49007030, "url": "https://news.ycombinator.com/item?id=49007030", "by": "eloisius", "date": "2026-07-22", "stance": "recommend", "quote": "I use these a lot.", "excerpt": "I use these a lot. If I find I keep front-loading a lot of context I just create an assistant. Like I just created one specific for Qt that includes all the context I kept prefacing questions with. The only thing I wish was a little easier was to change the model of the assistant.", "context": "", "use_case": "custom assistants with context", "switched_from": "", "story": "Back to Kagi"}, {"id": 790256129, "item_id": 49391008, "url": "https://news.ycombinator.com/item?id=49391008", "by": "cavoirom", "date": "2026-08-21", "stance": "neutral", "quote": "Yes, I use AI assistant a lot.", "excerpt": "Yes, I use AI assistant a lot. I copy the agent definition from Geir Isene to a custom assistant, it works nicely. In my experience, Kimi K2.6 reasoning works best. https://github.com/isene/ClaudeCode/blob/main/agents/web-research-specialist.md", "context": "", "use_case": "web research", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 790229664, "item_id": 49389354, "url": "https://news.ycombinator.com/item?id=49389354", "by": "delis-thumbs-7e", "date": "2026-08-21", "stance": "recommend", "quote": "", "excerpt": "For those wanting to try Kagi does not just have ai search help, but full chat app: https://help.kagi.com/kagi/ai/assistant.html You can get it on at least iOS as well as its own app. You can select from bunch of China-models, I use Kim pretty much always. You can also do a system prompt and bunch of the same stuff you can with Claude etc. But it lies to me hardly ever. I don\u2019t know how they did that.", "context": "", "use_case": "AI chat", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}]}, {"label": "Straight answers", "summary": "Commenters report rare fabrications and no-nonsense responses.", "quotes": [{"id": 790229664, "item_id": 49389354, "url": "https://news.ycombinator.com/item?id=49389354", "by": "delis-thumbs-7e", "date": "2026-08-21", "stance": "recommend", "quote": "", "excerpt": "For those wanting to try Kagi does not just have ai search help, but full chat app: https://help.kagi.com/kagi/ai/assistant.html You can get it on at least iOS as well as its own app. You can select from bunch of China-models, I use Kim pretty much always. You can also do a system prompt and bunch of the same stuff you can with Claude etc. But it lies to me hardly ever. I don\u2019t know how they did that.", "context": "", "use_case": "AI chat", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 767920964, "item_id": 47995060, "url": "https://news.ycombinator.com/item?id=47995060", "by": "gherkinnn", "date": "2026-05-03", "stance": "neutral", "quote": "I use Kimi in Kagi's Assistant", "excerpt": "I never looked in to the details of these benchmarks, I live with the assumptions that most benchmarks of any kind are gamed and useless. What I do see in my own work and that of others around me, is that Claude consistently outperforms Gemini and to a lesser extent Codex. With Claude eating tokens with declining return, concessions have to be made and Codex is a usable middle ground. I use Kimi in Kagi's Assistant f", "context": "", "use_case": "chat access to Kimi", "switched_from": "", "story": "Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge"}]}, {"label": "Unobtrusive", "summary": "Easy to use or skip, for example by adding a question mark to a query.", "quotes": [{"id": 758983504, "item_id": 47436469, "url": "https://news.ycombinator.com/item?id=47436469", "by": "entropyie", "date": "2026-03-19", "stance": "recommend", "quote": "Please keep Assistant, it's an easy to use alternative to OpenAI, and is not intrusive.", "excerpt": "Please keep Assistant, it's an easy to use alternative to OpenAI, and is not intrusive. I will say that I find the GUI infuriating though... It's never clear where the cursor is when you start a new chat. Don't understand the low contrast layout with too much whitespace.", "context": "", "use_case": "AI chat assistant", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 790251632, "item_id": 49390727, "url": "https://news.ycombinator.com/item?id=49390727", "by": "claytongulick", "date": "2026-08-21", "stance": "recommend", "quote": "I'm here to admit I was wrong, it's incredibly useful.", "excerpt": "I remember at the time they were working on it a lot of people (honestly, including me) were pretty critical of them \"wasting\" their limited resources on AI stuff. We saw it as being sort of similar to the t-shirt drama [1]. I'm here to admit I was wrong, it's incredibly useful. It misses the mark frequently, like any LLM, but it's well annotated with footnotes that link to the original material. I use it all the tim", "context": "", "use_case": "AI search answers", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}]}], "caveats": [{"label": "Limited scope", "summary": "Some see it as a search summarizer, not a general chatbot or coding tool.", "quotes": [{"id": 758787216, "item_id": 47424201, "url": "https://news.ycombinator.com/item?id=47424201", "by": "treesknees", "date": "2026-03-18", "stance": "neutral", "quote": "I\u2019ve used it quite a bit, but just as a natural language frontend to their search engine.", "excerpt": "I\u2019ve used it quite a bit, but just as a natural language frontend to their search engine. I don\u2019t see it as a true alternative to generic chat bots like Claude or ChatGPT, and certainly not a coding tool. I would likely not subscribe to Assistant.", "context": "", "use_case": "natural language search frontend", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 755644960, "item_id": 47227810, "url": "https://news.ycombinator.com/item?id=47227810", "by": "treesknees", "date": "2026-03-02", "stance": "neutral", "quote": "I\u2019ve been using the Kagi Assistant with various models.", "excerpt": "I\u2019ve been using the Kagi Assistant with various models. It\u2019s more of a glorified search summarizer but it\u2019s essentially free with my existing subscription.", "context": "Kagi subscriber", "use_case": "search summarizing and chat", "switched_from": "", "story": "Ask HN: What Online LLM / Chat do you use?"}]}, {"label": "Clunky interface", "summary": "One commenter finds the GUI frustrating, and another wants easier model switching.", "quotes": [{"id": 758983504, "item_id": 47436469, "url": "https://news.ycombinator.com/item?id=47436469", "by": "entropyie", "date": "2026-03-19", "stance": "recommend", "quote": "Please keep Assistant, it's an easy to use alternative to OpenAI, and is not intrusive.", "excerpt": "Please keep Assistant, it's an easy to use alternative to OpenAI, and is not intrusive. I will say that I find the GUI infuriating though... It's never clear where the cursor is when you start a new chat. Don't understand the low contrast layout with too much whitespace.", "context": "", "use_case": "AI chat assistant", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 784112480, "item_id": 49007030, "url": "https://news.ycombinator.com/item?id=49007030", "by": "eloisius", "date": "2026-07-22", "stance": "recommend", "quote": "I use these a lot.", "excerpt": "I use these a lot. If I find I keep front-loading a lot of context I just create an assistant. Like I just created one specific for Qt that includes all the context I kept prefacing questions with. The only thing I wish was a little easier was to change the model of the assistant.", "context": "", "use_case": "custom assistants with context", "switched_from": "", "story": "Back to Kagi"}]}, {"label": "LLM misses", "summary": "Like any LLM, it frequently misses the mark.", "quotes": [{"id": 790251632, "item_id": 49390727, "url": "https://news.ycombinator.com/item?id=49390727", "by": "claytongulick", "date": "2026-08-21", "stance": "recommend", "quote": "I'm here to admit I was wrong, it's incredibly useful.", "excerpt": "I remember at the time they were working on it a lot of people (honestly, including me) were pretty critical of them \"wasting\" their limited resources on AI stuff. We saw it as being sort of similar to the t-shirt drama [1]. I'm here to admit I was wrong, it's incredibly useful. It misses the mark frequently, like any LLM, but it's well annotated with footnotes that link to the original material. I use it all the tim", "context": "", "use_case": "AI search answers", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}]}, {"label": "Research limits", "summary": "Quick research uses only already crawled sites, and its benefit over existing models is unclear to one commenter.", "quotes": [{"id": 735979184, "item_id": 45998699, "url": "https://news.ycombinator.com/item?id=45998699", "by": "ranyume", "date": "2025-11-20", "stance": "recommend", "quote": "I used quick research and it was pretty cool.", "excerpt": "I used quick research and it was pretty cool. A couple of caveats to keep in mind: 1. It answers using only the crawled sites. You can't make it crawl a new page. 2. It doesn't use a page' search function automatically. This is expected, but doesn't hurt to take that in mind. I think i'd be pretty useful. You ask for recent papers on a site and the engine could use hackernews' search function, then kagi would crawl t", "context": "", "use_case": "quick research over crawled sites", "switched_from": "", "story": "Kagi Assistants"}, {"id": 735986528, "item_id": 45999158, "url": "https://news.ycombinator.com/item?id=45999158", "by": "hatthew", "date": "2025-11-20", "stance": "compare", "quote": "When should I use kagi quick/research assistant instead of, e.g. kimi?", "excerpt": "I'm a little confused about what the point of these are compared to the existing features/models that kagi already has. Are they just supposed to be a one-stop shop where I don't have to choose which model to use? When should I use kagi quick/research assistant instead of, e.g. kimi? I tried the quick assistant a bit (don't have ultimate so I can't try research), and while the writing style seems slightly different, ", "context": "", "use_case": "AI assistant", "switched_from": "", "story": "Kagi Assistants"}]}, {"label": "No API", "summary": "One commenter wants a proper API if Assistant is sold as its own product.", "quotes": [{"id": 758948512, "item_id": 47434282, "url": "https://news.ycombinator.com/item?id=47434282", "by": "fxtentacle", "date": "2026-03-18", "stance": "recommend", "quote": "I\u2019m a happy user of both Kagi Search and Assistant.", "excerpt": "I\u2019m a happy user of both Kagi Search and Assistant. I would totally support a \u201ceven more than Pro\u201d subscription for Assistant, but then it should also have its own proper API if I pay for it like a proper product. That said, I wonder how things would work if you subscribe to the assistant but not to search? Because to me, the deep search integration is precisely what makes this specific AI assistant better than, for ", "context": "", "use_case": "AI assistant with search", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}]}], "who": [{"by": "treesknees", "context": "Kagi subscriber", "url": "https://news.ycombinator.com/item?id=47227810", "date": "2026-03-02"}], "tags": ["for Kagi subscribers", "for web research", "for non-coding questions", "on iOS"], "use_cases": ["ai assistant", "web research", "ai search answers", "ai chat", "custom assistants with context", "chat access to kimi"], "compared": [{"slug": "claude", "name": "Claude", "co": 5, "switched_from": 0, "switched_to": 0}, {"slug": "kimi", "name": "Kimi", "co": 5, "switched_from": 0, "switched_to": 0}, {"slug": "chatgpt", "name": "ChatGPT", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "kagi", "name": "Kagi", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=47423624", "title": "Kagi is contemplating the removal of the assistant from its professional tier", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=49388154", "title": "Kagi added a setting for removing paywalled links from search results", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=47227046", "title": "Ask HN: What Online LLM / Chat do you use?", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=45997294", "title": "Kagi Assistants", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49941447", "title": "An Update on Orion for Linux and Windows", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49798451", "title": "Study: Young users (9 to 18Y) ditch Google for AI, with unknown consequences", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1, "compare": 1}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"neutral": 1, "recommend": 4}, "2026-04": {}, "2026-05": {"neutral": 1}, "2026-06": {}, "2026-07": {"recommend": 1}, "2026-08": {"recommend": 2, "neutral": 1}, "2026-09": {"recommend": 1}, "2026-10": {"recommend": 1}}, "quotes": [{"id": 799086081, "item_id": 49942880, "url": "https://news.ycombinator.com/item?id=49942880", "by": "springtimesun", "date": "2026-10-03", "stance": "recommend", "quote": "I agree on the assistant. It is very capable.", "excerpt": "The way I remember it marketed, and the way I originally found it, was as a workaround to setting the default search on iOS. This was before I was conscious of AI and before I remember it being in any of Kagi\u2019s products. I ended up staying because the Adblock is good (search remains good). The browser is fine. It does have bugs and needs to be hard closed occasionally. I agree on the assistant. It is very capable. I ", "context": "", "use_case": "AI assistant", "switched_from": "", "story": "An Update on Orion for Linux and Windows"}, {"id": 796780880, "item_id": 49798805, "url": "https://news.ycombinator.com/item?id=49798805", "by": "o_m", "date": "2026-09-22", "stance": "recommend", "quote": "I use Kagi Assistant. It doesn't just give a summary, it is more like a personal \"Googler\"/web surfer.", "excerpt": "I use Kagi Assistant. It doesn't just give a summary, it is more like a personal \"Googler\"/web surfer. I feel like I'm involved in the process. My coworkers use Google and often quote back the AI summary me instead of checking the source and referring to that. It's scary seeing even those with higher education behave like this.", "context": "", "use_case": "web research", "switched_from": "", "story": "Study: Young users (9 to 18Y) ditch Google for AI, with unknown consequences"}, {"id": 790256129, "item_id": 49391008, "url": "https://news.ycombinator.com/item?id=49391008", "by": "cavoirom", "date": "2026-08-21", "stance": "neutral", "quote": "Yes, I use AI assistant a lot.", "excerpt": "Yes, I use AI assistant a lot. I copy the agent definition from Geir Isene to a custom assistant, it works nicely. In my experience, Kimi K2.6 reasoning works best. https://github.com/isene/ClaudeCode/blob/main/agents/web-research-specialist.md", "context": "", "use_case": "web research", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 790251632, "item_id": 49390727, "url": "https://news.ycombinator.com/item?id=49390727", "by": "claytongulick", "date": "2026-08-21", "stance": "recommend", "quote": "I'm here to admit I was wrong, it's incredibly useful.", "excerpt": "I remember at the time they were working on it a lot of people (honestly, including me) were pretty critical of them \"wasting\" their limited resources on AI stuff. We saw it as being sort of similar to the t-shirt drama [1]. I'm here to admit I was wrong, it's incredibly useful. It misses the mark frequently, like any LLM, but it's well annotated with footnotes that link to the original material. I use it all the tim", "context": "", "use_case": "AI search answers", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 790229664, "item_id": 49389354, "url": "https://news.ycombinator.com/item?id=49389354", "by": "delis-thumbs-7e", "date": "2026-08-21", "stance": "recommend", "quote": "", "excerpt": "For those wanting to try Kagi does not just have ai search help, but full chat app: https://help.kagi.com/kagi/ai/assistant.html You can get it on at least iOS as well as its own app. You can select from bunch of China-models, I use Kim pretty much always. You can also do a system prompt and bunch of the same stuff you can with Claude etc. But it lies to me hardly ever. I don\u2019t know how they did that.", "context": "", "use_case": "AI chat", "switched_from": "", "story": "Kagi added a setting for removing paywalled links from search results"}, {"id": 784112480, "item_id": 49007030, "url": "https://news.ycombinator.com/item?id=49007030", "by": "eloisius", "date": "2026-07-22", "stance": "recommend", "quote": "I use these a lot.", "excerpt": "I use these a lot. If I find I keep front-loading a lot of context I just create an assistant. Like I just created one specific for Qt that includes all the context I kept prefacing questions with. The only thing I wish was a little easier was to change the model of the assistant.", "context": "", "use_case": "custom assistants with context", "switched_from": "", "story": "Back to Kagi"}, {"id": 767920964, "item_id": 47995060, "url": "https://news.ycombinator.com/item?id=47995060", "by": "gherkinnn", "date": "2026-05-03", "stance": "neutral", "quote": "I use Kimi in Kagi's Assistant", "excerpt": "I never looked in to the details of these benchmarks, I live with the assumptions that most benchmarks of any kind are gamed and useless. What I do see in my own work and that of others around me, is that Claude consistently outperforms Gemini and to a lesser extent Codex. With Claude eating tokens with declining return, concessions have to be made and Codex is a usable middle ground. I use Kimi in Kagi's Assistant f", "context": "", "use_case": "chat access to Kimi", "switched_from": "", "story": "Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge"}, {"id": 758983504, "item_id": 47436469, "url": "https://news.ycombinator.com/item?id=47436469", "by": "entropyie", "date": "2026-03-19", "stance": "recommend", "quote": "Please keep Assistant, it's an easy to use alternative to OpenAI, and is not intrusive.", "excerpt": "Please keep Assistant, it's an easy to use alternative to OpenAI, and is not intrusive. I will say that I find the GUI infuriating though... It's never clear where the cursor is when you start a new chat. Don't understand the low contrast layout with too much whitespace.", "context": "", "use_case": "AI chat assistant", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 758948512, "item_id": 47434282, "url": "https://news.ycombinator.com/item?id=47434282", "by": "fxtentacle", "date": "2026-03-18", "stance": "recommend", "quote": "I\u2019m a happy user of both Kagi Search and Assistant.", "excerpt": "I\u2019m a happy user of both Kagi Search and Assistant. I would totally support a \u201ceven more than Pro\u201d subscription for Assistant, but then it should also have its own proper API if I pay for it like a proper product. That said, I wonder how things would work if you subscribe to the assistant but not to search? Because to me, the deep search integration is precisely what makes this specific AI assistant better than, for ", "context": "", "use_case": "AI assistant with search", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 758788528, "item_id": 47424283, "url": "https://news.ycombinator.com/item?id=47424283", "by": "1313ed01", "date": "2026-03-18", "stance": "recommend", "quote": "I use the assistant daily, often instead of search.", "excerpt": "I use the assistant daily, often instead of search. The search is good, but the sad fact is searching www has been getting less interesting fast and there simply isn't much of value to find (maybe if they added an option to search in the Wayback Machine? I would pay extra for that!). Adding a LLM on top of search results and to fire off multiple searches makes it possible to sometimes squeeze a little bit of actually", "context": "", "use_case": "LLM-assisted search", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 758787216, "item_id": 47424201, "url": "https://news.ycombinator.com/item?id=47424201", "by": "treesknees", "date": "2026-03-18", "stance": "neutral", "quote": "I\u2019ve used it quite a bit, but just as a natural language frontend to their search engine.", "excerpt": "I\u2019ve used it quite a bit, but just as a natural language frontend to their search engine. I don\u2019t see it as a true alternative to generic chat bots like Claude or ChatGPT, and certainly not a coding tool. I would likely not subscribe to Assistant.", "context": "", "use_case": "natural language search frontend", "switched_from": "", "story": "Kagi is contemplating the removal of the assistant from its professional tier"}, {"id": 755675058, "item_id": 47229691, "url": "https://news.ycombinator.com/item?id=47229691", "by": "mongrelion", "date": "2026-03-03", "stance": "recommend", "quote": "I prefer to keep everything in Kagi.", "excerpt": "Through my Kagi subscription I get access to quite a few models [1] but I tend to rely on Qwen3 (fast) for quick questions and Qwen3 (reasoning) when I want a more structured approach, for example, when I am researching a topic. I have tried the same approach with Kimi K2.5 and GLM 5 but I keep going back fo Qwen3. I also have access to Perplexity which is quite decent to be honest, but I prefer to keep everything in", "context": "", "use_case": "accessing multiple LLMs", "switched_from": "", "story": "Ask HN: What Online LLM / Chat do you use?"}, {"id": 755644960, "item_id": 47227810, "url": "https://news.ycombinator.com/item?id=47227810", "by": "treesknees", "date": "2026-03-02", "stance": "neutral", "quote": "I\u2019ve been using the Kagi Assistant with various models.", "excerpt": "I\u2019ve been using the Kagi Assistant with various models. It\u2019s more of a glorified search summarizer but it\u2019s essentially free with my existing subscription.", "context": "Kagi subscriber", "use_case": "search summarizing and chat", "switched_from": "", "story": "Ask HN: What Online LLM / Chat do you use?"}, {"id": 735986528, "item_id": 45999158, "url": "https://news.ycombinator.com/item?id=45999158", "by": "hatthew", "date": "2025-11-20", "stance": "compare", "quote": "When should I use kagi quick/research assistant instead of, e.g. kimi?", "excerpt": "I'm a little confused about what the point of these are compared to the existing features/models that kagi already has. Are they just supposed to be a one-stop shop where I don't have to choose which model to use? When should I use kagi quick/research assistant instead of, e.g. kimi? I tried the quick assistant a bit (don't have ultimate so I can't try research), and while the writing style seems slightly different, ", "context": "", "use_case": "AI assistant", "switched_from": "", "story": "Kagi Assistants"}, {"id": 735979184, "item_id": 45998699, "url": "https://news.ycombinator.com/item?id=45998699", "by": "ranyume", "date": "2025-11-20", "stance": "recommend", "quote": "I used quick research and it was pretty cool.", "excerpt": "I used quick research and it was pretty cool. A couple of caveats to keep in mind: 1. It answers using only the crawled sites. You can't make it crawl a new page. 2. It doesn't use a page' search function automatically. This is expected, but doesn't hurt to take that in mind. I think i'd be pretty useful. You ask for recent papers on a site and the engine could use hackernews' search function, then kagi would crawl t", "context": "", "use_case": "quick research over crawled sites", "switched_from": "", "story": "Kagi Assistants"}]}