{"slug": "searxng", "name": "SearXNG", "category": "selfhosted", "category_name": "Self-hosted and home server", "description": "Open-source, self-hostable metasearch engine that aggregates results from many other search engines.", "recommenders": 16, "commenters": 24, "warners": 0, "score": 16.408, "rising": 0.07, "first": "2025-11-01", "latest": "2026-10-31", "why": "Loved as a self-hosted, ad-free metasearch engine and as a search backend for local AI tools and coding agents.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 16, "neutral": 10, "compare": 0, "warn": 0}, "spark": [0, 1, 0, 1, 0, 0, 1, 3, 6, 2, 0, 2], "listed": true, "loved": ["AI search backend", "Result quality"], "caveat": "Rate limiting", "short_quote": "I use self-hosted SearXNG as part of my low-budget, privacy-oriented home AI stack with Open WebUI. It's a pretty useful tool!", "icon": false, "domain": null, "github_repo": "github.com/searxng/searxng", "official_url": "https://docs.searxng.org/", "pricing": "open source", "aliases": ["SearXNG"], "verdict": [{"text": "Loved as a self-hosted, ad-free metasearch engine", "cites": [{"id": 780523392, "item_id": 48782712, "url": "https://news.ycombinator.com/item?id=48782712", "by": "queenkjuul", "date": "2026-07-03", "stance": "recommend", "quote": "Highly recommend this. I set up a self-hosted instance and been using it exclusively for months. It's better than DDG", "excerpt": "Highly recommend this. I set up a self-hosted instance and been using it exclusively for months. It's better than DDG and i don't miss Google whatsoever. Image search is worse i guess mostly for lack of CDN so it's slow but whatever.", "context": "", "use_case": "self-hosted web search", "switched_from": "DuckDuckGo", "story": "SearXNG: A free internet metasearch engine"}, {"id": 802560224, "item_id": 50160014, "url": "https://news.ycombinator.com/item?id=50160014", "by": "chillfox", "date": "2026-10-20", "stance": "recommend", "quote": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago", "excerpt": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago when it started being rate limite/captcha'd frequently. My main reason for liking it is that it just gives me results without any ads or special summary/snippet/QA/etc... boxes. I really wouldn't mind paying API pricing for search, I think it would end up at less than $10/year, but I haven't ", "context": "", "use_case": "main search engine", "switched_from": "", "story": "DeepSeek search and fetch \u2013 $0.75 per 1000 successful requests"}, {"id": 774065072, "item_id": 48379067, "url": "https://news.ycombinator.com/item?id=48379067", "by": "operatingthetan", "date": "2026-06-02", "stance": "recommend", "quote": "I've switched to a local instance of SearXNG, no AI in results", "excerpt": "I've switched to a local instance of SearXNG, no AI in results and I don't see things I search for in ads on other platforms now.", "context": "", "use_case": "private web search", "switched_from": "", "story": "I Don't Want My Search Engine to Think for Me"}]}, {"text": " and as a search backend for local AI tools and coding agents.", "cites": [{"id": 779242192, "item_id": 48702637, "url": "https://news.ycombinator.com/item?id=48702637", "by": "wyrdcurt", "date": "2026-06-27", "stance": "recommend", "quote": "I use self-hosted SearXNG as part of my low-budget, privacy-oriented home AI stack with Open WebUI. It's a pretty useful tool!", "excerpt": "I use self-hosted SearXNG as part of my low-budget, privacy-oriented home AI stack with Open WebUI. It's a pretty useful tool! I'm a bit hesitant to post this because I'm not really here for self-promotion, but at some point I did have an LLM help me write up a guide on how I implemented it. It's here if anyone is curious: https://optimoss.ai/resources/searxng.html", "context": "", "use_case": "private search for home AI", "switched_from": "", "story": "You've tried DuckDuckGo and Brave Search, now get serious with SearXNG"}, {"id": 780511744, "item_id": 48781984, "url": "https://news.ycombinator.com/item?id=48781984", "by": "c-hendricks", "date": "2026-07-03", "stance": "recommend", "quote": "I use Searxng through Onyx, both as regular search and Onyx's Deep Research mode.", "excerpt": "I use Searxng through Onyx, both as regular search and Onyx's Deep Research mode. I also have https://github.com/ihor-sokoliuk/mcp-searxng to add search to coding agents. Haven't really had many issues with it.", "context": "", "use_case": "web search", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}, {"id": 788871712, "item_id": 49304482, "url": "https://news.ycombinator.com/item?id=49304482", "by": "satvikpendem", "date": "2026-08-14", "stance": "recommend", "quote": "I use something similar with the SearXNG MCP", "excerpt": "Looks good as I use something similar with the SearXNG MCP, but a shame this isn't an open weight model. There are some wrappers around SearXNG which seem to reduce the token counts returned thus making it easier for the calling model to understand, but a full dedicated model for search is nice. How does it compare with Perplexity, Gemini with search, and Parallel AI? Those are the cloud providers of search based mod", "context": "", "use_case": "search for LLMs", "switched_from": "", "story": "Introducing Toast 1"}]}, {"text": " The most common complaint is that it depends entirely on upstream search engines,", "cites": [{"id": 786503025, "item_id": 49156439, "url": "https://news.ycombinator.com/item?id=49156439", "by": "axegon_", "date": "2026-08-03", "stance": "recommend", "quote": "I also run searxng behind a tor proxy and while it does a pretty solid job overall", "excerpt": "Annoyingly search was at large solved just a few years ago and sadly someone has to reinvent the wheel soon. Lately I've completely switched to ecosia. It gives really decent results for the time being, hoping it'd improve with their co-op with qwant. I also run searxng behind a tor proxy and while it does a pretty solid job overall, it still relies entirely on other search engines so it's not a question of \"if\" but ", "context": "", "use_case": "metasearch", "switched_from": "", "story": "Ask HN: What are the viable alternatives to DuckDuckGo?"}, {"id": 780537872, "item_id": 48783617, "url": "https://news.ycombinator.com/item?id=48783617", "by": "RandyOrion", "date": "2026-07-04", "stance": "recommend", "quote": "I've been using searxng for several years now.", "excerpt": "I've been using searxng for several years now. I don't run my own instances because the inhumane network censorship imposed by GFW, and proxy detection enforced by search engines. Instead, I rely on public instances on the list [1] and libredirect [2]. Note that service from a single instance is not guaranteed, but you can always switch to other available instances with little cost within a minute. I won't say searxn", "context": "behind the GFW, uses public instances", "use_case": "metasearch, avoiding AI reviews", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}]}, {"text": " which can rate-limit or captcha it.", "cites": [{"id": 802560224, "item_id": 50160014, "url": "https://news.ycombinator.com/item?id=50160014", "by": "chillfox", "date": "2026-10-20", "stance": "recommend", "quote": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago", "excerpt": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago when it started being rate limite/captcha'd frequently. My main reason for liking it is that it just gives me results without any ads or special summary/snippet/QA/etc... boxes. I really wouldn't mind paying API pricing for search, I think it would end up at less than $10/year, but I haven't ", "context": "", "use_case": "main search engine", "switched_from": "", "story": "DeepSeek search and fetch \u2013 $0.75 per 1000 successful requests"}, {"id": 780534306, "item_id": 48783394, "url": "https://news.ycombinator.com/item?id=48783394", "by": "denysvitali", "date": "2026-07-04", "stance": "neutral", "quote": "It also needs a SearXNG server to run", "excerpt": "I've built https://github.com/denysvitali/searxng-mcp to use this as an MCP for coding agents. Works very well, until you get rate limited by the providers (e.g: DDG). It also needs a SearXNG server to run, so I recently pivoted towards a self-contained solution: https://github.com/denysvitali/search-mcp", "context": "", "use_case": "metasearch backend", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}]}], "praise": [{"label": "AI search backend", "summary": "Widely used to give local LLMs, Open WebUI, deep-research tools and coding agents web search via MCP.", "quotes": [{"id": 779242192, "item_id": 48702637, "url": "https://news.ycombinator.com/item?id=48702637", "by": "wyrdcurt", "date": "2026-06-27", "stance": "recommend", "quote": "I use self-hosted SearXNG as part of my low-budget, privacy-oriented home AI stack with Open WebUI. It's a pretty useful tool!", "excerpt": "I use self-hosted SearXNG as part of my low-budget, privacy-oriented home AI stack with Open WebUI. It's a pretty useful tool! I'm a bit hesitant to post this because I'm not really here for self-promotion, but at some point I did have an LLM help me write up a guide on how I implemented it. It's here if anyone is curious: https://optimoss.ai/resources/searxng.html", "context": "", "use_case": "private search for home AI", "switched_from": "", "story": "You've tried DuckDuckGo and Brave Search, now get serious with SearXNG"}, {"id": 780511744, "item_id": 48781984, "url": "https://news.ycombinator.com/item?id=48781984", "by": "c-hendricks", "date": "2026-07-03", "stance": "recommend", "quote": "I use Searxng through Onyx, both as regular search and Onyx's Deep Research mode.", "excerpt": "I use Searxng through Onyx, both as regular search and Onyx's Deep Research mode. I also have https://github.com/ihor-sokoliuk/mcp-searxng to add search to coding agents. Haven't really had many issues with it.", "context": "", "use_case": "web search", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}, {"id": 788871712, "item_id": 49304482, "url": "https://news.ycombinator.com/item?id=49304482", "by": "satvikpendem", "date": "2026-08-14", "stance": "recommend", "quote": "I use something similar with the SearXNG MCP", "excerpt": "Looks good as I use something similar with the SearXNG MCP, but a shame this isn't an open weight model. There are some wrappers around SearXNG which seem to reduce the token counts returned thus making it easier for the calling model to understand, but a full dedicated model for search is nice. How does it compare with Perplexity, Gemini with search, and Parallel AI? Those are the cloud providers of search based mod", "context": "", "use_case": "search for LLMs", "switched_from": "", "story": "Introducing Toast 1"}]}, {"label": "Result quality", "summary": "Several users made it their daily driver and found it better than DuckDuckGo, including for hard-to-find things.", "quotes": [{"id": 780523392, "item_id": 48782712, "url": "https://news.ycombinator.com/item?id=48782712", "by": "queenkjuul", "date": "2026-07-03", "stance": "recommend", "quote": "Highly recommend this. I set up a self-hosted instance and been using it exclusively for months. It's better than DDG", "excerpt": "Highly recommend this. I set up a self-hosted instance and been using it exclusively for months. It's better than DDG and i don't miss Google whatsoever. Image search is worse i guess mostly for lack of CDN so it's slow but whatever.", "context": "", "use_case": "self-hosted web search", "switched_from": "DuckDuckGo", "story": "SearXNG: A free internet metasearch engine"}, {"id": 781303718, "item_id": 48831482, "url": "https://news.ycombinator.com/item?id=48831482", "by": "nekusar", "date": "2026-07-08", "stance": "recommend", "quote": "Ive even changed my daily driver to it at home, since it gets great results", "excerpt": "Thank you for addressing my list. I'd like to use it, but requirements on non-local services is a deal breaker for me. Right now, with my Nanoclaw, I'm running it in a container on a VM on proxmox. If things get bad, I lose a backed up machine and any services it has credentials to. I can understand why IMAP is a pain. There's plenty of functions that can trash mailboxes. I don't envy you all in this task. For my STT", "context": "", "use_case": "private search", "switched_from": "", "story": "Show HN: Rowboat \u2013 Open-source, local-first alternative to Claude Desktop"}, {"id": 783616706, "item_id": 48976044, "url": "https://news.ycombinator.com/item?id=48976044", "by": "anenefan", "date": "2026-07-20", "stance": "neutral", "quote": "searx for hard to find things that sometimes didn't turn up in DDG", "excerpt": "Competitor isn't a word I could use to describe the web search scene in regard to google. However if one wanted a good search engine that one didn't have to keep banging on the keyboard for a half decent result I could say Yandex is one of the larger search engines that's performing really well on a lot of tech and niche areas compared to google or even duckduckgo atm. I though am pretty biased for I don't put up wit", "context": "", "use_case": "hard-to-find searches", "switched_from": "", "story": "Ask HN: Are there any new competitors to Google search in 2026?"}]}, {"label": "No ads or clutter", "summary": "Returns plain results without ads, AI answers or snippet boxes, and searches don't follow users into ads elsewhere.", "quotes": [{"id": 802560224, "item_id": 50160014, "url": "https://news.ycombinator.com/item?id=50160014", "by": "chillfox", "date": "2026-10-20", "stance": "recommend", "quote": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago", "excerpt": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago when it started being rate limite/captcha'd frequently. My main reason for liking it is that it just gives me results without any ads or special summary/snippet/QA/etc... boxes. I really wouldn't mind paying API pricing for search, I think it would end up at less than $10/year, but I haven't ", "context": "", "use_case": "main search engine", "switched_from": "", "story": "DeepSeek search and fetch \u2013 $0.75 per 1000 successful requests"}, {"id": 774065072, "item_id": 48379067, "url": "https://news.ycombinator.com/item?id=48379067", "by": "operatingthetan", "date": "2026-06-02", "stance": "recommend", "quote": "I've switched to a local instance of SearXNG, no AI in results", "excerpt": "I've switched to a local instance of SearXNG, no AI in results and I don't see things I search for in ads on other platforms now.", "context": "", "use_case": "private web search", "switched_from": "", "story": "I Don't Want My Search Engine to Think for Me"}]}, {"label": "Provider independence", "summary": "Aggregating many engines frees users from relying on any single provider and helps route around censorship.", "quotes": [{"id": 754983488, "item_id": 47186468, "url": "https://news.ycombinator.com/item?id=47186468", "by": "barnacs", "date": "2026-02-27", "stance": "recommend", "quote": "I highly recommend self-hosting a meta-search engine to get away from any single  provider", "excerpt": "I highly recommend self-hosting a meta-search engine to get away from any single provider without losing the benefits of either. I have been using searx[0] happily for years. [0]: https://github.com/searxng/searxng", "context": "", "use_case": "self-hosted meta search", "switched_from": "", "story": "Leaving Google has actively improved my life"}, {"id": 772263840, "item_id": 48266490, "url": "https://news.ycombinator.com/item?id=48266490", "by": "rdmuser", "date": "2026-05-25", "stance": "recommend", "quote": "Searxng is the best known one.", "excerpt": "For searches where you want more that just the first result and want a depth of results to go through and maybe even check out more than the first page of results I like to use meta-search engines that grab results from multiple sources. Plus it helps route around censorship since you are getting results from a variety of sources. Searxng is the best known one. I was quite fond of ixquick but it shut down ages ago. T", "context": "", "use_case": "meta-search", "switched_from": "", "story": "Search engines alternatives now that Google isn't Google anymore"}]}, {"label": "Long-term use", "summary": "Some commenters report using it happily for years.", "quotes": [{"id": 780537872, "item_id": 48783617, "url": "https://news.ycombinator.com/item?id=48783617", "by": "RandyOrion", "date": "2026-07-04", "stance": "recommend", "quote": "I've been using searxng for several years now.", "excerpt": "I've been using searxng for several years now. I don't run my own instances because the inhumane network censorship imposed by GFW, and proxy detection enforced by search engines. Instead, I rely on public instances on the list [1] and libredirect [2]. Note that service from a single instance is not guaranteed, but you can always switch to other available instances with little cost within a minute. I won't say searxn", "context": "behind the GFW, uses public instances", "use_case": "metasearch, avoiding AI reviews", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}, {"id": 754983488, "item_id": 47186468, "url": "https://news.ycombinator.com/item?id=47186468", "by": "barnacs", "date": "2026-02-27", "stance": "recommend", "quote": "I highly recommend self-hosting a meta-search engine to get away from any single  provider", "excerpt": "I highly recommend self-hosting a meta-search engine to get away from any single provider without losing the benefits of either. I have been using searx[0] happily for years. [0]: https://github.com/searxng/searxng", "context": "", "use_case": "self-hosted meta search", "switched_from": "", "story": "Leaving Google has actively improved my life"}]}], "caveats": [{"label": "Rate limiting", "summary": "Upstream providers increasingly rate-limit or captcha SearXNG queries.", "quotes": [{"id": 802560224, "item_id": 50160014, "url": "https://news.ycombinator.com/item?id=50160014", "by": "chillfox", "date": "2026-10-20", "stance": "recommend", "quote": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago", "excerpt": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago when it started being rate limite/captcha'd frequently. My main reason for liking it is that it just gives me results without any ads or special summary/snippet/QA/etc... boxes. I really wouldn't mind paying API pricing for search, I think it would end up at less than $10/year, but I haven't ", "context": "", "use_case": "main search engine", "switched_from": "", "story": "DeepSeek search and fetch \u2013 $0.75 per 1000 successful requests"}, {"id": 780534306, "item_id": 48783394, "url": "https://news.ycombinator.com/item?id=48783394", "by": "denysvitali", "date": "2026-07-04", "stance": "neutral", "quote": "It also needs a SearXNG server to run", "excerpt": "I've built https://github.com/denysvitali/searxng-mcp to use this as an MCP for coding agents. Works very well, until you get rate limited by the providers (e.g: DDG). It also needs a SearXNG server to run, so I recently pivoted towards a self-contained solution: https://github.com/denysvitali/search-mcp", "context": "", "use_case": "metasearch backend", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}]}, {"label": "Upstream dependence", "summary": "It relies entirely on other search engines, so it can't fully degoogle you and may degrade if they change.", "quotes": [{"id": 786503025, "item_id": 49156439, "url": "https://news.ycombinator.com/item?id=49156439", "by": "axegon_", "date": "2026-08-03", "stance": "recommend", "quote": "I also run searxng behind a tor proxy and while it does a pretty solid job overall", "excerpt": "Annoyingly search was at large solved just a few years ago and sadly someone has to reinvent the wheel soon. Lately I've completely switched to ecosia. It gives really decent results for the time being, hoping it'd improve with their co-op with qwant. I also run searxng behind a tor proxy and while it does a pretty solid job overall, it still relies entirely on other search engines so it's not a question of \"if\" but ", "context": "", "use_case": "metasearch", "switched_from": "", "story": "Ask HN: What are the viable alternatives to DuckDuckGo?"}, {"id": 780537872, "item_id": 48783617, "url": "https://news.ycombinator.com/item?id=48783617", "by": "RandyOrion", "date": "2026-07-04", "stance": "recommend", "quote": "I've been using searxng for several years now.", "excerpt": "I've been using searxng for several years now. I don't run my own instances because the inhumane network censorship imposed by GFW, and proxy detection enforced by search engines. Instead, I rely on public instances on the list [1] and libredirect [2]. Note that service from a single instance is not guaranteed, but you can always switch to other available instances with little cost within a minute. I won't say searxn", "context": "behind the GFW, uses public instances", "use_case": "metasearch, avoiding AI reviews", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}]}, {"label": "Image search", "summary": "One self-hoster found image search worse and slow, lacking a CDN.", "quotes": [{"id": 780523392, "item_id": 48782712, "url": "https://news.ycombinator.com/item?id=48782712", "by": "queenkjuul", "date": "2026-07-03", "stance": "recommend", "quote": "Highly recommend this. I set up a self-hosted instance and been using it exclusively for months. It's better than DDG", "excerpt": "Highly recommend this. I set up a self-hosted instance and been using it exclusively for months. It's better than DDG and i don't miss Google whatsoever. Image search is worse i guess mostly for lack of CDN so it's slow but whatever.", "context": "", "use_case": "self-hosted web search", "switched_from": "DuckDuckGo", "story": "SearXNG: A free internet metasearch engine"}]}, {"label": "Below Kagi", "summary": "One user called it okay but not quite as good as Kagi.", "quotes": [{"id": 784272562, "item_id": 49017035, "url": "https://news.ycombinator.com/item?id=49017035", "by": "delis-thumbs-7e", "date": "2026-07-22", "stance": "neutral", "quote": "I have recently started using searXNG, which is ok, and somehow better than mpst for image searches, but not quite as good as Kagi.", "excerpt": "Kagi is great. The search gives you the actual thing you are looking for, but also their translate tool is very nifty, and their LLM assistants are actually better for my purposes than Anthropic or whatever. I have tried the same models via openrouter, but can\u2019t get as good responses, so there\u2019s something very clever they do with their harness. I use their Orion -browser and its summarise -function, which is very goo", "context": "", "use_case": "image search", "switched_from": "", "story": "Back to Kagi"}]}, {"label": "Integration effort", "summary": "Combining it into a local AI retrieval stack took quite a bit of custom coding.", "quotes": [{"id": 787905570, "item_id": 49244098, "url": "https://news.ycombinator.com/item?id=49244098", "by": "Roark66", "date": "2026-08-10", "stance": "neutral", "quote": "All components use open source projects such as SearXNG, Crawl4AI, MetaMCP, Jina rerank", "excerpt": "I've been using Qwen3.6 models locally for a couple of weeks. Both the A3B moe and the dense variant. The moe works well in Librechat combined with my local search/Web retrieval system. All components use open source projects such as SearXNG, Crawl4AI, MetaMCP, Jina rerank, but all needed quite a bit of coding to work nicely together. I get 140 tok/s on short prompts on an rtx3090 on the qwen3.6 moe which makes is ea", "context": "", "use_case": "local web search", "switched_from": "", "story": "DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years"}]}, {"label": "Public instances", "summary": "Service from any single public instance is not guaranteed, though switching instances is quick.", "quotes": [{"id": 780537872, "item_id": 48783617, "url": "https://news.ycombinator.com/item?id=48783617", "by": "RandyOrion", "date": "2026-07-04", "stance": "recommend", "quote": "I've been using searxng for several years now.", "excerpt": "I've been using searxng for several years now. I don't run my own instances because the inhumane network censorship imposed by GFW, and proxy detection enforced by search engines. Instead, I rely on public instances on the list [1] and libredirect [2]. Note that service from a single instance is not guaranteed, but you can always switch to other available instances with little cost within a minute. I won't say searxn", "context": "behind the GFW, uses public instances", "use_case": "metasearch, avoiding AI reviews", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}]}], "who": [{"by": "snailmailman", "context": "gets frequent captchas without VPN", "url": "https://news.ycombinator.com/item?id=49163338", "date": "2026-08-03"}, {"by": "RandyOrion", "context": "behind the GFW, uses public instances", "url": "https://news.ycombinator.com/item?id=48783617", "date": "2026-07-04"}, {"by": "Roark66", "context": "homelab user", "url": "https://news.ycombinator.com/item?id=46353048", "date": "2025-12-22"}], "tags": ["self-hostable", "for local AI stacks", "for coding agents (MCP)", "privacy-focused", "for homelabs"], "use_cases": ["self-hosted search", "metasearch", "web search", "main search engine", "search for llms", "local web search"], "compared": [{"slug": "duckduckgo", "name": "DuckDuckGo", "co": 8, "switched_from": 1, "switched_to": 0}, {"slug": "kagi", "name": "Kagi", "co": 5, "switched_from": 1, "switched_to": 0}, {"slug": "open-webui", "name": "Open WebUI", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "gemini", "name": "Gemini", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48779454", "title": "SearXNG: A free internet metasearch engine", "mentions": 5}, {"url": "https://news.ycombinator.com/item?id=49155492", "title": "Ask HN: What are the viable alternatives to DuckDuckGo?", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50317310", "title": "Ask HN: Will apps be going away in favor of personal assistants?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50138531", "title": "DeepSeek search and fetch \u2013 $0.75 per 1000 successful requests", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49870367", "title": "When did Google get so weird?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49299746", "title": "Introducing Toast 1", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 2}, "2025-12": {"recommend": 1}, "2026-01": {}, "2026-02": {"recommend": 1}, "2026-03": {}, "2026-04": {"neutral": 1}, "2026-05": {"recommend": 1}, "2026-06": {"recommend": 3}, "2026-07": {"recommend": 6, "neutral": 3}, "2026-08": {"neutral": 3, "recommend": 2}, "2026-09": {"neutral": 1}, "2026-10": {"recommend": 2}}, "quotes": [{"id": 805084736, "item_id": 50317796, "url": "https://news.ycombinator.com/item?id=50317796", "by": "jasonvorhe", "date": "2026-10-31", "stance": "recommend", "quote": "my own hosted model + searxng drops results faster", "excerpt": "Some will, some won't. I prefer some webapps to their native ones and vice versa. I used to run some proprietary apps that I replaced with open source ones, often clients interfacing with already self hosted stuff. I rarely touch Kagi anymore because my own hosted model + searxng drops results faster. I don't expect most of these apps to go away just because of agents/assistants alone. Proprietary apps and services w", "context": "", "use_case": "self-hosted search", "switched_from": "Kagi", "story": "Ask HN: Will apps be going away in favor of personal assistants?"}, {"id": 802560224, "item_id": 50160014, "url": "https://news.ycombinator.com/item?id=50160014", "by": "chillfox", "date": "2026-10-20", "stance": "recommend", "quote": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago", "excerpt": "I have been using SearXNG as my main search engine for a while (not for AI stuff), and it's been great up until 2-3 months ago when it started being rate limite/captcha'd frequently. My main reason for liking it is that it just gives me results without any ads or special summary/snippet/QA/etc... boxes. I really wouldn't mind paying API pricing for search, I think it would end up at less than $10/year, but I haven't ", "context": "", "use_case": "main search engine", "switched_from": "", "story": "DeepSeek search and fetch \u2013 $0.75 per 1000 successful requests"}, {"id": 797989347, "item_id": 49874334, "url": "https://news.ycombinator.com/item?id=49874334", "by": "delis-thumbs-7e", "date": "2026-09-28", "stance": "neutral", "quote": "I would use SearXNG locally accessing it elsewhere with Tailscale.", "excerpt": "Kagi is brilliant. I find the whole Yandex -thing silly (EU spending on liquefied gas etc. from Russia is more than Yandex\u2019s whole annual revenue) and only wish same scrutiny would be put on corporations funding Israel genocides. I use DDG at work on Firefox with all AI blocked. If I would apart from Kagi, I would use SearXNG locally accessing it elsewhere with Tailscale. I think Hister seems promising, but have not ", "context": "", "use_case": "self-hosted search", "switched_from": "", "story": "When did Google get so weird?"}, {"id": 788871712, "item_id": 49304482, "url": "https://news.ycombinator.com/item?id=49304482", "by": "satvikpendem", "date": "2026-08-14", "stance": "recommend", "quote": "I use something similar with the SearXNG MCP", "excerpt": "Looks good as I use something similar with the SearXNG MCP, but a shame this isn't an open weight model. There are some wrappers around SearXNG which seem to reduce the token counts returned thus making it easier for the calling model to understand, but a full dedicated model for search is nice. How does it compare with Perplexity, Gemini with search, and Parallel AI? Those are the cloud providers of search based mod", "context": "", "use_case": "search for LLMs", "switched_from": "", "story": "Introducing Toast 1"}, {"id": 787905570, "item_id": 49244098, "url": "https://news.ycombinator.com/item?id=49244098", "by": "Roark66", "date": "2026-08-10", "stance": "neutral", "quote": "All components use open source projects such as SearXNG, Crawl4AI, MetaMCP, Jina rerank", "excerpt": "I've been using Qwen3.6 models locally for a couple of weeks. Both the A3B moe and the dense variant. The moe works well in Librechat combined with my local search/Web retrieval system. All components use open source projects such as SearXNG, Crawl4AI, MetaMCP, Jina rerank, but all needed quite a bit of coding to work nicely together. I get 140 tok/s on short prompts on an rtx3090 on the qwen3.6 moe which makes is ea", "context": "", "use_case": "local web search", "switched_from": "", "story": "DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years"}, {"id": 786613408, "item_id": 49163338, "url": "https://news.ycombinator.com/item?id=49163338", "by": "snailmailman", "date": "2026-08-03", "stance": "neutral", "quote": "", "excerpt": "I wish it was a problem with my vpn/exit node. But I get these captchas when I\u2019m not on a VPN. I assume it\u2019s just because I don\u2019t login to Google and I enable tracking prevention stuff in Firefox? But that\u2019s really only on my desktop. I get them on my iphone too which is vanilla iOS safari. I get captchas and the cloudflare checkboxes extremely frequently, and sometimes cannot get past them at all. I saw the articles", "context": "gets frequent captchas without VPN", "use_case": "search without captchas", "switched_from": "", "story": "SearXNG in Rust"}, {"id": 786503025, "item_id": 49156439, "url": "https://news.ycombinator.com/item?id=49156439", "by": "axegon_", "date": "2026-08-03", "stance": "recommend", "quote": "I also run searxng behind a tor proxy and while it does a pretty solid job overall", "excerpt": "Annoyingly search was at large solved just a few years ago and sadly someone has to reinvent the wheel soon. Lately I've completely switched to ecosia. It gives really decent results for the time being, hoping it'd improve with their co-op with qwant. I also run searxng behind a tor proxy and while it does a pretty solid job overall, it still relies entirely on other search engines so it's not a question of \"if\" but ", "context": "", "use_case": "metasearch", "switched_from": "", "story": "Ask HN: What are the viable alternatives to DuckDuckGo?"}, {"id": 786500608, "item_id": 49156288, "url": "https://news.ycombinator.com/item?id=49156288", "by": "dml2135", "date": "2026-08-03", "stance": "neutral", "quote": "I have not used it yet, but this project looks interesting to me", "excerpt": "I have not used it yet, but this project looks interesting to me: https://docs.searxng.org/", "context": "", "use_case": "metasearch", "switched_from": "", "story": "Ask HN: What are the viable alternatives to DuckDuckGo?"}, {"id": 784272562, "item_id": 49017035, "url": "https://news.ycombinator.com/item?id=49017035", "by": "delis-thumbs-7e", "date": "2026-07-22", "stance": "neutral", "quote": "I have recently started using searXNG, which is ok, and somehow better than mpst for image searches, but not quite as good as Kagi.", "excerpt": "Kagi is great. The search gives you the actual thing you are looking for, but also their translate tool is very nifty, and their LLM assistants are actually better for my purposes than Anthropic or whatever. I have tried the same models via openrouter, but can\u2019t get as good responses, so there\u2019s something very clever they do with their harness. I use their Orion -browser and its summarise -function, which is very goo", "context": "", "use_case": "image search", "switched_from": "", "story": "Back to Kagi"}, {"id": 783616706, "item_id": 48976044, "url": "https://news.ycombinator.com/item?id=48976044", "by": "anenefan", "date": "2026-07-20", "stance": "neutral", "quote": "searx for hard to find things that sometimes didn't turn up in DDG", "excerpt": "Competitor isn't a word I could use to describe the web search scene in regard to google. However if one wanted a good search engine that one didn't have to keep banging on the keyboard for a half decent result I could say Yandex is one of the larger search engines that's performing really well on a lot of tech and niche areas compared to google or even duckduckgo atm. I though am pretty biased for I don't put up wit", "context": "", "use_case": "hard-to-find searches", "switched_from": "", "story": "Ask HN: Are there any new competitors to Google search in 2026?"}, {"id": 781303718, "item_id": 48831482, "url": "https://news.ycombinator.com/item?id=48831482", "by": "nekusar", "date": "2026-07-08", "stance": "recommend", "quote": "Ive even changed my daily driver to it at home, since it gets great results", "excerpt": "Thank you for addressing my list. I'd like to use it, but requirements on non-local services is a deal breaker for me. Right now, with my Nanoclaw, I'm running it in a container on a VM on proxmox. If things get bad, I lose a backed up machine and any services it has credentials to. I can understand why IMAP is a pain. There's plenty of functions that can trash mailboxes. I don't envy you all in this task. For my STT", "context": "", "use_case": "private search", "switched_from": "", "story": "Show HN: Rowboat \u2013 Open-source, local-first alternative to Claude Desktop"}, {"id": 780537872, "item_id": 48783617, "url": "https://news.ycombinator.com/item?id=48783617", "by": "RandyOrion", "date": "2026-07-04", "stance": "recommend", "quote": "I've been using searxng for several years now.", "excerpt": "I've been using searxng for several years now. I don't run my own instances because the inhumane network censorship imposed by GFW, and proxy detection enforced by search engines. Instead, I rely on public instances on the list [1] and libredirect [2]. Note that service from a single instance is not guaranteed, but you can always switch to other available instances with little cost within a minute. I won't say searxn", "context": "behind the GFW, uses public instances", "use_case": "metasearch, avoiding AI reviews", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}, {"id": 780534306, "item_id": 48783394, "url": "https://news.ycombinator.com/item?id=48783394", "by": "denysvitali", "date": "2026-07-04", "stance": "neutral", "quote": "It also needs a SearXNG server to run", "excerpt": "I've built https://github.com/denysvitali/searxng-mcp to use this as an MCP for coding agents. Works very well, until you get rate limited by the providers (e.g: DDG). It also needs a SearXNG server to run, so I recently pivoted towards a self-contained solution: https://github.com/denysvitali/search-mcp", "context": "", "use_case": "metasearch backend", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}, {"id": 780523392, "item_id": 48782712, "url": "https://news.ycombinator.com/item?id=48782712", "by": "queenkjuul", "date": "2026-07-03", "stance": "recommend", "quote": "Highly recommend this. I set up a self-hosted instance and been using it exclusively for months. It's better than DDG", "excerpt": "Highly recommend this. I set up a self-hosted instance and been using it exclusively for months. It's better than DDG and i don't miss Google whatsoever. Image search is worse i guess mostly for lack of CDN so it's slow but whatever.", "context": "", "use_case": "self-hosted web search", "switched_from": "DuckDuckGo", "story": "SearXNG: A free internet metasearch engine"}, {"id": 780511744, "item_id": 48781984, "url": "https://news.ycombinator.com/item?id=48781984", "by": "c-hendricks", "date": "2026-07-03", "stance": "recommend", "quote": "I use Searxng through Onyx, both as regular search and Onyx's Deep Research mode.", "excerpt": "I use Searxng through Onyx, both as regular search and Onyx's Deep Research mode. I also have https://github.com/ihor-sokoliuk/mcp-searxng to add search to coding agents. Haven't really had many issues with it.", "context": "", "use_case": "web search", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}, {"id": 780480864, "item_id": 48780054, "url": "https://news.ycombinator.com/item?id=48780054", "by": "ManWith2Plans", "date": "2026-07-03", "stance": "recommend", "quote": "It's exceptional and I recommend it highly.", "excerpt": "I've been using this for some projects. It's exceptional and I recommend it highly. I actually included a recipe to deploy it to kubernetes in typekro, my TypeScript infrastructure-as-code project for kubernetes: https://typekro.run/api/searxng/", "context": "", "use_case": "search for projects", "switched_from": "", "story": "SearXNG: A free internet metasearch engine"}, {"id": 779916762, "item_id": 48744797, "url": "https://news.ycombinator.com/item?id=48744797", "by": "anthk", "date": "2026-07-01", "stance": "recommend", "quote": "I don't use Google. DDG, searx and the like.", "excerpt": "It's still there, at IRC/Usenet/some niche forums. Replace phreaking with maybe some mesh networks and ways to connect computers without calling an ISP. There are still niche blogs and even phlogs. And you can still use Pidgin and libpurple plugins to connect to a huge array of protocols. Ditto with core Biltbee or Bitlbee+libpurple allowing you to use any IRC client (even the ones without TLS for DOS and Win9X) to c", "context": "", "use_case": "web search", "switched_from": "Google", "story": "The Internet I Grew Up with Doesn't Exist Anymore"}, {"id": 779242192, "item_id": 48702637, "url": "https://news.ycombinator.com/item?id=48702637", "by": "wyrdcurt", "date": "2026-06-27", "stance": "recommend", "quote": "I use self-hosted SearXNG as part of my low-budget, privacy-oriented home AI stack with Open WebUI. It's a pretty useful tool!", "excerpt": "I use self-hosted SearXNG as part of my low-budget, privacy-oriented home AI stack with Open WebUI. It's a pretty useful tool! I'm a bit hesitant to post this because I'm not really here for self-promotion, but at some point I did have an LLM help me write up a guide on how I implemented it. It's here if anyone is curious: https://optimoss.ai/resources/searxng.html", "context": "", "use_case": "private search for home AI", "switched_from": "", "story": "You've tried DuckDuckGo and Brave Search, now get serious with SearXNG"}, {"id": 776298112, "item_id": 48518632, "url": "https://news.ycombinator.com/item?id=48518632", "by": "medfield", "date": "2026-06-13", "stance": "recommend", "quote": "a better SearXNG setup", "excerpt": "I use local models to explore, hosted models to refine. I somewhat envy those who can sustain local models (q8 120b+) running as a hobby.... for me, the practical path is a better SearXNG setup and knowing my routes forward.", "context": "", "use_case": "search", "switched_from": "", "story": "RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8"}, {"id": 774065072, "item_id": 48379067, "url": "https://news.ycombinator.com/item?id=48379067", "by": "operatingthetan", "date": "2026-06-02", "stance": "recommend", "quote": "I've switched to a local instance of SearXNG, no AI in results", "excerpt": "I've switched to a local instance of SearXNG, no AI in results and I don't see things I search for in ads on other platforms now.", "context": "", "use_case": "private web search", "switched_from": "", "story": "I Don't Want My Search Engine to Think for Me"}, {"id": 772263840, "item_id": 48266490, "url": "https://news.ycombinator.com/item?id=48266490", "by": "rdmuser", "date": "2026-05-25", "stance": "recommend", "quote": "Searxng is the best known one.", "excerpt": "For searches where you want more that just the first result and want a depth of results to go through and maybe even check out more than the first page of results I like to use meta-search engines that grab results from multiple sources. Plus it helps route around censorship since you are getting results from a variety of sources. Searxng is the best known one. I was quite fond of ixquick but it shut down ages ago. T", "context": "", "use_case": "meta-search", "switched_from": "", "story": "Search engines alternatives now that Google isn't Google anymore"}, {"id": 764584673, "item_id": 47786542, "url": "https://news.ycombinator.com/item?id=47786542", "by": "blackmanta", "date": "2026-04-15", "stance": "neutral", "quote": "an \u201curgent\u201d news job that uses searx", "excerpt": "I have an instance that does search related to my research interests, tracks news related to viruses in the US, events happening around my area and an \u201curgent\u201d news job that uses searx and for things going on around me. I used Qwen 3.5 9B and tuned some of the jobs with GPT 5.4. I recently switched to use Gemma 4 and there was seemingly no major difference. I\u2019ve found it useful for the digest and for findings papers ", "context": "", "use_case": "news search", "switched_from": "", "story": "Is anyone actually using OpenClaw?"}, {"id": 754983488, "item_id": 47186468, "url": "https://news.ycombinator.com/item?id=47186468", "by": "barnacs", "date": "2026-02-27", "stance": "recommend", "quote": "I highly recommend self-hosting a meta-search engine to get away from any single  provider", "excerpt": "I highly recommend self-hosting a meta-search engine to get away from any single provider without losing the benefits of either. I have been using searx[0] happily for years. [0]: https://github.com/searxng/searxng", "context": "", "use_case": "self-hosted meta search", "switched_from": "", "story": "Leaving Google has actively improved my life"}, {"id": 741648768, "item_id": 46353048, "url": "https://news.ycombinator.com/item?id=46353048", "by": "Roark66", "date": "2025-12-22", "stance": "recommend", "quote": "I run a searXNG and Crawl4AI", "excerpt": "I'm glad the author clarified he wants to prevent his instance from crashing not simply \"block robots and allow humans\". I think the idea that you can block bots and allow humans is fallacious. We should focus on a specific behaviour that causes problems (like making a bajillion requests one for each commit, instead of cloning the repo). To fix this we should block clients that work in such ways. If these bots learn ", "context": "homelab user", "use_case": "AI live web search", "switched_from": "", "story": "How I protect my Forgejo instance from AI web crawlers"}, {"id": 732786194, "item_id": 45799137, "url": "https://news.ycombinator.com/item?id=45799137", "by": "incomingpain", "date": "2025-11-03", "stance": "neutral", "quote": "Especially easy if you already run searxng locally.", "excerpt": "I love this one: https://github.com/LearningCircuit/local-deep-research I tied it together with qwen3 30b thinking. Very easy to get it up and running, but lots of the numbers are shockingly low. You need to boost iterations and context. Especially easy if you already run searxng locally. I havent finished tuning the actual settings, but for the detailed report it'll take ~20 minutes and so far has given pretty good ", "context": "", "use_case": "local search backend", "switched_from": "", "story": "Tongyi DeepResearch \u2013 open-source 30B MoE Model that rivals OpenAI DeepResearch"}, {"id": 732522608, "item_id": 45782663, "url": "https://news.ycombinator.com/item?id=45782663", "by": "nickthegreek", "date": "2025-11-01", "stance": "neutral", "quote": "just setup searxng yesterday", "excerpt": "just setup searxng yesterday and mcp for it in lm studio to be able to search the net for answers to simple queries. small ibm granite worked surpassingly well, while oss20b seemed to be looping searches.", "context": "", "use_case": "web search for local LLM", "switched_from": "", "story": "Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop"}]}