# Kagi Assistant

79 Hacker News commenters recommended Kagi Assistant and 20 criticized it, November 2025 to November 2026. It was recommended in 12 of 13 months. It meets the Hacker Approved badge rule.

**Verdict:** Recommended for search-grounded answers with footnoted sources, personalised ranking and many models in one subscription. Main caveat: it often gives confidently wrong answers.

## Why people recommend it

- Deep integration with Kagi search (4 comments): "Kagi has it as an option in its Assistant thing, where there is naturally a lot of searching and summarizing results." ([source](https://news.ycombinator.com/item?id=47837202)) "the deep search integration is precisely what makes this specific AI assistant better than, for example, ChatGPT" ([source](https://news.ycombinator.com/item?id=47434282)) "has worked great for me in scenarios where the search result data is more important than the model" ([source](https://news.ycombinator.com/item?id=47675632))
- Answers grounded in web sources (3 comments): "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 useful information" ([source](https://news.ycombinator.com/item?id=47424283)) "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." ([source](https://news.ycombinator.com/item?id=49390727)) "tends to produce higher-quality results for information that would not normally be within a given model's training data" ([source](https://news.ycombinator.com/item?id=49391768))
- Many models in one subscription (3 comments): "That plan comes with Kagi Assistant, which is more than enough with big selection of simple models for a great portion of AI assisted queries." ([source](https://news.ycombinator.com/item?id=49007202)) "They support many providers and new notable models are typically rolled out only a few days after release" ([source](https://news.ycombinator.com/item?id=45999930)) "It's more of a glorified search summarizer but it's essentially free with my existing subscription." ([source](https://news.ycombinator.com/item?id=47227810))
- Privacy from big-tech metadata sharing (2 comments): "One of the advantages being that they claim to be "privacy" layer that doesn't give other companies metadata about you." ([source](https://news.ycombinator.com/item?id=47428327)) "thanks to the strict privacy conditions of the API and the mixing of queries from thousands of users" ([source](https://news.ycombinator.com/item?id=47047748))

## What people warn about

- Not better than ChatGPT or Gemini (3 comments): "Kagi feels more like the results I would have had from ChatGPT a couple years ago" ([source](https://news.ycombinator.com/item?id=48451969)) "the Assistant is simply worse than using for example Gemini or ChatGPT directly" ([source](https://news.ycombinator.com/item?id=47424122)) "I don't see much difference in information compared to using existing models" ([source](https://news.ycombinator.com/item?id=45999158))
- Privacy trade-offs remain (2 comments): "its really good (GLM 4.7) but still there is some amount of tracking/logs still kept" ([source](https://news.ycombinator.com/item?id=46707385)) "I still felt that there was still very much a privacy trade off" ([source](https://news.ycombinator.com/item?id=46771566))

## Alternatives hackers recommend

- [Perplexity](https://hackerapproved.com/p/perplexity.md): 121 recommend
- [Google AI Mode](https://hackerapproved.com/p/google-ai-mode.md): 74 recommend
- [Phind](https://hackerapproved.com/p/phind.md): 36 recommend
- [Google AI summaries](https://hackerapproved.com/p/google-ai-summaries.md): 13 recommend

## Where to get it

- [Visit the official site](https://kagi.com/)

## Cite as

Hacker Approved, "Kagi Assistant", https://hackerapproved.com/p/kagi-assistant/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).