Keenable
A different web search API for AI agents
Details
- External ID
- 49435555
- Source
- HN
- Company
- —
- Product
- Keenable
- Website domain
- keenable.ai
- Launched
- Aug. 25, 2026
- Cohort
- —
- Upvotes
- 12
- Upvotes percentile
- 0.6364247311827957
- Tags
- —
- Fetched at
- Sept. 10, 2026, 5:32 a.m.
- Updated at
- Sept. 10, 2026, 5:32 a.m.
Description
Hey HN! We built https://keenable.ai, a different web search API for AI agents.Keenable searches our own 100B+ page index. We are focused on low cost and latency (p95 <250ms from us-east). We don’t believe in benchmaxxing, so we open-sourced our internal benchmarking suite, NEEDLE (available at https://keenableai.github.io/needle): a live benchmark that compares Keenable with other search APIs on fresh agent-like queries.I spent seven years at Amazon as a scientist working on web grounding for Alexa/AGI, and my co-founder Andrey previously led search at Yandex. We started Keenable because agents search differently from humans, and we wanted to build around those patterns directly.The API is available now and we provide a free allowance of 100,000 requests a month.It also exposes a novel SQL-like interface to the web, which is useful for structured extraction and agent workflows.Happy to answer questions about the index, crawl, ranking, latency, or benchmarking.
Enrichment
- Theme
- ai agent infrastructure and tooling
- Vertical
- Horizontal
- Function
- Search & retrieval
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- web search api for ai agents
- Manually corrected
- False
Could you build this?
No Operating an independent 100B+ page web search index with sub-250ms p95 latencies requires massive web-scale distributed systems infrastructure, crawling pipelines, and specialized information retrieval architectures.
What it would actually take: Building an independent search engine of this scale requires petabyte-scale distributed crawlers with polite IP-rotation infrastructure, document parsing and deduplication pipelines, and an inverted index distributed across thousands of NVMe-backed nodes. Serving queries under 250ms requires custom C++/Rust query engines, custom BM25/learned sparse retrieval algorithms, and high-throughput vector re-rankers. This demands millions of dollars in capital expenditure, bandwidth, and a team of seasoned distributed systems and IR engineers.
Discussion
5 comments analyzed.
Competitors mentioned: Google, Perplexity, Exa, Parallel, Brave
Concerns raised: Unclear differentiation vs Perplexity, Agent behavior with repeated rapid calls
Competitors
Other products that read as similar to this one — 285 launches clear the similarity bar, closest 8 shown.
Attention rank: #101 of 286 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 299 days after the earliest competitor.
- Crustdata - Web Search API for AI Agents · yc · 2026-02-05 · 79 upvotes · similarity 0.53
- Seltz · hn · 2026-04-20 · 5 upvotes · similarity 0.51
- Keen Code · hn · 2026-08-10 · 6 upvotes · similarity 0.49
- Web Search Agents by Nimble · ph · 2026-09-14 · 306 upvotes · similarity 0.46
- AgentSearch · hn · 2026-04-23 · 5 upvotes · similarity 0.46
- The new Firecrawl /search · ph · 2026-07-24 · 259 upvotes · similarity 0.46
- Archal: API sandboxes, built for AI agents · yc · 2026-08-22 · 60 upvotes · similarity 0.44
- 83 browser-use trajectories, visualized · hn · 2026-01-23 · 7 upvotes · similarity 0.42
Other launches for this product
- No other launches for this product.