August 2026 Summaries

Lightpanda Agent, a headless browser engine for automation, crawling, and AI agents, now uses Keenable as its default search provider when no other configured search API key is available. The agent evaluates search providers in order and selects the first with valid credentials, while its final provider must function without credentials, a requirement now fulfilled by Keenable. This integration allows agents to find relevant web pages from questions rather than requiring users to supply URLs, supporting tasks such as locating product specifications and gathering broader public opinions from multiple sources. Keenable’s Zig client was contributed upstream to Lightpanda’s zenai library, enabling search requests to run within the same process as page loading without an external wrapper or translation layer. Users can access search capabilities immediately after installing Lightpanda, while the KEENABLE_API_KEY environment variable provides higher request volume beyond the public endpoint’s per-IP limits.

NEEDLE is presented as a continuously refreshed, open-source benchmark for evaluating web search engines used by AI agents, designed to avoid the leakage, memorization, and overfitting problems associated with static benchmarks. Its queries span breaking news, finance, scholarly research, rare long-tail entities, and legal materials, drawing on live public data sources and agent search logs, with daily or hourly updates and publicly available code, tasks, and metrics. The benchmark compares Keenable with Google, Bing, Brave, Tavily, Parallel, and Exa, while also estimating an upper bound based on the best results collectively returned by all engines. The authors argue that rare, natural-language, and multi-step research queries remain particularly difficult and are most representative of real agent traffic. They further contend that independently owned search indexes are essential for improving retrieval quality, reducing latency, and providing unique coverage, whereas engines built around human engagement signals such as clicks, videos, and simplified queries may be poorly suited to agents, which search iteratively, use advanced operators, and can efficiently inspect authoritative sources.

Andrey Styskin, formerly head of Yandex’s search, AI, and cloud division, and German AI scientist Matthias Petri have launched Keenable, a startup focused on addressing an unspecified problem. The company emerged from stealth with $26 million in seed funding led by Accel, with participation from Conviction Partners and several angel investors.