返回全部资讯
Rohan Paul (@rohanpaul_ai)T2·开发与工程

Eon 推出 Yukon 无服务器数据引擎 面向智能体数据层

原标题:A lot of the useful agent infrastructure right now is being built below the model, in the data layer...
58AI 研判分

Eon 发布 Yukon 无服务器数据引擎,将事件数据摄取、清洗并压缩为自有存储桶中的开放 Iceberg 表,智能体通过 MCP 读取表上下文。官方公开基准显示其计算开销比 Spark 低 4 倍、比 Flink 低 7 倍,核心思路是让智能体在查询前先了解表结构以减少无效扫描。

报道正文

Rohan Paul (@rohanpaul_ai) · 2026-11-05 17

A lot of the useful agent infrastructure right now is being built below the model, in the data layer.

Agents query the same tables all day, and every request needs the newest rows plus the full history.

@Eon_io_ built Eon Yukon for that pattern. It ingests, cleans and compacts events into open Iceberg tables in your own bucket, and agents read each table’s context over MCP. In Eon’s public benchmark, it used 4x less compute than Spark and 7x less than Flink.

Thats expected because, an agent that knows what a table holds before it queries it can skip a lot of wasted scans.

↳ 引用 @OfirEhrlich (Ofir Ehrlich): What I'm seeing across the industry right now is that the biggest bottleneck to AI adoption isn't model capabilities. It's data infrastructure.

Today, we're expanding the Eon Data Foundation with the launch of Eon Yukon, a new serverless data engine purposely built to change that.

AI agents need fresh, contextualized data to act. Specialized models need a continuous feed of data and feedback to improve. Both are still served by a stack, an architecture, and methods built for dashboards:

-Spark and Flink clusters sized for peak, plus compaction jobs to keep tables usable.

-A pipeline and a copy for every consumer, staged bronze to silver to gold.

-Hand-written jobs, wired together by an orchestrator and kept alive by specialists.

The result: shipping data is complicated, risky, and expensive. While coding agents ship apps in hours, they rarely build or run data pipelines. The data is too volatile, and a mistake costs too much.

With Yukon, data moves from ingestion to processing to serving in one continuous flow, without the infrastructure and pipelines traditionally required to connect them.

Events become compacted, sorted, deduplicated Iceberg tables within seconds.

Real-time aggregations run inline, with fully managed state. Agents and applications can access fresh data with sub-millisecond latency through a Redis-compatible API or through our SQL and spark compatible query engine.

Beyond moving and serving data, Yukon makes it continuously understandable - Live column-level statistics, accessible through MCP, give agents visibility into the data. Built-in monitoring, sampling, and data minimization help teams maintain control.

At 1M events/sec and equal freshness, Yukon used 4x less compute than Spark and 7x less than Flink. The benchmark is public: run it yourself with Eon’s ingest-bench.

This is another major step toward our vision of an Autonomous Data Foundation for the AI era, built to both protect enterprise data and unlock its full potential.