Firecrawl 发布 Firecrawl Local:本地抓取性能大幅提升
做智能体的朋友可以看下,Firecrawl 把抓取整套搬到了本地,Rust 重写后比自托管快 37 倍,空闲内存才 11 MB,MCP 和 SDK 直接兼容,想省 API 费用或在意数据隐私的可以试试。
Firecrawl 发布 Firecrawl Local,将整个仓库重构为可完全本地运行的抓取方案,以 Rust 重写抓取原语。官方给出的对比数据是:相比自托管版本快 37 倍,内存占用降低 230 倍,空闲时仅占 11 MB,且 100% 开源。
Firecrawl Local 开箱即用,兼容 Firecrawl 现有的全部 MCP 接口与 SDK,开发者可以把抓取能力直接嵌进本地运行的智能体工作流,不再依赖云端 API 或远程自托管服务。轻量的内存占用让它在笔记本等低资源环境也能跑起来。
抓取是智能体获取网页数据的基础环节,本地化方案能降低成本和网络延迟,也减少数据外发带来的隐私顾虑。对需要高频抓取、且已有本地智能体部署的开发者来说,这是一条替代云端抓取服务的路径。
Introducing Firecrawl Local. We rebuilt the Firecrawl repo so agents can scrape locally. - 37x faster rust based scrape primitive (vs self-hosted) - 230x less memory (11 MB idle) - 100% open source Compatible out of the box with all of our MCP & SDKs. https://t.co/02y6pGZEMz
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Firecrawl, MCP and tools, agents, open-source models.
Source attribution: curated from Firecrawl (@firecrawl_dev).