Firecrawl Open-source Autonomous Web Proxy Framework: Supports Multiple Models and Parallel Sub-proxies, One-click Generation of Research Tools

robot
Abstract generation in progress
ME News Report, April 17 (UTC+8), according to Beating Monitoring, Firecrawl officially open-sourced the Web Agent web proxy framework, aimed at helping developers build AI agents capable of autonomously executing "search - crawl - interaction" closed-loop tasks. The framework is based on Firecrawl's existing /agent architecture, supporting integration with Anthropic, OpenAI, or various self-hosted large models, emphasizing flexibility and self-hosting capabilities in web research scenarios. The core architecture of the framework adopts a "Plan-Act" cycle mechanism. After receiving instructions, the agent first decomposes the steps and then synchronizes tasks through "Subagents" generated in parallel within independent browser sessions. This design has clear advantages when handling large-scale concurrent tasks, such as in video demonstrations where agents can extract real-time stock data and news from multiple company websites simultaneously. For developers, this tool significantly lowers the barrier to developing web proxies. By using the command firecrawl create agent, a complete proxy template based on Next.js or Express can be quickly generated. Additionally, the framework introduces a reusable "Skill Manual" (SKILL.md), allowing developers to encapsulate complex workflows (such as specific crawling logic for Yahoo Finance) as Skills, which agents can invoke directly in subsequent tasks. In the latest version, Web Agent has upgraded its default driving model to Claude Opus 4.7 and includes a specialized skill package for the financial sector. The project is currently open-sourced under the MIT license, encouraging community contributions through Forks. (Source: BlockBeats)
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • 9
  • 6
  • Share
Comment
Add a comment
Add a comment
BluePeonyObserver
· 6h ago
Browser session management has always been a pain point; open-sourcing it could save a lot of headaches.
View OriginalReply0
FeeSwitchLobbyist
· 7h ago
What specific scenarios does the financial skills package cover? Is it for financial report scraping or real-time market data?
View OriginalReply0
Semi-MeltedIceCream
· 13h ago
Search - Crawl - Interaction Loop, isn't this just combining RPA and LLM together? The idea is quite innovative.
View OriginalReply0
Half-UnderstoodZk
· 13h ago
Compatibility with self-hosted large models is crucial; enterprise intranet scenarios finally have a solution.
View OriginalReply0
GateUser-3f3455c7
· 13h ago
From crawling tools to Agent frameworks, Firecrawl's transformation is quite aggressive.
View OriginalReply0
VinesCoiledIntoGeometricShapes
· 13h ago
How to control the task granularity when sub-agents execute in parallel? Is there a best practice document?
View OriginalReply0
NonceCollector
· 13h ago
Independent browser session isolation is well done; otherwise, multiple proxies contaminating each other's data would drive you crazy.
View OriginalReply0
NftClosetGhost
· 13h ago
Create agent with one-click template generation, very friendly for lazy developers. Try forking one this weekend.
View OriginalReply0
BetaParanoiac
· 13h ago
MIT License receives high praise, the Financial Skills Pack defaults to Claude Opus 4.7, quantitative enthusiasts are ecstatic
View OriginalReply0
View More
  • Pinned