Firecrawl launches Prometheus web agent

// 3h agoPRODUCT LAUNCH

Firecrawl launches Prometheus web agent

Prometheus by Firecrawl is an experimental agent that writes and runs verified TypeScript scraping code based on natural language descriptions. The generated collectors can execute locally or via a managed hosted scheduler that automatically self-heals as target website layouts change.

// ANALYSIS

Automating code generation for scrapers via natural language and including self-healing features tackles the biggest pain point of web scraping—maintenance and brittleness. However, the system's overall viability relies heavily on the quality and reliability of its automated self-healing when target site structures change significantly.

* Converts natural language prompts directly into verified TypeScript scraping scripts.

* Offers automated self-healing to update scraping selectors and code as websites change.

* Integrates directly into workflows via HTTP APIs, CLI, MCP support, or as a coding skill.

* Supports both local self-hosted execution and a fully managed hosted scheduler.

// TAGS

devtoolartificial-intelligenceweb-scrapingagentfirecrawl

DISCOVERED

3h ago

2026-06-13

PUBLISHED

8h ago

2026-06-13

RELEVANCE

8/ 10

AUTHOR

[REDACTED]

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE33m ago

Vercel Labs' open-source AI browser automation tool, agent-browser, has reached one million weekly downloads on npm, with developer Chris Tate sharing insights on optimizing startup performance.

Chris Tate announced that Vercel Labs' agent-browser, an open-source headless browser automation tool tailored for AI agents, has reached 1,000,000 weekly downloads on npm. Tate noted that a temporary download dip lined up with a transition from running via `npx` to a global install command (`npm i -g`). Implementing a global installation path reduced the tool's startup time to approximately 1 millisecond, which is crucial for low-latency agentic workflows.

MODEL45m ago

Anthropic has launched Claude Fable 5, its latest flagship AI model featuring a 1 million token context window designed for complex agentic workflows and software engineering tasks.

Anthropic has introduced Claude Fable 5, a new flagship AI model optimized for long-running, goal-directed agentic workflows and software engineering tasks. The model boasts a 1 million token context window and is equipped with hard guardrails that fallback to Opus 4.8 for sensitive queries, although access has recently been suspended globally due to U.S. government export control directives.

OPEN SOURCE58m ago

CUA-Gym automates the generation of verifiable reinforcement learning training environments and datasets for computer-use agents to bypass the training data bottleneck.

CUA-Gym is an open-source pipeline and dataset developed by XLang AI to scale Reinforcement Learning with Verifiable Rewards (RLVR) for Computer-Use Agents (CUAs). It addresses the training data bottleneck by co-generating task instructions, environment states, and Python reward functions using a multi-agent Generator-Discriminator-Orchestrator architecture. The framework is paired with CUA-Gym-Hub, which hosts 98 high-fidelity, self-contained mock web applications designed with state injection and session isolation. This setup allows parallel RL training sessions on shared backends without resource interference, producing over 32,000 verified RLVR training tuples that significantly improve CUA performance on benchmarks like OSWorld and WebArena.