Open sourceTypeScript · ≈205k stars · AGPL-3.0
Firecrawl
Turn websites into clean markdown for LLMs and agents.
Firecrawl crawls, scrapes and converts entire sites into LLM-ready markdown with structure — the go-to ingestion primitive for agent context pipelines.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- User reportsSelf-hostable; one user runs their own instance for agents and sees request failure rates consistently under 2%.[1][2]
- DocsClear credit pricing: scrape, crawl and map cost 1 credit per page, the free tier gives 1,000 credits a month, and paid plans run from $19 to $749 a month.[1]
- User reportsPractitioners rank it among the solid paid options for agent web search and scrape, alongside Exa, Tavily and Parallel.[1][2]
- MetadataVery popular (about 197k stars), and it also publishes spin-off libraries such as pdf-inspector.[1][2]
Cons
- MetadataAGPL-3.0: running a modified version as a network service obliges you to release your source.[1]
- DocsSelf-hosting defaults to bundled Playwright (Fire-engine must be configured separately), the API is unauthenticated by default, and the Compose file is "not a production architecture."[1]
- DocsStructured JSON output costs about 5 credits per page instead of 1, and Hobby, Standard and Growth credits don't roll over.[1]
- User reportsSite operators complain about its traffic (one says Firecrawl customers caused 95% of a traffic overcharge), and a user notes it logs requests.[1][2]
- Best for
- Agent builders who need reliable web-to-markdown scraping and crawling via an API, or an AGPL self-host.
- Watch out for
- Budget for the JSON-extraction multiplier, and check whether AGPL obligations apply if you modify and host it.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
Activity
- Last push
- · yesterday
- Latest release
- v2.11.0
· 5mo ago - Last 90 days
- 0 releases
v2.11.0Firecrawl v2.11.0
· 5mo agoFirecrawl v2.11.0 Improvements Firecrawl Research Index — Added a specialized index for agentic AI/ML research: search across 3M+ arXiv papers and the GitHub code behind them (issues, merged PRs, and READMEs, refreshed daily), fetch a paper's details or related work, and check…
v2.10Firecrawl v2.10
· 6mo agoFirecrawl v2.10 Improvements /parse endpoint — Upload local files (PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, HTML) up to 50 MB and get back clean, LLM-ready Markdown, JSON, or a summary. Tables and reading order are preserved, with full Zero Data Retention support for enterprise…
- · 7mo ago
Firecrawl v2.9.0 Improvements Browser Interaction via /interact endpoint — Scrape a page, then call /interact to take actions on it — click buttons, fill forms, navigate deeper, or extract dynamic content. Describe what you want in natural language via prompt, or write…
- · 9mo ago
v2.8.0 Firecrawl v2.8.0 is here! Firecrawl v2.8.0 brings major improvements to agent workflows, developer tooling, and self-hosted deployments across the API and SDKs, including our new Skill. Parallel Agents for running thousands of /agent queries simultaneously, powered by…
- · 11mo ago
Firecrawl v2.7.0 is here! ZDR Search support for enterprise customers. Improved Branding Format with better detection. Partner Integrations API now in closed beta. Faster and more accurate screenshots. Self-hosted improvements And a lot more enhacements, check it out below! New…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
The team behind it
San Francisco, CA · Est. 2023
Turn websites into clean, LLM-ready markdown.
Firecrawl (the team formerly known as Mendable, now renamed after the product) crawls, scrapes and structures the web for agents — the de-facto 'eyes' of many research and automation harnesses. Core is open source.
Neighbours on the workbench
Python · ≈150k stars · MIT
langchain-ai/langchain
The most widely used framework for LLM-powered applications.
Maintained by LangChain
langchain-openai==1.8.5releasedGo · ≈94k stars · Apache-2.0
infiniflow/ragflow
Agent-native RAG engine and context infrastructure.
Maintained by infiniflow
Python · ≈88k stars · Apache-2.0
unclecode/crawl4ai
Open-source, LLM-friendly web crawler.
Maintained by Unclecode
v0.9.6releasedConnections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
