Current context
for coding agents
Give your coding agent the Developer Index plus package, repo and container data
through Firecrawl Alexandria on one API key.
companies of all sizes
Perfect for
AI coding agent builders
Ground Claude Code, Codex, Cursor or your own agent in current docs and changelogs so generated code matches the library version you run.
Platform and DevEx teams
Give internal agents one approved path to package metadata and licenses across registries, plus release notes from source repositories.
Security and supply chain
Check a dependency's latest version, license and source repository, and read its open issues before it lands in a lockfile.
Developer tool startups
Ship features that read release notes, package metadata and container tags without building and maintaining each integration.
Migration and upgrade work
Pull the migration guide passage and the related issues for a major version bump so the agent plans the upgrade from the source.
Docs and DevRel teams
See how developers use your library in issues and PRs, and which questions your docs leave unanswered.
Developer IndexDocs, repos and issuesPackage registriesVersions and licenses
GitHubReleases and issuesDocker HubImage tags and architectures
- registry
- npm
- package
- zod
- license
- MIT
- source
- github.com/colinhacks/zod
- migration_guide
- matched passage
How it works
Search docs, repos and issues with the Developer Index
The Developer Index is Firecrawl's own index of READMEs, docs, pull requests, issues, OpenAPI specs and agent skills. A query returns matched passages, so the agent reads only the paragraph that answers its question.
Check versions and licenses across package registries
One Alexandria tool covers the main JavaScript, Python, Rust and Java package registries: latest version, license, project links, version history and download counts. Agents confirm a package exists and what it is licensed under before they add it.
Read releases, issues and contributors
Alexandria returns public repositories, releases, issues, labels and contributors as structured records. Pair a release with its open issues to decide whether an upgrade is safe.
Pick the right container image
Search the public container image catalog by name, architecture or category, then read an image's tags, digests and known vulnerability counts. Agents writing Dockerfiles or CI config choose a tag that exists for the target architecture.
Fall back to the live web when a source is missing
The same API key runs Firecrawl Search, Scrape and Crawl, so when an answer only lives on a blog post or a vendor's docs site the agent fetches that page as clean Markdown without switching tools.
Coding agents find more with the
Firecrawl Developer Index.
All numbers are from the DevDex benchmark: 1,179 developer retrieval tasks (393 repository, 400 issue-to-fix, 386 documentation) driven by Claude Opus 4.8 through the same harness with one search tool and ten results per call. Each system is called with its default configuration, and a run that returns nothing counts as a miss. The full harness and a 594-item public sample are open source in the firecrawl/benchmark-devdex repo.
· Figures from the run of Aug 21, 2026
Easily connect with your
AI agents
Copy and paste this into your AI agent.
Run npx -y firecrawl-cli@latest init --all --browser. Use my existing Firecrawl login or help me log in. Read the installed skills before running queries.
curl -s https://firecrawl.dev/agent-onboarding/SKILL.mdPeople love
building with Firecrawl
Firecrawl is an open-source framework that takes a URL, crawls it, and conver..."
Upload a CSV of emails and..."
Firecrawl is an open-source framework that takes a URL, crawls it, and conver..."
Upload a CSV of emails and..."
How Firecrawl compares to alternatives
| Feature | Firecrawl | Building each API integration | Generic web scrapers | LLM web search alone |
|---|---|---|---|---|
| One API key across 100+ providers | Yes | No | No | No |
| Structured records from official sources | Yes | Yes | No | No |
| Matched passages from docs, issues and PRs | Yes | No | No | No |
| Free tool discovery with listed prices | Yes | No | No | No |
| Live web search and scraping on the same key | Yes | No | Yes | Yes |
| Works through MCP, CLI and SDKs | Yes | No | No | Yes |
| Provider terms managed in one dashboard | Yes | No | No | No |
| Source URL kept with every record | Yes | Yes | Yes | Yes |
| No per-provider auth, pagination or schema work | Yes | No | No | No |
Tutorials & guides
Introducing Firecrawl Developer Index: A Specialized Index for Coding Agents
READMEs, docs, issues, and PRs for coding agents: 70M+ artifacts, refreshed continuously, with most sources refreshed daily.
Read tutorial →
How to Give AI Coding Agents Up-to-Date Documentation
Why LLMs write code against last year's APIs, and how to give Cursor and Claude Code current, version-specific documentation.
Read tutorial →
Firecrawl Alexandria and the Developer Index Are Now in ChatGPT and Codex
The Firecrawl plugin gives ChatGPT and Codex access to Firecrawl Alexandria: 100+ official data providers plus Firecrawl's own Research, Developer, and Government indexes.
Read tutorial →
Watch & learn
Introducing Alexandria - The 113M-Source Library Your AI Agent Needs
Firecrawl
A walkthrough of Firecrawl Alexandria: how an agent finds the right data provider, checks what it costs and pulls live, structured records in one call.
Watch on YouTubeFrequently
asked questions
Flexible pricing
Free Plan
Hobby
StandardMost popular
Growth
Scale Plans
High-volume plans for teams that need more power and dedicated support. Get access to higher rate limits, more concurrent browsers, and priority support. Scale checks out instantly, no sales call needed.
Need more? Contact us