by getopencrawl
Multiplayer context layer for coding agents. Claude Code, Codex and any MCP client.
# Add to your Claude Code skills
git clone https://github.com/getopencrawl/opencrawl-coreGuides for using ai agents skills like opencrawl-core.
See how opencrawl-core compares with popular alternatives.
opencrawl-core is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by getopencrawl. Multiplayer context layer for coding agents. Claude Code, Codex and any MCP client. It has 54 GitHub stars.
opencrawl-core's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/getopencrawl/opencrawl-core" and add it to your Claude Code skills directory (see the Installation section above).
opencrawl-core is primarily written in TypeScript. It is open-source under getopencrawl on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh opencrawl-core against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.

Agent coordination in the OpenCrawl console. Illustrative example.
OpenCrawl gives your agents a shared place to find past work and coordinate what comes next. Works with Claude Code and Codex; other MCP clients can search too.
Start a local development preview from unstable main (setup guide):
git clone https://github.com/getopencrawl/opencrawl-core.git
cd opencrawl-core
./dev/up --no-airbyte
Open http://localhost:8092, sign in with the login printed in your terminal, and paste the onboarding setup prompt into your coding agent.
For Kubernetes, use the Helm self-host kit with published images and bundled or existing services. For a single Docker host, see self-hosting. Prefer a managed workspace? Try OpenCrawl Cloud.
main is the unstable development channel. Versioned helm-v* self-host kits
are the stable release channel, scheduled weekly from fully validated commits on
main. Choose a tagged kit from Releases
for its fixed source version and image digests. Cloud consumes exact development
build versions independently of those stable distribution checks. See
release channels and validation.
Capture is opt-in. Sessions and memories are team-visible by default and can contain sensitive information. Review privacy and exclusions before enabling capture.
For agent search, prefer the advertised opencrawl_search_v1 tool, then
opencrawl_search, then search. Updated servers omit tool output and the
identified current chat by default; includeToolOutputs and
includeCurrentSession opt in. Check the response's searchContext before
assuming either exclusion, especially with older servers. See
search defaults and client activation.
Issues and pull requests are welcome. See CONTRIBUTING.md to get started and SECURITY.md to report vulnerabilities privately.
Apache-2.0. Plugins are MIT. Pre-1.0 preview.