OpenClaw is a personal AI assistant designed to run locally on users' devices and integrate with existing messaging platforms. What began as a personal experiment by Peter Steinberger rapidly attracted a global community. However, the project's popularity has introduced unprecedented challenges in managing contributions and ensuring security.
Maintainers report that the traditional pull request process has been transformed. Steinberger noted, "I don't even call them pull requests. I call them prompt requests," referring to the thousands of contributions—many generated by automated AI tools—that pour in. Josh Lehman, a contributor from Martian Engineering, observed, "There were some contributors that had multiple hundreds of pull requests running these sort of automated software factories that were just mining everything for issues."
Despite the flood, the team is committed to keeping the project accessible. They aim to welcome first-time open-source contributors, non-developers with specific problems, and people using AI agents to help, while still maintaining quality through human review. The project's maintainers, including Brad Groux (CEO of Digital Meld), Josh Avant (OpenClaw Foundation), Sally O'Malley (Principal software engineer at Red Hat), Val Alexandar (OpenCoven), and Vincent Koc (Chief architect, OpenClaw Foundation), participated in the interview.
A central concern is software supply chain risk. With an AI agent capable of executing code and accessing user data, the project must balance powerful capabilities with robust security. The maintainers are drawing on lessons from the GitHub Secure Open Source Fund, which helps projects address such vulnerabilities. They emphasize the importance of connecting with other maintainers facing similar challenges to share best practices.
The GitHub Blog feature outlines ten lessons from the conversation, though only the first three—covering how AI changed contributions and community—are detailed in the article. These include recognizing the shift from pull requests to prompt requests, keeping the door open for new contributors while managing volume, and building a culture of trust and effective code review.