- Gemini CLI gets Github Actions version with full integration into your repo
- It’s an autonomous agent and collaborator all in one
- There are free tiers with plenty of requests
Just weeks after Google launched Gemini CLI, its open source AI agent to integrate Gemini into a user’s terminal, the company has partnered up with Microsoft-owned GitHub to launch Gemini CLI GitHub Actions.
The company described Gemini CLI GitHub Actions as a free, beta-stage AI teammate that lives within a GitHub repo, capable of acting as an autonomous agent and an on-demand collaborator.
Gemini CLI GitHub Actions can auto-label, prioritze and filter new issues, provide instant feedback on quality, style and correctness, and collaborate on-demand with the @gemini-cli command to write tests, implement fixes, brainstorm and more.
GitHub teams up with Google to bring Gemini CLI to users
Speaking about how the tool was built, Senior Software Engineer Jerop Kipruto and Senior Director Ryan J. Salva explained: “When community members noticed our new workflows, they asked us to share what we’ve built.”
“Triggered by events like new issues or pull requests, it works asynchronously in the background, using the full context of your project to automatically handle tasks,” the software workers explained in a blog post.
Google also noted its commitment to enterprise-grade security, noting that Vertex AI and Gemini Code Assist Standard/Enterprise users can use Google Cloud’s Workload Identity Federation (WIF) to eliminate the need for long-lived API keys, tightening security by reducing the risk of compromise.
The GitHub Actions version of Gemini CLI is available to try in beta today – Gemini Code Assist Free Tier users get 60 requests per minute and 1000 requests per day, but other account types have different quotas.
In a separate post before GitHub’s involvement, Google boasted the Gemini command line interface (CLI) tool gives developers the “most direct path from your prompt to [its] model.”