xai-org/grok-prompts

Prompts for our Grok chat assistant and the `@grok` bot on X.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 1 hour ago
Added to GitGenius on September 15th, 2026
Created on May 15th, 2025
Open Issues & Pull Requests: 94 (+0)
GitHub issues: Enabled
Number of forks: 503
Total Stargazers: 4,475 (+0)
Total Subscribers: 140 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 5.8 hours
Mean response time: 16.0 days
90th percentile: 34.8 days
Tracked items: 39

Most active contributors

Sign in to see contributor activity.

How this project is maintained

100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Three people close 100% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 67
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 376 days
Stale 30+ days: 63
Stale 90+ days: 60

Recent activity

Opened in 7 days: 1
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Detailed Description

Grok-prompts is a repository of system prompts used by the Grok chat assistant and related features across X and grok.com.

The repository makes public the system prompts that guide Grok's behavior across different product contexts. These prompts define how the assistant responds to users, handle safety considerations, and support specific features like code generation and content explanation. The prompts are maintained in Jinja template format and plain text, allowing the team to version control and regularly update the instructions that shape the model's outputs.

Developers working with the xAI API or studying how large language models are prompted in production will find this repository valuable for understanding the actual instructions used to govern Grok's behavior. The collection includes prompts for different model variants—including Grok 4, Grok 3, and specialized versions like code-focused and fast inference models—as well as prompts for specific product features such as the Explain button on X and the Grok bot. This transparency into production prompting strategies offers insight into how instruction design differs across model sizes and use cases.

The repository shows consistent maintenance with regular updates to system prompts across multiple model versions and product features. The team actively refines prompts, as evidenced by versioned files tracking iterations of the Grok 4 system prompt and the introduction of new prompt variants for different model capabilities like thinking and non-thinking modes.