mvanhorn/cli-printing-press

Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first,...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 58 minutes ago
Added to GitGenius on September 14th, 2026
Created on March 23rd, 2026
Open Issues & Pull Requests: 73 (+0)
GitHub issues: Enabled
Number of forks: 506
Total Stargazers: 4,693 (+1)
Total Subscribers: 16 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 44.3 hours
Mean response time: 7.7 days
90th percentile: 20.9 days
Tracked items: 1,645

Most active contributors

Sign in to see contributor activity.

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 97% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Almost all tracked open issues have seen activity in the last three months. Only 12% of issues opened in the past year have been closed. Three people close 95% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 71
New in 7 days: 18
Closed in 7 days: 30
Avg open age: 30 days
Stale 30+ days: 15
Stale 90+ days: 2

Recent activity

Opened in 7 days: 12
Closed in 7 days: 20
Comments in 7 days: 3
Events in 7 days: 28

Top labels

  • bug (1,030)
  • comp:generator (863)
  • priority:P2 (755)
  • source:retro (636)
  • priority:P1 (421)
  • comp:scorer (249)
  • wontfix (193)
  • enhancement (163)

Detailed Description

CLI Printing Press is a CLI generator that reads API documentation and web sources to automatically create optimized command-line interfaces designed for AI agents.

The tool solves the problem of AI agents wasting tokens and time navigating poorly designed CLIs or hunting through documentation. It works by analyzing official API docs, studying popular community CLIs and MCP servers, and scraping undocumented APIs from the web. It then applies patterns proven effective for agent efficiency—local SQLite caching, compound commands that combine multiple API calls into single queries, and agent-native flag design—to generate token-efficient Go CLIs, Claude Code skills, and MCP servers for any API or website.

Adoption suits teams building AI agent workflows who want to reduce token spend and latency when agents interact with external services. The tool is particularly valuable when you need compound queries that no single API can answer, or when you want to stitch together multiple data sources into one efficient command. It works best with Claude Code as the primary agent interface, though it also supports Codex with separate installation flags. The tool generates ready-to-install CLIs across a catalog covering various API categories.

The project shows active development with regular updates to the generator and skill system. The maintainers actively expand the catalog of printed CLIs available for immediate use. Installation and verification workflows are documented with specific guidance for different agent platforms. The tool maintains compatibility requirements and provides troubleshooting paths for common setup issues.