commandcodeai/command-code

Command Code AI — the best coding agent for open models.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 5 minutes ago
Added to GitGenius on September 17th, 2026
Created on December 20th, 2017
Open Issues & Pull Requests: 312 (+0)
GitHub issues: Enabled
Number of forks: 350
Total Stargazers: 4,003 (+0)
Total Subscribers: 71 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 17.1 hours
Mean response time: 4.1 days
90th percentile: 11.4 days
Tracked items: 487

Most active contributors

Sign in to see contributor activity.

How this project is maintained

About 15% of issues opened in the past year have never received a reply. 99% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 18% of tracked open issues have had no activity in three months. Only 47% of issues opened in the past year have been closed. Three people close 63% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 308
New in 7 days: 52
Closed in 7 days: 21
Avg open age: 52 days
Stale 30+ days: 171
Stale 90+ days: 55

Recent activity

Opened in 7 days: 47
Closed in 7 days: 20
Comments in 7 days: 17
Events in 7 days: 43

Top labels

  • windows (52)
  • p2 (49)
  • p1 (40)
  • p0 (20)
  • /design (5)
  • desktop (2)
  • non-issue (2)
  • todo (1)

Detailed Description

Command Code is a coding agent that learns your coding taste.

The tool addresses the problem of coding agents producing output misaligned with individual developer preferences and team standards. It works by building full-stack projects, shipping features, fixing bugs, writing tests, and refactoring code while continuously learning from your accept, reject, and edit decisions. Each interaction becomes a signal that shapes a personalized taste profile, which the tool uses to enforce the invisible logic of your coding choices through its taste-1 model. The tool operates in interactive mode with slash commands, input modes, and file path autocomplete, and allows teams to share taste profiles portably via command-line operations.

Developers should choose this tool if they want an AI coding agent that adapts to their specific coding style rather than applying generic patterns. It suits projects where consistency with existing code conventions matters and where teams benefit from shared coding standards. The tool is installable via npm and can be started directly in a project directory, with documentation covering quickstart, interactive mode features, and practical workflows for everyday tasks.

Almost all open issues are raised by outside users rather than the core team, indicating a substantial base of adopters reporting real-world use. Maintainers typically respond to new issues and pull requests within a day.