vudovn/ag-kit

AG Kit is an agent engineering toolkit that provides a complete workspace structure for building AI agents on the Google Antigravity runtime.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 54 minutes ago
Added to GitGenius on September 1st, 2026
Created on January 14th, 2026
Open Issues & Pull Requests: 57 (+0)
GitHub issues: Enabled
Number of forks: 1,515
Total Stargazers: 8,169 (+0)
Total Subscribers: 117 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 16.0 hours
Mean response time: 29.1 days
90th percentile: 131.7 days
Tracked items: 54

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Only 11% of issues opened in the past year have been closed. Three people close 64% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 30
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 173 days
Stale 30+ days: 29
Stale 90+ days: 0

Recent activity

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

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

AG Kit is an agent engineering toolkit that provides a complete workspace structure for building AI agents on the Google Antigravity runtime.

The tool solves the problem of setting up and managing agent-based systems by installing a standardized `.agents/` workspace contract with built-in support for rules, skills, specialist agents, workflows, and persistent memory. It includes intelligent routing across twenty role definitions, orchestration commands, Model Context Protocol integration, and a native safety hook that prevents destructive filesystem operations like root deletion and drive formatting while allowing normal project cleanup. The approach bundles these capabilities into a local Antigravity plugin with validation through CI checks, regression tests, and dependency review.

Developers should choose this tool if they are building agents within a Google Antigravity workspace and need a structured, production-ready foundation. It suits projects that require persistent context management, multi-agent orchestration, and safety guardrails for tool use. The tool requires Node.js 22 or newer for repository-level tooling, Python 3.10 or newer for validators, and a trusted Antigravity workspace. The native safety hook is deliberately narrow and does not replace Antigravity's own permissions, sandboxing, or human approval workflows. The project provides a production checklist, security documentation, and migration guidance for teams adopting it.

The project maintains a substantial base of adopters who report real-world issues, with almost all open issues raised by outside users rather than the core team. Maintainers typically respond to new issues and pull requests within a day.