zgsm-ai/costrict

Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 42 minutes ago
Added to GitGenius on September 15th, 2026
Created on April 10th, 2025
Open Issues & Pull Requests: 10 (+0)
GitHub issues: Enabled
Number of forks: 202
Total Stargazers: 4,432 (+0)
Total Subscribers: 76 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 13.5 hours
Mean response time: 13.3 days
90th percentile: 41.9 days
Tracked items: 82

Most active contributors

Sign in to see contributor activity.

How this project is maintained

About 7% of issues opened in the past year have never received a reply. Work labelled "bug" is answered fastest, typically in about 4 hours, while "enhancement" waits about 3 days. 87% of issues opened in the past year have been closed, leaving a working backlog. Three people close 89% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 6
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 100 days
Stale 30+ days: 4
Stale 90+ days: 3

Recent activity

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

Top labels

  • enhancement (36)
  • bug (31)
  • gemini-cli (1)
  • status/need-issue (1)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Costrict is a VS Code extension that provides AI-assisted coding capabilities including code completion, code review, and agentic workflows for enterprise development teams.

The tool addresses the need for AI-powered development assistance that prioritizes code quality and enterprise requirements. It integrates multiple AI model providers including Claude, Deepseek, Gemini, GLM, and Minimax, allowing teams to choose their preferred backend. The extension operates within the VS Code environment and offers three primary modes: AI Completion for suggesting code as developers type, AI CodeReview for analyzing code quality and suggesting improvements, and AI Agent for autonomous coding tasks that can work across multiple files and implement features with minimal human direction.

Teams evaluating Costrict should consider it if they need enterprise-grade AI coding assistance with flexibility in model selection and a focus on code quality over raw speed. The tool suits organizations that want to integrate AI coding into their existing VS Code workflows without switching editors or adopting entirely new development environments. It is particularly relevant for shops already invested in specific AI model providers, since the multi-model support means teams are not locked into a single vendor's offerings.

The project shows active development with regular updates to support new AI models and maintain compatibility with VS Code's evolving extension ecosystem. Work spans multiple AI provider integrations, suggesting ongoing effort to keep the tool current with the rapidly changing landscape of available models. The codebase is maintained in TypeScript, indicating a focus on type safety and maintainability for a tool that will be extended and modified over time. The project maintains a public homepage separate from the repository, reflecting an orientation toward end-user adoption and documentation beyond what the GitHub repository alone provides.