deepseek-ai/deepseek-coder-v2

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 27 minutes ago
Added to GitGenius on September 9th, 2026
Created on June 14th, 2024
Open Issues & Pull Requests: 78 (+0)
GitHub issues: Enabled
Number of forks: 1,108
Total Stargazers: 7,007 (+0)
Total Subscribers: 80 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 26.5 hours
Mean response time: 30.7 days
90th percentile: 117.8 days
Tracked items: 25

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 4% of issues opened in the past year have been closed. Three people close 55% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 41
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 434 days
Stale 30+ days: 41
Stale 90+ days: 34

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

DeepSeek-Coder-V2 is a code intelligence model that aims to match the capabilities of closed-source alternatives through an open-source approach.

The tool addresses the need for high-quality code generation, understanding, and analysis by providing a model trained specifically for coding tasks. It operates as a downloadable model that can be run locally or accessed through an API platform, allowing developers to integrate code intelligence capabilities into their workflows without relying on proprietary services.

Developers should consider this tool if they need code generation or analysis features and prefer open-source models they can run on their own infrastructure. The project is suitable for teams building development tools, IDE integrations, or applications requiring code understanding. The README positions the tool as an alternative to closed-source code models, emphasizing its open availability and local deployment options.

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 few days.