yetone/magpie

Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.

View on GitHub ↗Jump to charts ↓Open shareable report →

yetone/magpie has 14k+ stars and 1k+ forks on GitHub, is written in Go, and was last pushed on Oct 17, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 18 minutes ago
Added to GitGenius on September 30th, 2026
Created on September 23rd, 2026
Open Issues & Pull Requests: 1,014 (+8)
GitHub issues: Enabled
Number of forks: 1,044
Total Stargazers: 14,661 (+78)
Total Subscribers: 18 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 0.8 hours
Mean response time: 2.7 hours
90th percentile: 4.1 hours
Tracked items: 1,697

How this project is maintained

About 10% of issues opened in the past year have never received a reply. 83% 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 58% of issues opened in the past year have been closed. Three people close 70% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 935
New in 7 days: 1,182
Closed in 7 days: 553
Avg open age: 1 days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 1,085
Closed in 7 days: 518
Comments in 7 days: 2,209
Events in 7 days: 5,054

Top labels

  • bug (4)
  • enhancement (2)
  • question (1)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Magpie is a menu bar application that centralizes model selection across multiple AI agents on your machine.

The problem magpie solves is the fragmentation of AI agent configuration: each tool like Codex, Claude Code, and Gemini CLI maintains its own settings in different formats and locations. Rather than editing config files scattered across your system, magpie provides a single interface where you can see all agents and their assigned models, then click to switch any of them. The tool runs a local gateway that translates between different API standards—OpenAI chat completions, OpenAI Responses, and Anthropic Messages—so all agents can point to one endpoint and access models from any provider you've connected.

Magpie suits developers who work with multiple AI coding agents and want to experiment with different models without manual configuration editing. It is particularly valuable if you use agents from different vendors and want to share subscriptions across them: if you sign into Claude Code or ChatGPT, other agents can use those credentials through the gateway without storing or copying keys. The tool preserves your existing config files exactly as they are, touching only the specific values you change and maintaining comments, ordering, and indentation. It works on macOS, Linux, and Windows, with a small binary footprint and multiple interfaces: a menu bar panel, a desktop window, a terminal UI, and a plain CLI. The gateway supports a wide range of providers including Anthropic, OpenAI, Gemini, DeepSeek, Kimi, and many others, with real-time model lists fetched from vendors rather than hardcoded.

The project shows consistent maintenance with regular updates addressing user-reported issues and feature requests. Development includes active refinement of the gateway's API translation layer and expansion of supported providers. The tool receives ongoing improvements to its configuration handling and model discovery mechanisms.