What it does
Core capabilities at a glance
- Claude Code
- Codex
- Deepseek
- Gemini CLI
- Macos
Deep dive
The full breakdown - performance, comparisons, and setup
magpie
magpie is an agent framework - Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
Overview
Claude Code on Kimi. Codex on DeepSeek. Gemini CLI on GLM. OpenCode on your ChatGPT plan. Switch any of them from the menu bar. One local gateway serves them all, and when a quota runs out, it quietly moves on to the next account.
Each agent keeps its model in its own file, in its own format, with its own keys and base URLs. A subscription you pay for works in one agent and nowhere else. magpie puts all of that behind one app and one local gateway:
- Pick any model for any agent from one list. magpie edits the one key that matters in the agent's own config. - Use one provider everywhere: an API key, a local model, or the Claude, ChatGPT, Copilot, Gemini or Grok plan you're signed in to. - Keep going when a quota runs out: a routing group moves to the next account or model, and the agent never sees the error.
It's for you if you use more than one agent, more than one provider, or more than one account. If you use one agent on its vendor's own plan and that's enough, you don't need it.
Runs on macOS, Windows and Linux (menu bar app, window, TUI, web UI and CLI), in Docker, and on Termux.
magpie is open-source, written primarily in Go, with 16,074 GitHub stars under the MIT license. The latest release is v0.1.1290 (2026-10-18).
Key capabilities
From the project's documentation:
- Pick any model for any agent from one list. magpie edits the one key that matters in the agent's own config.
- Claude: drives the real local claude binary and bridges your agent's tools over MCP
- Codex / ChatGPT: your ChatGPT plan's models, in every other agent
- GitHub Copilot, Gemini (Code Assist), Antigravity, Grok (SuperGrok) and more
- Any OpenCode auth plugin or pi package from npm
- WSL: on Windows, agents inside WSL distros are wired too, and their sessions counted.
Install
A quick way to get started (always check the official docs for the latest):
go install github.com/yetone/magpie@latestHow it fits a local-AI stack
magpie runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:
Sources
- Source code & docs: yetone/magpie
- Official website: https://usemagpie.ai
Stats from GitHub, 2026-10-19.
Frequently asked
Quick answers to common questions
What is magpie?
magpie is a agent-framework tool for local AI workloads. Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
Is magpie free and open source?
Yes, magpie has 16,074 GitHub stars and is licensed under MIT. You can self-host it for free on macos, linux, windows, docker, web.
What platforms does magpie support?
magpie runs on macos, linux, windows, docker, web.
What hardware do I need for magpie?
The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. magpie has 16,074 GitHub stars and an active community.
Does magpie support GPU acceleration?
magpie supports GPU acceleration via CUDA, Metal, or Vulkan depending on your platform. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.
What are the best alternatives to magpie?
Popular alternatives include other agent-framework tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.
How much does magpie cost?
magpie is free-open-source. It is completely free and open source to self-host.
Pairs well with
Complementary tools, models, and hardware