# yetone/magpie > A menu-bar utility for macOS/Linux/Windows that lets you pick the model for each AI agent (Codex, Claude Code, Gemini CLI, etc.) and runs a local gateway translating OpenAI and Anthropic APIs between agents and providers. - Magnitude: 5.1 out of 10 — Early signal - Stars: 145 total · +0 stars today, ≈ 124 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Go · License: MIT · Created: 2026-09-23 · Last push: 2026-09-23 - GitHub: https://github.com/yetone/magpie · Homepage: https://usemagpie.ai · Page: https://gitnova.dev/en/r/yetone/magpie ## Useful for - Switch Claude Code to a Kimi model without hand-editing settings.json - Expose a ChatGPT (Codex) subscription as a provider for other agents via the local gateway - Save a profile of all agents' settings and switch between them in one move ## Why it’s here - 0 stars so far today, about 124 expected by the end of the day. - The spike has held for 2 days in a row — not a one-off blip. - The repository is 1 day old and already has 145 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - Top new repositories this week: #130. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 4 - Issues and pull requests: 0 - Watchers: 0 - Average over the last week: 137 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 42 ## Stars per day, last 5 days (oldest → newest, today is partial) 2026-09-20 … 2026-09-24: 0, 0, 0, 150, 0 ## Spotted in now - Top new repositories this week: #130 ## Similar by description 1. **decolua/9router** — 2.8 · Steady · AI agents · JavaScript · +0 stars today, ≈ 51 by evening Local router for AI coding tools: connects Claude Code, Cursor, Cline and other CLIs to 40+ providers, auto-fallbacks between them, and compresses tool output to save tokens. Full card: https://gitnova.dev/en/r/decolua/9router.md 2. **0xSero/harness-bridge** — 0.7 · Steady · AI agents · TypeScript · +0 stars today, ≈ 1 by evening A bridge that points any coding harness (Claude Code, Codex, OpenCode, Copilot, etc.) at any OpenAI/Anthropic/Responses-compatible inference endpoint: pick a served model, click a harness, and it launches already connected, without… Full card: https://gitnova.dev/en/r/0xSero/harness-bridge.md 3. **yudaprasetya007/routeVSCODE** — 0.0 · Quiet · AI agents · JavaScript · +0 stars today, ≈ 0 by evening A VSCode extension and local proxy that let you switch the AI model in GitHub Copilot Chat with one click, without reloading the window. It works through the 9Router gateway and supports 40+ providers (OpenAI, Anthropic, Gemini, DeepSeek,… Full card: https://gitnova.dev/en/r/yudaprasetya007/routeVSCODE.md 4. **lidge-jun/opencodex** — 3.2 · Steady · AI agents · TypeScript · +0 stars today, ≈ 97 by evening Local proxy server that translates Codex's Responses API into other LLM protocols (Claude, Gemini, Grok, DeepSeek, Ollama, etc.), supporting streaming, tool calls, reasoning tokens and images. It also manages a ChatGPT account pool for… Full card: https://gitnova.dev/en/r/lidge-jun/opencodex.md 5. **OnlistTeam/ai-manager** — 3.5 · Early signal · Developer tools · Rust · +0 stars today, ≈ 40 by evening A local-first desktop app for installing, updating, and configuring AI coding CLI tools (Claude Code, Codex and others), and managing their API endpoints, Skills, MCP connections, and prompts without hand-editing config files or PATH. Full card: https://gitnova.dev/en/r/OnlistTeam/ai-manager.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-24 02:08 UTC, updated every 30 minutes.