Runs on: Windows WSL2 macOS Linux Docker
| # | Shot | Project | Stars | Plugs into | What it does |
|---|---|---|---|---|---|
| 1 | open-codesignOpenCoworkAI/open-codesign | 8,143 | Claude CodeClaude / AnthropicCodex / OpenAIGemini / GoogleLocal / Ollama | Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT. winget install OpenCoworkAI.OpenCoDesign | |
| 2 | minuet-ai.nvimmilanglacier/minuet-ai.nvim | 1,440 | Claude CodeClaude / AnthropicCodex / OpenAIGemini / GoogleLocal / Ollama | (1.3k ⭐) - Code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama git clone https://github.com/milanglacier/minuet-ai.nvim.git | |
| 3 | slotstreamcarloslfu/slotstream | 639 | Claude CodeClaude / AnthropicCodex / OpenAILocal / Ollama | Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex. curl -fsSL https://raw.githubusercontent.com/carloslfu/slotstream/main/install.sh | sh | |
| 4 | mimo2codex7as0nch/mimo2codex | 627 | Codex / OpenAILocal / Ollama | 让最新版 OpenAI Codex CLI / Codex 桌面端接入主流大模型的本地代理(新增mac/win包支持，后台运行，开机自动重启)。内置 小米 MiMo V2.5/DeepSeek V4 Pro，并提供通用 provider 机制，**OpenAI Chat Completions 兼容**（Qwen / GLM / Kimi / 本地 vLLM / Ollama / LM Studio …）或**原生 Responses API**（OpenAI 自家）的上游接到新版 Codex。把 Codex 的 Responses API 实时翻译成上游的 Chat Completions API，按客户端发的 `model` 字段在 provider 之间自动路由. npm install -g mimo2codex # 1. install (Node ≥ 18) | |
| 5 | Sniprixinhahaha/snip | 350 | Claude CodeClaude / AnthropicMCPLocal / Ollama | by rixinhahaha - A visual whiteboard between you and your agent: Claude renders diagrams, HTML, or UI components through Snip instead of describing them in text, you approve or annotate directly on the output (circle, arrow, note), and the agent gets structured feedback and iterates. Works via CLI or MCP, doubles as a full local screenshot/annotation app with on-device AI organization (Ollama), an brew install --cask rixinhahaha/snip/snip | |
| 6 | backdoorajsai47/backdoor | 301 | Claude CodeClaude / AnthropicCodex / OpenAILocal / Ollama | Run Claude Code against any AI provider. DeepSeek, Groq, Ollama, OpenRouter — your call. git clone https://github.com/ajsai47/backdoor | |
| 7 | Opencode Models Discoveryyuhp/opencode-models-discovery | 199 | opencodeCodex / OpenAILocal / Ollama | Configurable model discovery and filtering without long manual config git clone https://github.com/yuhp/opencode-models-discovery.git | |
| 8 | opencode-llm-proxyKochC/opencode-llm-proxy | 85 | Claude / AnthropicopencodeCodex / OpenAIGemini / GoogleGitHub CopilotLocal / Ollama | OpenCode-backed API gateway with tool calling git clone https://github.com/KochC/opencode-llm-proxy.git | |
| 9 | mcp-clientrakesh-eltropy/mcp-client | 49 | Claude / AnthropicMCPCodex / OpenAIGemini / GoogleLocal / Ollama | MCP REST API and CLI client for interacting with MCP servers, supports OpenAI, Claude, Gemini, Ollama etc git clone https://github.com/rakesh-eltropy/mcp-client.git | |
| 10 | openclaw-self-healingRamsbaby/openclaw-self-healing | 40 | Claude CodeClaude / AnthropicCodex / OpenAIGemini / GoogleLocal / Ollama | 4-tier autonomous crash recovery for Claude Code and any service — 64% auto-resolved, LLM-agnostic (Claude/GPT-4/Gemini/Ollama), Prometheus metrics curl -fsSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install.sh | bash -s -- --dry-run | |
| 11 | jarvisRamsbaby/jarvis | 20 | Claude CodeClaude / AnthropicLocal / Ollama | Turns an idle Claude Max subscription into a 24/7 AI ops system — Discord bot, 76 scheduled tasks, 12 AI teams, local LanceDB RAG, 98% context compression via Nexus CIG, and 4-layer self-healing infrastructure. Uses claude -p headless mode at $0 extra cost git clone https://github.com/Ramsbaby/jarvis.git |