Multi-model AI gateway — 8 providers plus local models, no system prompt injection.
Multi-model AI gateway for MCP clients. MCP clients like Claude Code, Claude Desktop, and Cursor are locked to their host model. Vox gives them access to every other model — Gemini, GPT, Grok, DeepSeek, Kimi, or your local Ollama — through a single tool. The design is deliberately minimal: prompts go to providers unmodified, responses come back unmodified. No system prompt injection. No response…
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
Multi-model AI gateway for MCP clients. MCP clients like Claude Code, Claude Desktop, and Cursor are locked to their host model. Vox gives them access to every other model — Gemini, GPT, Grok, DeepSeek, Kimi, or your local Ollama — through a single tool. The design is deliberately minimal: prompts go to providers unmodified, responses come back unmodified. No system prompt injection. No response formatting. No behavioral directives. The only value Vox adds is routing and conversation memory —…