vox — security grade CAUTION, quality 70/100

Security audit verdict: CAUTION · quality 70/100

Flagged: opens a tunnel service. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by steipete · AI Tool · ★ 94

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is vox safe to install? View the security audit →

About vox

vox CLI + bridge server that connects Twilio Media Streams (PSTN phone calls) ↔ OpenAI Realtime (speech-to-speech) and lets the voice model call back into your local agent via tools. This repo is intentionally “thin glue”: WebSocket proxying, barge-in/interrupt handling, logging, and a minimal tool adapter. What you get : HTTP endpoint that returns TwiML and a WebSocket endpoint Twilio streams audio to. : outbound calling via Twilio REST to connect a call to your running . OpenAI Realtime session configured for G.711 μ-law passthrough () so there’s no resampling/DSP required. tool that can call: an HTTP endpoint (), or a local subprocess (, JSONL request/response). Requirements Node.js = 22 A public HTTPS URL to your laptop (Twilio needs to reach and ). works fine. OpenAI API key Twilio account + a phone number (for PSTN calling) Setup Fill in at least: (the public HTTPS base URL that maps to your local server, e.g. your ngrok URL) Run Start the bridge: Smoke check: Inbound calls (recommended dev loop) Point your Twilio Phone Number’s “A call comes in” webhook to: When you

callclitypescript

Quick Facts

Stars94
Forks18
LanguageTypeScript
CategoryAI Tool
LicenseMIT
Quality Score69.5642921456516/100
Last Updated2026-09-04
Created2025-12-13
Platformscli, node
Est. Tokens~14k

vox alternative? Top 6 similar tools

Looking for a vox alternative? If you're comparing vox with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • sudocode by sudocode-ai · ⭐ 290

    Lightweight agent orchestration dev tool that lives in your repo

  • mcp-server-atlassian-bitbucket by aashari · ⭐ 160

    Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces,

  • claude-code-open by kill136 · ⭐ 158

    Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

  • c0ntextKeeper by Capnjbrown · ⭐ 62

    Automatic context preservation for Claude Code. Never lose work to compaction again. 7 hooks, 187 semantic pat

  • mcp-cli by apify · ⭐ 459

    mcpc is a CLI client for MCP. It supports persistent sessions, stdio/HTTP, OAuth 2.1, JSON output for code mod

  • agnix by agent-sh · ⭐ 405

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

More AI Tool Tools

Explore other popular ai tool tools:

View all AI Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is vox?

vox is Let's your agent run phone calls. It is categorized as a AI Tool with 94 GitHub stars.

What programming language is vox written in?

vox is primarily written in TypeScript. It covers topics such as call, cli, typescript.

How do I install or use vox?

You can find installation instructions and usage details in the vox GitHub repository at github.com/steipete/vox. The project has 94 stars and 18 forks, indicating an active community.

What license does vox use?

vox is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to vox?

The top alternatives to vox on Agent Skills Hub include sudocode, mcp-server-atlassian-bitbucket, claude-code-open. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse AI Tool tools