openlive — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by katipally · Codex Skill · ★ 265

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

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

About openlive

OpenLive The open voice and vision layer for AI agents. Your AI can think. OpenLive gives it ears, a mouth, and eyes. Bring your own model, or talk to the coding agents you already use, with the whole voice loop running on your own machine. An open alternative to ElevenLabs Agents, Gemini Live, and OpenAI Realtime.     [![Down

claude-codeclicodexcoding-agentsconversational-aicursorhermeslocal-firstopen-sourceopenai-realtime

Quick Facts

Stars265
Forks55
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score65.7048847918307/100
Open Issues1
Last Updated2026-08-27
Created2026-07-09
Platformsclaude-code, cli, codex, gemini, node
Est. Tokens~16k

Compatible Skills

These tools work well together with openlive for enhanced workflows:

  • neurolink — semantic(0.36)+complementary+shared_fw(openai)+rare_topics+same_lang+similar_pop+shared_platform (79%)
  • freestyle — semantic(0.36)+complementary+shared_fw(openai)+rare_topics+same_lang+similar_pop+shared_platform (75%)
  • better-chatbot — semantic(0.19)+complementary+shared_fw(openai)+rare_topics+same_lang+similar_pop+shared_platform (74%)
  • better-chatbot — semantic(0.17)+complementary+shared_fw(openai)+rare_topics+same_lang+similar_pop+shared_platform (73%)
  • ai — semantic(0.29)+complementary+shared_fw(openai)+rare_topics+same_lang+similar_pop+shared_platform (73%)

openlive alternative? Top 6 similar tools

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

  • memorix by AVIDS2 · ⭐ 760

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • agentsys by agent-sh · ⭐ 982

    AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod

  • OpenContext by 0xranx · ⭐ 729

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • maestro by ReinaMacCredy · ⭐ 231

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

  • sage by usetig · ⭐ 105

    An LLM council that reviews your coding agent's every move

  • ok-skills by mxyhi · ⭐ 484

    Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKI

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is openlive?

openlive is Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) runs locally. An open alternative to ElevenLabs Agents, Gemin. It is categorized as a Codex Skill with 265 GitHub stars.

What programming language is openlive written in?

openlive is primarily written in TypeScript. It covers topics such as claude-code, cli, codex.

How do I install or use openlive?

You can find installation instructions and usage details in the openlive GitHub repository at github.com/katipally/openlive. The project has 265 stars and 55 forks, indicating an active community.

What license does openlive use?

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

What are the best alternatives to openlive?

The top alternatives to openlive on Agent Skills Hub include memorix, agentsys, OpenContext. 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 Codex Skill tools