QwenAudio/qwen-audio-agent
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
About the project
A realtime voice runtime for AI agents: full-duplex voice conversation while a connected backend agent (Qwen Code, Claude Code, Codex, etc.) runs tasks and returns results into the same conversation.
Useful for
- Run a voice assistant with a fully local Hugging Face speech-to-speech stack
- Connect Claude Code or Codex as a backend agent to execute tasks by voice
- Create multiple async tasks and ask about their progress in the conversation
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 4 stars so far today, about 10 expected by the end of the day.
- GitHub Trending JavaScript today: #5, +15 stars.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 2,814
- Today
- 4 · ≈ 10 by evening
- Forks
- 277
- Issues and pull requests
- 515
- Watchers
- 18
- Language
- JavaScript
- License
- Apache-2.0
- Latest release
- v2.0.1 · September 26, 2026
- Created
- July 27, 2026
- Last push
- September 28, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 29, 2026GitHub Trending JavaScript today: #5, +15 stars
More in this category
-
8.6
paperclipai/paperclip
Open-source Node.js and React platform for orchestrating a team of AI agents: goals, org chart, budgets, tickets and audit. Suits teams running autonomous agents (Claude Code, Codex, Cursor, etc.) and wanting to manage…
-
7.6
NVIDIA/OpenShell
A safe, private runtime for autonomous AI agents: isolated sandbox containers governed by declarative YAML policies restricting filesystem, network, and process access. Manages credential injection for agents like…
-
7.5
mvschwarz/openrig
OpenRig is a harness orchestrator for AI coding agents: a team of agents (Claude Code and Codex) is defined in YAML and booted with one command, turning scattered terminal sessions into a managed team with a lead agent.
-
7.2
vectorize-io/hindsight
Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server…
-
6.8
dzhng/jevgrep
A CLI for coding agents that finds relevant files and source excerpts in a repository from a question about code behavior. It uses Jev for relevance ranking and requires a Vercel AI Gateway, TypeSafe, or OpenRouter key.
-
6.5
aliyun/ai-agent-handbook
An open handbook on building enterprise AI agents across their full lifecycle: architecture, build, run, governance and optimization. Aimed at developers, architects, tech leads and business owners adopting agents in…