CATEGORY INTELLIGENCE / WORLDWIDE
Voice agents
Real-time conversations that get things done.
Red ocean · Measured classification
Cooling recently, still above last year
The recent search pullback coexists with a higher level than last year. Compare concrete use cases; neither window measures customer demand.
Report dated · Method 1.2.0 · moderate evidence confidence
- 112 active projects match the published GitHub search scope.
- The keyword “ai voice agent” has 104 complete weeks; 0% are reported as zero.
- Matching active GitHub projects
- 112
- Search-interest growth
- -52% · Last 8 complete weeks vs previous 8
- Search term and region
- ai voice agent · Worldwide
- Complete weekly observations
- 104
Why this classification
- Search attention is cooling recently but remains above the same period last year. A pullback is not a long-term decline.
- Median weekly search interest fell 52% across two consecutive eight-week windows.
- 112 matching active repositories; this is search coverage, not a count of direct competitors.
- Four-week search change: -29%; thirteen-week change: -34%. These windows check the direction of the eight-week comparison.
Source evidence
GitHub repository search · topic:voice-agent fork:false archived:false stars:>=5 pushed:>=2026-03-20
Collected 2026-09-16T04:47:05.539Z
Google Trends search interest · Collected 2026-09-16T04:47:05.535Z
Leading repositories
| Repository | Stars | Description |
|---|---|---|
| agentscope-ai/agentscope | 31,756 | Build and run agents you can see, understand and trust. |
| QwenAudio/qwen-audio-agent | 2,651 | A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents |
| xzf-thu/VoiceMem | 1,797 | Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level. |
| Lynpoint/CyberVerse | 1,650 | Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video. |
| ddalcu/mlx-serve | 1,283 | Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling. |
| PatterAI/Patter | 1,056 | Open-source voice-AI SDK. The Vapi/Retell alternative for builders who want to own the stack. Give your AI agent a phone number in 4 lines — Python and TypeScript, MIT licensed, Twilio, Telnyx, and Plivo. |
| restsend/rustpbx | 798 | A PBX written by rust |
| oxbshw/LLM-Agents-Ecosystem-Handbook | 549 | One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools. |
| PunithVT/ai-avatar-system | 492 | 🎭 AI Avatar / digital human platform — upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self-hosted. Claude · Whisper · Chatterbox · MuseTalk. |
| deepgram/deepgram-python-sdk | 463 | Official Python SDK for Deepgram. |
Limits of this result
- Google Trends measures relative search attention, not customers, revenue or willingness to pay.
- Supply counts active repositories matching the displayed GitHub topic and phrase queries; unmatched and closed-source competitors are outside this coverage.
- Repository density and search attention are separate observations. Neither proves commercial competition or demand.
Search interest measures attention, not paying customers. Classification thresholds are published heuristics and still require empirical calibration.
Use and share the evidence
Permanent report · Markdown · JSON · PNG card
