TEN-framework/ten-framework

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

11082 stars · 1354 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

TEN is an open-source framework for building real-time multimodal conversational AI agents, with a focus on low-latency voice assistants. It includes an ecosystem of components such as agent examples, VAD, turn detection, and a developer portal.

Use cases

• build a real-time voice assistant with low latency
• create conversational AI agents that handle audio and video
• add voice chat to an application with LLMs
• self-host a multimodal AI agent with Docker
• implement turn detection and VAD in a voice pipeline

When to choose

• you need a real-time, low-latency voice or multimodal agent framework
• you want ready-made agent examples to start from
• you plan to self-host conversational AI agents

When to avoid

• you only need simple text chatbots without real-time audio
• you want a fully managed hosted service rather than a self-hosted framework
• your license requirements cannot accommodate its non-standard license

Facets

framework · maturity active

agent-framework speech-recognition audio-processing video-processing llm-inference chatbot artificial-intelligence speech-processing large-language-models python self-hosted cross-platform voice-ai conversational-agents real-time-multimodal vad turn-detection voice-assistant ai-agents real-time docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="TEN-framework/ten-framework")