AI Agent2024

TEN-framework/ten-framework

Builds real-time multimodal conversational AI agents with voice-assistant examples, VAD, turn detection, RTC/WebSocket transport, avatars, transcription, and edge-device demos.

Visit Website

Introduction

Voice agents fail when latency, turn-taking, and media plumbing are treated as details. TEN starts from the real-time conversation layer where speech, interruption, transport, and multimodal extensions must work together.

What Sets It Apart

It targets real-time multimodal conversational AI, with VAD, turn detection, speech-to-speech examples, diarization, avatars, SIP, transcription, ESP32 integration, RTC, and WebSocket support. The focus is media-native agent infrastructure.

Who Should Use It

Great fit if you build voice products, live avatars, telephony agents, or hardware voice interfaces. Look elsewhere for text-only agents, background workflows, or hosted voice APIs with minimal customization.

Back

Information

Websitegithub.com
OrganizationsTEN Framework
AuthorsTEN Framework (TEN-framework)
Published date2024/06/20

More Items

AI Model2026

Pipecat PhoneLLM Alpha 1

Daily, Pipecat

Open-weights LLM fine-tuned for phone-based voice agents that prioritizes low latency and reliable tool/function calling. Based on NVIDIA Nemotron 3 Nano (30B total, 3.5B active), supports very long contexts (262,144 tokens) and recommends temperature=0 with thinking disabled for deployment.

voice llm moe vllm safetensors+9

AI Agent2026

Garden Skills

ConardLi

A curated collection of production-ready Agent Skills that turn tasks—presentation production, image generation, local KB retrieval, article assembly, and web-design—into agent-loadable skill folders. Uses a SKILL.md contract, supports multiple agent runtimes (Claude Code, Cursor, Codex), and offers modular install paths with pinned release zips.

agent-skills coding-agents prompt-engineering ai-tools ai-image+5

AI Agent2026

Ponytail

Dietrich Gebert

Provides a ruleset and skills that make AI coding agents prefer the simplest correct implementation: reuse existing code, prefer stdlib/native features, and only write minimal new code. Cuts generated LOC, tokens, cost and time while preserving validation and safety.

agent-skills prompt-engineering plugin claude-code codex+9