Tiny Kitten TTS models hit SOTA expressivity on-device
Kitten TTS ships sub-25MB expressive TTS models, AWS unveils V-RAG for grounded video generation, and Thomson Reuters explains why agentic workflows win in 2026
devtools
Self-Improving Agents, Sync’d Browsers, and DIY Context Compression
Zendesk buys Forethought for self-learning AI agents as LangChain ships autonomous context compression and OpenAI expands agent runtimes. What this means for AI