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
rag
Canvas Swarms, Automatic RAG, and Squeezing Agent Context
Spine Swarm’s collaborative canvas agents, Captain’s automated RAG for files, and Context Gateway’s context compression show how production AI agents are matur
Agent Harnesses, HF Buckets, and Bedrock Fine-tuning: Making Agents Actually Shippable
Hugging Face adds Storage Buckets, AWS streamlines Oumi fine-tuning into Bedrock, and LangChain dissects the “agent harness” pattern powering real production AI
Token Diets, Talking Agents, and Smarter Memories
Cut MCP token waste with mcp2cli, boost tool-calling with Mastra 1.10.0, and explore open-source high‑fidelity speech with MOSS‑TTS for production AI agents.