- Sep 28, 2026One Control PointAt my day job, I was asked to be more efficient with AI spend. The honest answer was a semantic router in front of every model, so I pointed my own coding agent at one. It broke. Five bugs later, the fixes are upstream, which means everybody gets them.
- Inference
- vLLM
- Open Source
- +2 more
- Sep 04, 2026The Router Was RightI wanted one place to decide which model answers and how hard it thinks. That surfaced a bug one event from the end of every stream. I fixed the wrong thing first, the schema proved the router right, and the real fix is now upstream in vLLM.
- Inference
- vLLM
- Open Source
- +1 more
- Nov 02, 2025Watching AI Actually Control a Real Robot: Austin AI & Robotics MeetupLive demonstrations of ros-mcp-server connecting Claude to industrial warehouse robots, complete with diagnostic testing and multi-robot orchestration. Plus insights from Contoro Robotics on solving the worst job in warehousing.
- Robotics
- AI
- Austin Tech
- +2 more
- Aug 08, 2025Deep Agents Part 4: Using deepagents with MCP and LangGraphInstall deepagents, create an agent, integrate it with LangGraph and connect MCP tools, plus the roadmap ahead. Part 4 of the Deep Agents series.
- AI
- Python
- LangGraph
- +2 more
- Aug 05, 2025Deep Agents Part 1: Beyond 'Shallow' – Introducing Deep AgentsExploring the evolution from simple single-step AI agents to sophisticated 'Deep Agents' capable of handling complex, long-horizon tasks with advanced planning and execution capabilities
- AI
- LangGraph
- Python
- +2 more