Nemotron 3 Ultra Powers Agent Workflows
LangChain · x · 2026-07-16
LangChain shared a new video from @itsao detailing how to run NVIDIA Nemotron 3 Ultra on Baseten and integrate it into a Deep Agents Code workflow.
Highlighted capabilities include:
- 550B parameters, reaching speeds of 300 tokens/s
- Endpoint Agent support for skills, sub-agents, MCP
- First-class tracing provided by LangSmith
Ultimately, this is an engineering-focused demonstration of an agent/coding workflow rather than mere model promotion.
Related event: LangChain Demonstrates Nemotron 3 Ultra Agent Workflow(4 posts)→
More from coding & agent
- Building a Secure AI Agent Gateway: Self-Hosting OAuth for Multiple SaaS Apps — Defiant_Cod_2654 · 2026-07-22
- Rowboat launches as an open-source, local-first AI coworker with memory — ycombinator · 2026-07-22
- Scoble says AI “loops” really means long-running multi-agent workspaces — Scobleizer · 2026-07-22
- Kimi Code opens a waitlist as Moonshot rolls out its coding product — Fabulous_Bonus_8981 · 2026-07-22
- Open-source runtime lets each repo define its own AI code reviewer — ibabufrik · 2026-07-22
- Indie Dev Asks: What's Actually Broken in Your AI Agent's Memory Today? — AcceptableTime7937 · 2026-07-22