Deep Agents Harness Optimized Link
togethercompute · x · 2026-07-15
This is a supplementary entry to the LangChain Deep Agents cookbook, focusing on the Deep Agents Harness optimization for NVIDIA Nemotron 3 Ultra.
Building on the previous post, this example demonstrates how to use the file system as memory during multi-turn agent execution and achieve Ralph loops by refreshing the context in each iteration.
Related event: NVIDIA and LangChain Release Deep Agents Ralph Loop Cookbook(2 posts)→
More from coding & agent
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- Anthropic researcher: 99% of engineers now run swarms of 300+ self-improving agents — AlishaOutridge · 2026-09-11
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11