Deep Agents Ralph Loop Example
togethercompute · x · 2026-07-15
This new cookbook demonstrates how to implement Ralph loops using NVIDIA Nemotron 3 Ultra combined with LangChain Deep Agents.
The core approach involves refreshing the context at each iteration and using the file system as memory between iterations, allowing the agent to maintain its state across multiple execution rounds. The author also provided a complete notebook and an optimized harness version for review.
Related event: NVIDIA and LangChain Release Deep Agents Ralph Loop Cookbook(2 posts)→
More from coding & agent
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26