OpenShell Agents
Key Takeaways
Demonstrates using OpenShell with LangChain DeepAgents harness for agent options
Original Description
In this video, we look at OpenShell, the layer that runs the protection in NanoClaw Blueprints, but we actually do it with a LangChain DeepAgents harness to show how you can use a number of different agent options.
🔗 Links:
Github: https://github.com/langchain-ai/openshell-deepagent
NVIDIA: https://build.nvidia.com/openshell
Docs: https://docs.nvidia.com/openshell/home
Twitter: https://x.com/Sam_Witteveen
🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: https://drp.li/dIMes
👨💻Github:
https://github.com/samwit/llm-tutorials
⏱️Time Stamps:
00:00 Intro
00:39 Quick Recap: NemoClaw
01:47 3 Flavors of NemoClaw
02:47 LangChain Deep Agent Framework
03:07 Deep Agent Architecture
04:26 Deep Agents+NemoClaw+OpenShell
04:52 Deep Agent Project
05:51 OpenShell: The Core Idea - Out-of-Process Enforcement
07:52 4 Things Supervisor Controls
10:14 End-to-end Walkthrough
#NVIDIAAI #langchain
Watch on YouTube ↗
(saves to browser)
Sign in to unlock AI tutor explanation · ⚡30
More on: Agent Foundations
View skill →Related Reads
📰
📰
📰
📰
Why Anthropic Just Overtook OpenAI - And What It Means for Every SA Business Buying AI
Dev.to AI
I Built a 3-Layer Prompt Cache and Cut My LLM Costs by 73%
Dev.to AI
Meta opens its first paid model API with Muse Spark 1.1
Dev.to · Breach Protocol
Changes to LLM pricing: NextBit and SambaNova
Dev.to · Narev Bot
Chapters (10)
Intro
0:39
Quick Recap: NemoClaw
1:47
3 Flavors of NemoClaw
2:47
LangChain Deep Agent Framework
3:07
Deep Agent Architecture
4:26
Deep Agents+NemoClaw+OpenShell
4:52
Deep Agent Project
5:51
OpenShell: The Core Idea - Out-of-Process Enforcement
7:52
4 Things Supervisor Controls
10:14
End-to-end Walkthrough
🎓
Tutor Explanation
DeepCamp AI