Totally agree, all the interesting stuff is happening at the harness layer
@hwchase17
-
Community Middleware for Customizing Agents and DeepAgents
By
–
In case you haven’t seen – more and more community middleware is popping up as ways to customize your agents and deepagents Got some middleware you want to contribute? Reach out to Sydney!
-
DeepAgents vs LangChain: Agent Framework Comparison Guide
By
–
great q! deepagents has more "batteries included", which langchain v1 is a very minimalistic agent harness if you are doing more complex workflows (eg claude code for X) -> deepagents if you want something simple -> langchain both are customizable with middleware
-
Open Standards for AI Agents and Memory Access Requirements
By
–
i agree but there are some open standards (agents.md, skills) and you at least need to be able to access the memory
-
Agent SDK Design: Sandbox vs External Harness Approaches
By
–
most of the agents we see being built do this the main cases where we see people using "agent in a sandbox" is when they are using claude agent sdk (which is poorly designed for "harness outside sandbox")
-
Deep Agents Deploy: Production-Ready AI Agents with Memory
By
–
Deep Agents deploy gets you: – Deep Agents harness
– Sandbox of your choice (
@daytonaio , @modal , @RunloopDev )
– Short and long term memory
– Agents exposed via MCP and A2A Production ready and open standards -
Form Factor Lock-in Concerns in AI Hardware Design
By
–
its a directionally correct form factor but way too much lock in
-
AI Form Factor Directionally Correct but Creates Excessive Lock-in
By
–
its a directionally correct form factor but way too much lock in
-
Isidore Miller shares hot takes on agents and evaluations
By
–
was really fun to sit down with @isidoremiller for this one! he has a bunch of hot takes on agents and evals that you're going to want to hear!