Agents

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Luhui Dev

May 13

Anthropic Managed Agents: 2026 Agent Harness Architecture for Production AI Agents

#luhuidev #claude #agents

9 min read

Mininglamp

May 13

Why One Giant Model Ruling Everything Is a Bad Idea

#ai #opensource #agents #machinelearning

6 min read

Mark Nelson for Oracle Developers

May 13

AI agents know SQL. Oracle Database Skills teach them Oracle

#agents #ai #database #sql

8 min read

Neethu E V

May 13

I have talked to dozens of AI teams about production. The same things keep breaking.

#agents #ai #llm #monitoring

4 min read

joinwell52

May 13

When Agents Learn From Their Own Wreckage

#ai #agents #llm #multiagent

8 min read

yunchuan liu

May 13

AgentHub: A Multi-Model Terminal Workspace for Coding Agents

#showdev #agents #ai #cli

4 min read

Pieter Bosma

May 13

So Many OpenClaw Wrappers, So Little Time — I Built a Directory for That

#openclaw #ai #agents #devtool

2 min read

Vilius

May 26

I Tested 10 More Models. Five Brand New Families Debuted. None Scored Below 75%.

#ai #agents #benchmark #llm

3 min read

Vektor Memory

May 26

Human-in-the-Loop: The Most Important Concept in AI That Keeps You Employed

#ai #automation #agents #hitl

16 min read

Swapnanil Saha

May 26

LLM Context Window Token Budget: Why Your Window Fills Up Fast

#agents #ai #architecture #llm

17 min read

Ken Imoto

May 13

I Was Calling It 'Setup' for Six Months. arXiv Has a Better Word: Harness

#ai #agents #claudecode #harness

8 min read

Inalpha

May 27

I don't trust LLMs to place orders. Here's the middleware that does.

#agents #ai #opensource #architecture

1 min read

Shouvik Palit

May 13

I Tested Privacy-Aware Routing with 4 AI Agents: What Actually Stayed Local

#agents #ai #llm #privacy

4 min read

Domonique Luchin

May 13

How I use Claude Code to dispatch agent tasks from a Supabase queue table

#ai #agents #supabase #python

3 min read

Aurora

May 13

Building a Self-Hosted Multi-Agent System in Rust: Architecture Decisions and What I Learned

#rust #ai #agents #selfhosted

6 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

DEV Community

# agents

Anthropic Managed Agents: 2026 Agent Harness Architecture for Production AI Agents

Why One Giant Model Ruling Everything Is a Bad Idea

AI agents know SQL. Oracle Database Skills teach them Oracle

I have talked to dozens of AI teams about production. The same things keep breaking.

When Agents Learn From Their Own Wreckage

AgentHub: A Multi-Model Terminal Workspace for Coding Agents

So Many OpenClaw Wrappers, So Little Time — I Built a Directory for That

I Tested 10 More Models. Five Brand New Families Debuted. None Scored Below 75%.

Human-in-the-Loop: The Most Important Concept in AI That Keeps You Employed

LLM Context Window Token Budget: Why Your Window Fills Up Fast

I Was Calling It 'Setup' for Six Months. arXiv Has a Better Word: Harness

I don't trust LLMs to place orders. Here's the middleware that does.

I Tested Privacy-Aware Routing with 4 AI Agents: What Actually Stayed Local

How I use Claude Code to dispatch agent tasks from a Supabase queue table

Building a Self-Hosted Multi-Agent System in Rust: Architecture Decisions and What I Learned