DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Self-Evolving AI Agent: How to Stop Correcting Your LLM Twice

The Self-Evolving AI Agent: How to Stop Correcting Your LLM Twice

1
Comments
3 min read
Context Pointer OS: Reconstructing Memory for Long-Running AI Agents

Hermes Agent Challenge Submission: Build With Hermes Agent

Context Pointer OS: Reconstructing Memory for Long-Running AI Agents

1
Comments
3 min read
Claude Agent SDK vs Vercel AI SDK 6 — which to pick in 2026

Claude Agent SDK vs Vercel AI SDK 6 — which to pick in 2026

Comments 1
3 min read
Two DM-origin problems, not one: security hardening vs. compliance-bias hardening

Two DM-origin problems, not one: security hardening vs. compliance-bias hardening

Comments
3 min read
I Stopped Running API Workflows. I Taught My Agent to Own Them

I Stopped Running API Workflows. I Taught My Agent to Own Them

Comments
5 min read
Qwen3.6, and WilmerAI OpenCode workflows

Qwen3.6, and WilmerAI OpenCode workflows

Comments
3 min read
Google I/O 2026: We're Not Building Apps Anymore — We're Deploying Agents

Google I/O Writing Challenge Submission

Google I/O 2026: We're Not Building Apps Anymore — We're Deploying Agents

4
Comments
5 min read
Composable Agent Specs: Spec Delegation and the OAS Registry

Composable Agent Specs: Spec Delegation and the OAS Registry

Comments
5 min read
august 2 is closer than you think, what the eu ai act actually requires from your agents

august 2 is closer than you think, what the eu ai act actually requires from your agents

Comments
2 min read
Universal Language v0.1: A Geometric Symbolic Protocol for AI Agent Coordination and Moltbook

Universal Language v0.1: A Geometric Symbolic Protocol for AI Agent Coordination and Moltbook

1
Comments
3 min read
Synthadoc: Built an AI Judge for Our LLM Wiki Compiler - Here's What We Learned

Synthadoc: Built an AI Judge for Our LLM Wiki Compiler - Here's What We Learned

7
Comments
5 min read
Why every data quality tool tells you what broke — but leaves you alone to figure out why

Why every data quality tool tells you what broke — but leaves you alone to figure out why

1
Comments
5 min read
Four tiers for agent action, after the matplotlib incident

Four tiers for agent action, after the matplotlib incident

Comments
4 min read
Building Autonomous DevOps Agents with MCP and LangChain

Building Autonomous DevOps Agents with MCP and LangChain

1
Comments
5 min read
I Run 14 AI Agents in Production. Here Are the 6 Rules That Survived.

I Run 14 AI Agents in Production. Here Are the 6 Rules That Survived.

Comments
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.