DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
CrewAI's quadratic context problem: why a 5-agent crew costs 6 more than you expect

CrewAI's quadratic context problem: why a 5-agent crew costs 6 more than you expect

Comments 1
7 min read
MCP vs Skills: Why Skills Save Context Tokens

MCP vs Skills: Why Skills Save Context Tokens

1
Comments
6 min read
Claude, Codex, Gemini, Grok: A Field Report on Agentic Memory Write Reliability

Claude, Codex, Gemini, Grok: A Field Report on Agentic Memory Write Reliability

Comments
5 min read
eval-harness - an evaluation framework for agentic cli tools

eval-harness - an evaluation framework for agentic cli tools

1
Comments 1
3 min read
Running Hermes Agent with Kokoro TTS: A Local-First AI Assistant Setup

Running Hermes Agent with Kokoro TTS: A Local-First AI Assistant Setup

6
Comments
3 min read
Pydantic AI 的 5 个隐藏用法:类型安全的 Agent 框架

Pydantic AI 的 5 个隐藏用法:类型安全的 Agent 框架

Comments
3 min read
When Your AI Agent Restarts Mid-Task: Building Durable Workflows in Spring Boot

When Your AI Agent Restarts Mid-Task: Building Durable Workflows in Spring Boot

Comments
7 min read
Query-Time Entity Disambiguation in Graph RAG: When One Name Means Seventeen Nodes

Query-Time Entity Disambiguation in Graph RAG: When One Name Means Seventeen Nodes

2
Comments 2
5 min read
Mastering Ollama AI endpoints: How to use each one correctly

Mastering Ollama AI endpoints: How to use each one correctly

1
Comments
5 min read
You probably don't need a vector database for agent memory

You probably don't need a vector database for agent memory

Comments 7
5 min read
Your AI Guardrails Speak English Only — Here's the Multilingual Jailbreak Gap

Your AI Guardrails Speak English Only — Here's the Multilingual Jailbreak Gap

1
Comments
4 min read
Open-Weight AI Is Having Its Kubernetes Moment — And Developers Need to Pay Attention

Open-Weight AI Is Having Its Kubernetes Moment — And Developers Need to Pay Attention

Comments
8 min read
How Do You Contain an AI Agent Failure You Can't Prevent?

How Do You Contain an AI Agent Failure You Can't Prevent?

1
Comments
2 min read
AI Agents Hacked: Lessons from OpenAI & Hugging Face

AI Agents Hacked: Lessons from OpenAI & Hugging Face

Comments 1
10 min read
"Agent Memory adherence is a systems problem. So which model lets you meddle with that system?"

"Agent Memory adherence is a systems problem. So which model lets you meddle with that system?"

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