DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Build a Production-Ready RAG System Over Your Own Documents in 2026 – A Practical Tutorial

Build a Production-Ready RAG System Over Your Own Documents in 2026 – A Practical Tutorial

Comments 2
3 min read
AI's Infrastructure & Agents: From Chips to Code Automation

AI's Infrastructure & Agents: From Chips to Code Automation

Comments
4 min read
SentinelLM - A Proxy Middleware for Safer, Observable LLM Systems

SentinelLM - A Proxy Middleware for Safer, Observable LLM Systems

Comments
2 min read
Why AI-Generated Code is a Security Minefield (And What To Do About It)

Why AI-Generated Code is a Security Minefield (And What To Do About It)

Comments
4 min read
LLM Observability for Laravel - trace every AI call with Langfuse

LLM Observability for Laravel - trace every AI call with Langfuse

Comments 1
4 min read
The `prefer` parameter: routing AI requests by intent instead of model name

The `prefer` parameter: routing AI requests by intent instead of model name

1
Comments
3 min read
# Reading YC-Backed Code #1: claude-mem — Great Idea, Poor Implementation

# Reading YC-Backed Code #1: claude-mem — Great Idea, Poor Implementation

1
Comments
9 min read
16 GB VRAM LLM benchmarks with llama.cpp (speed and context)

16 GB VRAM LLM benchmarks with llama.cpp (speed and context)

Comments
4 min read
MCP Gateways for Claude: Choosing the Right Infrastructure Layer

MCP Gateways for Claude: Choosing the Right Infrastructure Layer

Comments 1
8 min read
How CloYou Reimagines AI App Architecture for Developer Workflows

How CloYou Reimagines AI App Architecture for Developer Workflows

Comments
3 min read
Claude Code VS Code extension freezes with multiple chat tabs? Workaround for Windows

Claude Code VS Code extension freezes with multiple chat tabs? Workaround for Windows

Comments
2 min read
Creating a Lua sandbox for my LLM tool

Creating a Lua sandbox for my LLM tool

Comments
4 min read
I built an npm middleware that scores your LLM prompts before they hit your agent workflow

I built an npm middleware that scores your LLM prompts before they hit your agent workflow

1
Comments
2 min read
How We Built An Operations Support AI Agent for a Global Auto Industry Leader's Post Sales Software Department

How We Built An Operations Support AI Agent for a Global Auto Industry Leader's Post Sales Software Department

Comments
4 min read
How to Get Gemma 4 26B Running on a Mac Mini with Ollama

How to Get Gemma 4 26B Running on a Mac Mini with Ollama

11
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.