AI & Agents

Curated insights on AI agents, LLMs, and prompt engineering - tools, frameworks, and ideas from building AI-powered products.

agents (128)llm (60)prompt-engineering (9)mlops (5)computer-vision (4)

Curator's note

The agent space is moving fast. I am tracking the shift from simple chatbots to autonomous coding agents, tool-using systems, and multi-agent orchestration. The most useful insights here are on practical agent architectures, not hype.

My content

Free local meeting transcription with Meetily

Free, open-source meeting transcription that runs 100% on your computer. No cloud, no subscriptions.

Solved: How to use an Anthropic Claude API key without browser login

Why sharing API keys for teaching, CI/CD, or team projects shouldn't require giving everyone access to your organization.

My AI assistant can finally test its own code

How connecting Claude to Playwright fixed one of my biggest frustrations with AI-driven development.

Curated insights

206 total

GPT-5.6 Sol, Terra, Luna: OpenAI's cost-efficiency bet vs Fable 5 llm

Shepherd: reversible, Git-like execution traces for AI agents agents

TinySearch: self-hosted MCP web research for local LLMs agents

Claude Science: Anthropic's beta for scientific research agents

Introducing the Safari MCP server for web developers agents

Claude Real Video: let Claude actually watch a video llm

Yann LeCun's $1B Bet Against LLMs [Part 1] llm

Anthropic open-sources knowledge-work plugins for Claude Cowork agents

How DeepSeek Runs a 284B LLM on a Laptop (Run AI Locally) llm

LLM Evals: Everything You Need to Know mlops

Reflexion: Language Agents with Verbal Reinforcement Learning agents

Mega-ASR: open-source ASR built for noisy real-world audio llm

Local Qwen isn't a worse Opus, it's a different tool llm

ralphex: The Extended Ralph Loop for Claude Code and codex agents

Agentic Loops: Self-Prompting AI Workflows and How They Work agents

Claude Code Workflows: script subagents in loops and sequences agents

Undocumented Claude Code Config Fields Found in the Source Code agents

Introducing Gemma 4 12B: a unified, encoder-free multimodal model llm

Lathe: LLM-generated hands-on technical tutorials you build yourself llm

DeepSeek-Reasonix: DeepSeek-native terminal AI coding agent agents

Awesome Claude Connectors: a directory of MCP integrations agents

The Vibe Coding Era: Why AI Won't Replace Software Engineers agents

One Person, Five Roles: Shipping a Full App with Claude Code on GCP agents

When to build an AI agent: a 4-point production checklist agents

ByteDance Lance: 3B unified multimodal model mlops

Shortcuts Playground: Claude Code/Codex plugin for Apple Shortcuts agents

Paperclip, the app people use to manage AI agents for work agents

Vibe Kanban - Orchestrate AI Coding Agents agents

Hinton: language as a modelling medium and mortal computation llm

n8n MCP server for Claude Code: TypeScript-validated workflows agents

Prompt guidance for OpenAI GPT-5.5 prompt-engineering

The real reason Google gave away Gemma 4 llm

Prompting 101: Anthropic's 10-block prompt skeleton prompt-engineering

Claude Code SDK and GitHub Action: headless agents in CI agents

Claude Code practical tips from Anthropic creator (Boris) agents

Systalyze: open-source GPU monitor exposing the 100% utilization lie mlops

OpenAI Privacy Filter: open-weight on-device PII redaction llm

Introducing GPT-5.5 llm

Tips for building good Claude Skills agents

HyperFrames: Write HTML, Render Video, Built for Agents agents

Introducing Claude Design by Anthropic Labs llm

Cloudflare's Agent Readiness Score: how agent-ready is your site? agents

Gemini Embeddings 2: text, image, video, audio in one vector space llm

video-use: edit videos with Claude Code via transcripts agents

7 levels of Claude Code and RAG agents

Artifacts: versioned storage that speaks Git agents

Automate work with routines - Claude Code Docs agents

Caveman: Claude Code skill cuts output tokens 65% via caveman-speak prompt-engineering

Codex for (almost) everything agents

Darkbloom: Private AI Inference on Apple Silicon llm

Friends Don't Let Friends Use Ollama llm

exo: Cluster Macs to Run Frontier AI Models Locally llm

Graphify: Knowledge Graph Skill for AI Coding Assistants agents

Introducing Agent Lee - a new interface to the Cloudflare stack agents

Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All llm

Why Chinese AI Is Suddenly So Good (ft. DeepSeek, Seedance 2.0) llm

ThePopeBot: git-native autonomous AI agent scaffolding agents

A Visual Guide to Gemma 4 llm

Anthropic releases advisor mode agents

Claude Mythos: Highlights from 244-page Release llm