Stories by omarsar

MCPNext: Next-Gen Universal Tool-Use Layer for AI Agents

MiniMax-M2 Deep Research Agent

Analyzing Papers with Nano Banana Pro

Built a Pulse Feature for Claude Code

Kimi CLI

Scaling Reinforcement Learning for Trillion-Scale Thinking Model

Deep Agents

Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing

Chain-of-Agents

Building Effective Agents While Reducing Cost

Agentic Web: Weaving the Next Web with AI Agents

Graph-R1: Towards Agentic GraphRAG Framework via End-to-End RL

The Implicit Dynamics of In-Context Learning

Deep Researcher with Test-Time Diffusion

AIOps in the Era of LLMs

OpenAI 4o Image Generation Guide

Context Engineering Guide

AI for Scientific Search

Reasoning LLMs Guide for Devs

1
2
3
4
5
6
7