Sàn agent

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

Harness engineering beginner tutorial, from 0 to 1

Build effective agents using Model Context Protocol and simple workflow patterns

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

Orchestrate multiple coding agents from desktop and mobile

Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

45+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running itself in a container. Also includes the dx plugin: skills for everyday dev workflows.

Autonomous AI development loop for Claude Code with intelligent exit detection

Let AI agents browse the web. An autonomous toolkit for browser-based AI agents.

List of free GPTs that doesn't require plus subscription

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

A collection of sample agents built with Agent Development Kit (ADK)

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.

A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

MagenticLite is an experimental agent that works across the browser and local file system

Run OpenClaw, (formerly Moltbot, formerly Clawdbot) on Cloudflare Workers

An Open-Source Asynchronous Coding Agent

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Agentic AI Framework for Java Developers

AI Observability & Evaluation

Build, Manage and Deploy AI/ML Systems