AI Workflows & Agentic Architecture Directory

Nex-N2 is an open-source agent model with Agentic Thinking framework. Nex-N2-Pro matches GPT-5.5 on agentic coding for zero API cost. Complete self-hosting guide.

Claude Code dynamic workflows let Claude Opus 4.8 orchestrate 100+ parallel agents for codebase migration. The Bun Zig-to-Rust port of 750K lines completed in 11 days with 99.8% test pass rate. Step-by-step setup guide.

Microsoft Scout is an always-on personal agent for Microsoft 365 that proactively manages email, calendar, and coordination. Employees report reclaiming 5-8 hours weekly.

NVIDIA Nemotron 3 Ultra is a 550B MoE open-weight model for multi-agent orchestration. 5x higher throughput, 30% lower cost vs GPT-5.5. Complete deployment guide with setup steps.

Google ADK 2.0 is the open-source framework for building production multi-agent systems. With graph workflows, ParallelAgent, and LoopAgent, it cuts research time from 4 hours to 45 minutes per brief. Available in 5 lang...

Hermes Agent is the fastest-growing open-source AI agent of 2026 with 165K+ GitHub stars. It runs as a persistent daemon, remembers every conversation, creates reusable skills from completed tasks, and gets 60% faster at...

Claude Code is Anthropic's terminal-based autonomous coding agent that reads your entire codebase, implements features across multiple files, runs tests, and submits pull requests from a single command. Teams using this...

OpenAI Symphony Codex Linear PR Orchestrator polls Linear for unassigned issues, assigns Codex agents to claim and implement each one, and creates a pull request — all without human intervention. Issues with clear accept...

The n8n 3-in-1 AI Automation Suite uses Claude 3.5 Sonnet and Gemini 1.5 Pro across 81 interconnected n8n nodes to run a content factory, customer intelligence engine, and campaign orchestrator from one instance. A 3-per...

Running Hermes Agent (Nous Research, v0.10.0, 176k+ GitHub stars) with local LLMs means pairing its self-improving agent framework with Ollama or llama.cpp for inference. Total monthly cost: $0 in API fees. A 9B model on...

Claude Code Codex dual-track coding uses Claude 3.5 Sonnet to architect and implement features locally while OpenAI Codex runs adversarial tests in a sandboxed parallel track. Codex generates 15-25 edge-case tests per fe...

Hermes CCC turns Claude Code into a queueable, channel-driven coding service. When a developer sends a task via Slack or Telegram, Hermes evaluates complexity and dispatches it to Claude Code in either print-mode for qui...