The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Agentic AI Systems
Agentic AI explained with chickens every pattern a runnable, CI-checked file.
Install
$
git clone https://github.com/ThibautMelen/agentic-ai-systemsInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Agentic AI Systems 🐔
Agentic systems explained with chickens — because AI orchestration doesn't have to be scary
Main Agent spawns Subagents like a hen with her chicks 🐔🪺🐦
🦄 Foundations • ⚙️ Workflows • 🐔 Autonomous • 📜 As Code • 🛠️ Implementation • 🗺️ Guides
Overview
%%{init: {'theme': 'base', 'themeVariables': { 'primaryColor': '#8b5cf6', 'primaryTextColor': '#fff', 'primaryBorderColor': '#7c3aed', 'lineColor': '#a78bfa', 'secondaryColor': '#ec4899', 'tertiaryColor': '#6366f1', 'noteTextColor': '#fff', 'noteBkgColor': '#8b5cf6', 'textColor': '#fff' }}}%%
mindmap
root((🐔 Agentic Systems))
🦄 Foundations
Augmented LLM
What Changed 2026
⚙️ Workflows
🏎️ Baseline
⛓️ Chaining
🚦 Routing
🛤️ Parallel
🦑 Orchestrator
🩻 Evaluator
🐔 Autonomous Agent
The Alternative
Multi-Window
🛠️ Implementation
🐦 Subagent
🦴 Command
📚 Skill
🪝 Hook
📜 Patterns as Code
Check before
Trace after
[!TIP] New in the 2026 edition — 🗞️ What Changed 2025-2026 (the dated map: context engineering, the multi-agent debate, the AGENTS.md · SKILL.md · MCP stack, harness engineering) and 📜 Patterns as Code (every pattern as a runnable file — checked in CI on every push, no API key needed).
⬆️ real capture: a repeated prompt graduates into a checked, runnable file — every pattern in this repo works this way · and three of them run a real campaign daily 🛰️
🗺️ Navigation
🦄 Foundations
The building block for everything
| 🦄 Augmented LLM | LLM + Retrieval + Tools + Memory |
| 🗞️ What Changed 2025-2026 | Context engineering · skills/MCP stack · harness era |
⚙️ Workflows
Predefined orchestration — code controls the flow
| # | Workflow | Use When |
|---|---|---|
| 0 | 🏎️ Baseline | Simple, 1-step task |
| 1 | ⛓️ Prompt Chaining | Sequential steps |
| 2 | 🚦 Routing | Classify & dispatch |
| 3 | 🛤️ Parallelization | Independent tasks |
| 4 | 🦑 Orchestrator | Expert delegation |
| 5 | 🩻 Evaluator | Quality iteration |
🐔 Autonomous Agent
Dynamic autonomy — LLM controls the flow
| Pattern | Use When |
|---|---|
| 🐔 Autonomous Agent | Open-ended problems |
| 🖥️ Multi-Window | Cross-session state (variant) |
🛠️ Implementation
Claude Code components & architecture
| Component | Location |
|---|---|
| 🐦 Subagent | .claude/agents/*.md |
| 🦴 Command | .claude/commands/*.md |
| 📚 Skill | .claude/skills/*/SKILL.md |
| 🪝 Hook | .claude/settings.json |
🗺️ Guides & 📖 Reference
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io