cyijun/agent-smith
Agent Smith has taken over your terminal: he recursively breaks down tasks and mercilessly executes them with Claude Code CLI/Opencode/openclaw until your project is "assimilated." Red pill or blue pill? On GitHub, only cloning his code matters.
This system helps development teams or project managers break down large, complex projects into smaller, manageable tasks that can be worked on simultaneously by multiple AI agents. You provide a high-level project goal, and the system automatically decomposes it into subtasks, assigns them to isolated 'agents', and then aggregates the individual results into a final project output. It's designed for anyone overseeing projects that can benefit from parallel execution by AI assistants, ensuring a conflict-free workflow.
Use this if you need to tackle a large project by having multiple AI agents work on different parts concurrently without interfering with each other.
Not ideal if your tasks are simple, highly sequential, or have frequent interdependencies that cannot be isolated.
Stars
7
Forks
1
Language
—
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/cyijun/agent-smith"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlorianBruniaux/claude-code-ultimate-guide
A tremendous feat of documentation, this guide covers Claude Code from beginner to power user,...
alirezarezvani/claude-skills
+180 production-ready skills & plugins for Claude Code, OpenAI Codex, and OpenClaw —...
war851/AI-Governance-Architecture
Claude Code best practices -- applied to application design. Interactive HLD/LLD visualization,...
travisjneuman/.claude
The Ultimate Claude Code Toolkit — 119 skills, 67 agents, 101 marketplace repos (6,600+...
uxderrick/mece-skill
MECE (Mutually Exclusive, Collectively Exhaustive) validation and decomposition skill for AI...