Skip to content

Repository files navigation

Multi-Agent System Pattern

Python 3.11 Curriculum stub pytest Vercel

Curriculum teaching stub for Multi-Agent collaboration — orchestrator + specialists with reviewer gates. Pattern used in VAP Platform.

▶ Live demo · Architecture · Portfolio · VAP case study

What this is

Teaching reference for multi-agent collaboration — specialized roles, delegation, coordinated handoffs.

How we solve it

Orchestrator-controlled routing with critic/reviewer gates before final output; live trace UI for interviews and teaching.

Case study & tradeoffs

venkat-ai.com/work · Tradeoffs in docs/ARCHITECTURE.md.


Org skills: vpeetla-ai-skills. This repo includes .cursor/skills/, AGENTS.md, and CONTEXT.md.

git clone https://github.com/vpeetla-ai/vpeetla-ai-skills.git
./vpeetla-ai-skills/scripts/install.sh --cursor --codex --project .

Scope: Curriculum stub with deterministic tests and a live trace viewer — not a production agent fleet. Compose into Venkat AI Platform for governed graphs.

Implementation status

Component Status Notes
Pattern demo + trace UI Scenario chips · simulated metrics · compose CTA (VAP/OmniForge)
Core agent loop Reference implementation
LangGraph production graph 🟡 Teaching scope — compose into VAP for fleet use
MCP tool bridge See LoopForge / VAP MCP docs
AegisAI gateway No side effects in pattern demo
Pytest regression pytest -q in repo

Live Demo Part of Curriculum Agent Patterns License: MIT

Part 4 of 5 in the Curriculum Agent Patterns series.

Curriculum teaching stub (compose into VAP for production graphs) of the Multi-Agent System pattern — specialized roles, delegation, and coordinated handoffs between agents.

# Pattern Repository Use when
1 ReAct react-agent-pattern Tool use + reasoning loops
2 Reflection reflection-agent-pattern Self-critique and improve output
3 Plan-Execute plan-execute-agent-pattern Decompose goals into steps
4 Multi-Agent this repo Specialized role delegation
5 Swarm swarm-agent-pattern Parallel autonomous agents

▶ Live demo · 📖 Full series roadmap · Compose in production — AI Content Factory (separate repo)


What you'll learn

  • Role-specialized agents (researcher, writer, reviewer) with clear contracts
  • Orchestrator delegates tasks and merges outputs
  • Shared state vs. message-passing tradeoffs
  • Boundaries that map to LangGraph / production service splits

Quick start

python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
python -m multi_agent_system_pattern
pytest

Runs without external API keys using deterministic stubs.

cp .env.example .env

See docs/LOCAL_DEVELOPMENT.md and docs/ARCHITECTURE.md.

Path to production (compose — not this stub)

This repo is a curriculum stub. For production composition, see AI Content Factory: Research → Content → SEO/Visual → HITL → Publisher agents on LangGraph.

▶ ACF live demo

Interview map

Business function: Minimal LangGraph teaching stub for one agent pattern (compose into VAP for production).

Staff+ prep crosswalk — playbook · study UI · Practice Arena · org matrix. Only entries this repo honestly exercises.

Category Entry Fit
System design Agent tool-use / orchestration (md) Pattern slice only — not a full platform
Coding Clone a graph (cycle-safe) (md) Light — graph structure intuition for LangGraph

Related

⭐ Star the repo if this pattern helps your work.

About

Multi-agent system pattern — specialized roles and delegation

Topics

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages