Multi-agent orchestration on top of Claude Code. Supervisor delegates, specialists execute, you gate. Browser-based IDE; local-first.
Build autonomous AI workflows with multi-agent orchestration, intelligent routing, hybrid RAG, knowledge graphs, MCP tools, persistent memory, and human-in-the-loop execution.
Production ready LangGraph multi-agent orchestration template with supervisor routing, FastAPI + Streamlit chat UI, MCP tool calling, local RAG + knowledge graph retrieval, PostgreSQL memory, per-user auth, and CI/CD.
Two files. ~250 tokens. Zero drift.
ISC-CodeConnect is a sophisticated multi-agent Retrieval-Augmented Generation (RAG) system specifically designed for Salesforce development. Built with LangGraph and powered by IBM WatsonX.ai Granite models, it orchestrates a network of specialized AI agents .
One MCP server exposing many tools, multiple LangGraph agents each bound to a filtered subset, and a supervisor routing each question to the right agent - deployed with a browser chat UI. The point: tool filtering is a client-side concern, and it is one line.
LangGraph multi-agent orchestrator template — dynamic Supervisor routing, 5 example specialist agents, and optional human-in-the-loop review. POC tier of the Multi-Agent Orchestrator Template family: in-memory state, no auth, minutes to first run.
Build a production-ready multi-agent AI system using LangGraph, MCP, Supervisor Agents, Guardrails, Observability, and Human-in-the-Loop. Learn to coordinate specialized agents, integrate tools, add safety controls, enable approvals, and monitor agent workflows.
One command. Real tmux parallelism. 3-layer mechanical verification.
Prisma is a Python-based multi‑agent coding assistant that uses a supervisor agent to break down natural‑language coding requests into parallel subtasks handled by specialized sub‑agents, then synthesizes their results into a single, clear response.
Open, inspectable multi-agent research workbench: Supervisor → Planner(ToT) → parallel Researchers(ReWOO) → Critic → footnoted Writer, with trajectory + faithfulness eval.
Multi-agent orchestration using the Supervisor pattern with LangGraph, LangChain and Mistral AI — with Langfuse tracing.
Demo with a conversational AI assistant that lets you buy tickets through natural language chat.
File-first control plane for supervising Codex, Claude Code, Antigravity and other AI agents toward production
To associate your repository with the supervisor-agent topic, visit your repo's landing page and select "manage topics."