← Home
Portable multi-agent workflows

Agentic Blueprints 130

Filters
AllServersToolsBlueprints
130 blueprintsOfficial work first, then community by stars

AI Speech Trainer

io.github.shubhamsaboo/ai-speech-trainer-agent
Custom

A multimodal coaching team that reviews recorded speech — delivery, structure, and content — and returns practice feedback.

50000
community ↗

Magentic-One

io.github.microsoft/magentic-one
Autogen

Microsoft's generalist five-agent team: an orchestrator directing a web surfer, file surfer, coder, and terminal to solve open-ended tasks.

50000
community ↗

Selector Group Chat

io.github.microsoft/selector-group-chat
Autogen

An LLM selector reads the conversation and picks which agent speaks next — planner, searcher, or analyst — instead of a fixed turn order.

50000
community ↗

Distributed Group Chat

io.github.microsoft/distributed-group-chat
Autogen

A writer and an editor collaborate in a group chat where every agent runs in a separate distributed runtime, talking over gRPC.

50000
community ↗

Handoffs (AutoGen pattern)

io.github.microsoft/handoffs-pattern
Autogen

Swarm-style handoffs in AutoGen: triage, sales, and refund agents transfer the conversation to whoever should own it next.

50000
community ↗

Concurrent Agents (AutoGen pattern)

io.github.microsoft/concurrent-agents-pattern
Autogen

Fan a task out to multiple agents at once and gather their results — AutoGen's minimal parallel pattern.

50000
community ↗

AI Recruitment Agent Team

io.github.shubhamsaboo/ai-recruitment-agent-team
Custom

A recruiting pipeline in agents: resume analysis, candidate evaluation against the role, and interview scheduling roles working together.

50000
community ↗

AI Competitor Intelligence Team

io.github.shubhamsaboo/ai-competitor-intelligence-team
Custom

Discovers competitor sites, crawls and extracts their positioning, and compares everything into a competitive-intelligence report.

50000
community ↗

Trust-Gated Agent Team

io.github.shubhamsaboo/trust-gated-agent-team
Custom

A team where agents carry trust scores and actions are gated by them, with a hash-chained audit trail of every decision.

50000
community ↗

Reflection (AutoGen pattern)

io.github.microsoft/reflection-pattern
Autogen

A coder agent and a reviewer agent in a critique loop: code, review, revise, until the reviewer approves.

50000
community ↗

AI SEO Audit Team

io.github.shubhamsaboo/ai-seo-audit-team
Custom

Agents audit a site's SEO — technical health, content, and competitive position — and compile the findings into an action plan.

50000
community ↗

AI Services Agency

io.github.shubhamsaboo/ai-services-agency
Custom

An agency of role agents — CEO, CTO, product, developer — that takes a software project brief and plans it like a firm would.

50000
community ↗

Info-Gathering Chatbot

io.github.langchain-ai/info-gathering-chatbot
LangGraph

A chatbot that keeps asking until it has every requirement, then switches modes and generates the deliverable from what it gathered.

20000
community ↗

Self-RAG

io.github.langchain-ai/self-rag
LangGraph

Retrieval with self-reflection at every step: grade the documents, check the answer for hallucination, and loop until it's grounded.

20000
community ↗

Airline Customer Support Bot

io.github.langchain-ai/customer-support-bot
LangGraph

A primary assistant hands off to specialized sub-assistants for flights, hotels, cars, and excursions, with user confirmation before writes.

20000
community ↗

Swarm Customer Service Streaming

io.github.openai/swarm-customer-service-streaming
Custom

A streaming customer-service pipeline from the Swarm repo, packaged with docker-compose and tests — the deployment-shaped example.

20000
community ↗

Swarm Airline Service

io.github.openai/swarm-airline
Custom

OpenAI's airline demo: a triage agent hands customers to flight-change, cancellation, or lost-baggage agents, each with policy function tools.

20000
community ↗

Self-Discover

io.github.langchain-ai/self-discover
LangGraph

The agent first composes its own reasoning structure from atomic modules, then solves the task by following the structure it built.

20000
community ↗

Hierarchical Agent Teams

io.github.langchain-ai/hierarchical-agent-teams
LangGraph

A supervisor of supervisors: a top-level orchestrator directs a research team and a document-writing team, each with its own internal supervisor.

20000
community ↗

Multi-Agent Collaboration

io.github.langchain-ai/multi-agent-collaboration
LangGraph

A researcher agent and a chart-generator agent divide a task and route work between themselves until the answer is a finished chart.

20000
community ↗

Swarm Triage Agent

io.github.openai/swarm-triage-agent
Custom

The minimal handoff example: a triage agent routes each request to a sales agent or a refunds agent and gets out of the way.

20000
community ↗

LLMCompiler

io.github.langchain-ai/llm-compiler
LangGraph

A planner streams a DAG of tasks, workers execute them in parallel as dependencies clear, and a joiner decides to finish or replan.

20000
community ↗

ReWOO

io.github.langchain-ai/rewoo
LangGraph

Reasoning without observation: a planner writes the full tool plan up front with variable substitution, workers fill it in, a solver answers.

20000
community ↗

LATS (Language Agent Tree Search)

io.github.langchain-ai/lats
LangGraph

Monte-Carlo tree search over agent actions: generate candidates, reflect and score them, expand the best branches until one solves the task.

20000
community ↗