Agentic Blueprints 40

WebVoyager

io.github.langchain-ai/web-voyager

LangGraph

A vision-enabled browser agent that looks at annotated screenshots and decides where to click, scroll, and type until the task is done.

SQL Agent

io.github.langchain-ai/sql-agent-tutorial

LangGraph

An agent that explores a database's schema, writes a query, double-checks it with a dedicated checker step, and recovers from execution errors.

Adaptive RAG

io.github.langchain-ai/adaptive-rag

LangGraph

Routes each question to the right retrieval strategy, grades what comes back, and falls back to web search when the index can't answer.

Chatbot Simulation Evaluation

io.github.langchain-ai/agent-simulation-evaluation

LangGraph

A simulated-user agent plays the customer against your chatbot so you can evaluate the whole conversation before real users do.

Corrective RAG

io.github.langchain-ai/corrective-rag

LangGraph

Grades retrieved documents for relevance and, when they fail the grade, falls back to web search before answering.

Code Assistant with Self-Correction

io.github.langchain-ai/code-assistant

LangGraph

Generates code grounded in docs, executes it, and loops on the errors — reflecting on failures before retrying until tests pass.

USACO Competitive Programming Agent

io.github.langchain-ai/usaco-agent

LangGraph

Solves olympiad programming problems with episodic retrieval of similar solved problems plus a reflect-and-retry execution loop.

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.

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.

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.

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.

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.

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.

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.

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.

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.