# google-gemini/gemini-fullstack-langgraph-quickstart

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Repository: https://github.com/google-gemini/gemini-fullstack-langgraph-quickstart
Canonical: https://ross.abutalabs.com/products/gemini-fullstack-langgraph-quickstart
Homepage: https://ai.google.dev/gemini-api/docs/google-search
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: gemini, gemini-api
Last push: 2026-06-14T05:25:52+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 35, longevity 33
- inputs: {"age_days": 468, "days_push": 80, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18322, forks 3071 (observed 2026-08-28T04:11:26.576870+00:00)

## What it is
A quickstart template demonstrating a fullstack AI research agent built with a React frontend and a LangGraph backend powered by Google Gemini. The agent iteratively generates search queries, grounds answers with Google Search, reflects on gaps, and returns cited answers.

## Use cases
- build a fullstack AI agent with Gemini and LangGraph
- learn how to build a research agent with citations
- get started with LangGraph and Gemini 2.5
- create a chatbot that searches the web and cites sources
- example React frontend with LangGraph backend
- build a deep research app with Gemini

## When to choose
- you want a working template for a Gemini + LangGraph research agent
- you want to learn agentic search-reflection loops with citations
- you want a React + FastAPI/LangGraph fullstack starting point

## When to avoid
- you need a production-ready application rather than a demo template
- you use LLM providers other than Gemini
- you want a framework or library rather than example code

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, rag, web-framework, chatbot
- domain: artificial-intelligence, web-development, tutorials
- platform: python, cross-platform
- tags: gemini, langgraph, react, fastapi, quickstart, fullstack, google-search-grounding, ai-agents, retrieval-augmented-generation, nodejs, web-server

## Member repositories
- google-gemini/gemini-fullstack-langgraph-quickstart (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.576870+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:02:04.775845+00:00, confidence not recorded.
  - readme: https://github.com/google-gemini/gemini-fullstack-langgraph-quickstart (fetched 2026-08-28T04:11:26.576870+00:00, sha e226f47f892b)
  - homepage: https://ai.google.dev/gemini-api/docs/google-search (fetched 2026-08-29T07:59:59.135701+00:00, sha 6cf70e5eecb4)
  - site_page: https://ai.google.dev/gemini-api/docs (fetched 2026-08-29T07:59:59.144874+00:00, sha 11489b3a3b69)
  - site_page: https://ai.google.dev/gemini-api/docs/get-started (fetched 2026-08-29T07:59:59.147018+00:00, sha 0d97879d85d3)
  - site_page: https://ai.google.dev/gemini-api/docs/api-key (fetched 2026-08-29T07:59:59.150208+00:00, sha 7aacb7b0841e)
  - site_page: https://ai.google.dev/gemini-api/docs/pricing (fetched 2026-08-29T07:59:59.152479+00:00, sha 63fb7a02921f)
  - site_page: https://ai.google.dev/gemini-api/docs/coding-agents (fetched 2026-08-29T07:59:59.155286+00:00, sha 3c57684e19de)
  - site_page: https://ai.google.dev/gemini-api/docs/models (fetched 2026-08-29T07:59:59.157487+00:00, sha 6415425758d4)
  - site_page: https://ai.google.dev/gemini-api/docs/latest-model (fetched 2026-08-29T07:59:59.159535+00:00, sha f4ac326d927e)
  - site_page: https://ai.google.dev/gemini-api/docs/image-generation (fetched 2026-08-29T07:59:59.161739+00:00, sha 417b11c2f0da)
- Data as of 2026-08-30T08:39:29.467469+00:00.