# reworkd/AgentGPT

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

Repository: https://github.com/reworkd/AgentGPT
Canonical: https://ross.abutalabs.com/products/agentgpt
Homepage: https://agentgpt.reworkd.ai
Language: TypeScript
License: GPL-3.0
License Family: copyleft
Topics: agent, autogpt, agi, openai, gpt, baby-agi, next, t3, t3-stack, langchain, agentgpt, llm, agents, ai, ai-agents
Archived: true
Last push: 2025-04-29T01:19:32+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 18, release rhythm 8, longevity 88
- inputs: {"age_days": 1245, "days_push": 492, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 36303, forks 9271 (observed 2026-08-28T04:12:01.021336+00:00)

## What it is
AgentGPT is a web application for assembling, configuring, and deploying autonomous AI agents directly in the browser. Users name a custom AI agent, give it a goal, and it iteratively plans tasks, executes them, and learns from results using OpenAI models.

## Use cases
- deploy autonomous ai agents in browser
- create an ai agent that works toward a goal
- auto-gpt style agent in the browser
- have an llm plan and execute tasks automatically
- build a research agent that compiles a report
- self-host an ai agent platform
- experiment with babyagi-style task loops

## When to choose
- you want a browser-based, no-code way to run autonomous AI agents
- you want to self-host an open-source AutoGPT alternative with a polished UI
- you want to experiment with goal-driven LLM agents without writing code

## When to avoid
- you need a programmatic agent framework or SDK to embed in your own code
- you need production-grade reliability or fine-grained control over agent behavior
- you don't have an OpenAI API key or want to avoid API costs

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, chatbot, web-scraping, prompt-engineering
- domain: large-language-models, artificial-intelligence, web-development
- platform: python, self-hosted, cross-platform
- tags: autonomous-agents, nextjs, fastapi, openai, langchain, browser-based, t3-stack, mysql, ai-agents, automation, web-server, docker, nodejs

## Member repositories
- reworkd/AgentGPT (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.021336+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 2026-08-29T16:26:42.640775+00:00, confidence not recorded.
  - readme: https://github.com/reworkd/AgentGPT (fetched 2026-08-28T04:12:01.021336+00:00, sha 83b0feaba863)
  - homepage: https://agentgpt.reworkd.ai (fetched 2026-08-29T07:48:03.429129+00:00, sha bd49aabd105f)
  - site_page: https://reworkd.ai/docs (fetched 2026-08-29T07:48:03.438630+00:00, sha 382f64c93743)
- Data as of 2026-08-30T08:39:29.467469+00:00.