# HKUDS/AutoAgent

"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"

Repository: https://github.com/HKUDS/AutoAgent
Canonical: https://ross.abutalabs.com/products/autoagent
Homepage: https://arxiv.org/abs/2502.05957
Language: Python
License: MIT
License Family: permissive
Topics: agent, llms
Last push: 2025-10-16T06:35:28+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 47, release rhythm 35, longevity 40
- inputs: {"age_days": 573, "days_push": 321, "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 9753, forks 1360 (observed 2026-08-28T04:10:37.077875+00:00)

## What it is
AutoAgent is a fully-automated, zero-code framework for creating and deploying LLM agents using natural language alone. It acts as an autonomous Agent Operating System with self-managing workflows, tools, and multi-agent orchestration, evaluated on the GAIA benchmark.

## Use cases
- build llm agents without coding
- create ai agents from natural language descriptions
- orchestrate multi-agent workflows conversationally
- customize agent tools and workflows via chat
- general ai assistant for task automation
- no-code agent development for non-programmers

## When to choose
- you want to build LLM agents without programming skills
- you need natural-language-driven agent and workflow creation
- you want a multi-agent general AI assistant
- you prefer a lightweight, MIT-licensed framework with active development

## When to avoid
- you need fine-grained programmatic control over agent internals
- you require a mature, production-hardened framework like LangChain or AutoGen
- your project needs strict deterministic pipelines rather than LLM-driven automation

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, workflow-automation, chatbot
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: zero-code, natural-language, multi-agent, agent-operating-system, no-code-ai, gaia-benchmark, ai-agents, automation

## Member repositories
- HKUDS/AutoAgent (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:37.077875+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 2026-08-29T17:21:11.727153+00:00, confidence not recorded.
  - readme: https://github.com/HKUDS/AutoAgent (fetched 2026-08-28T04:10:37.077875+00:00, sha cdf11294779a)
  - homepage: https://arxiv.org/abs/2502.05957 (fetched 2026-08-29T08:20:46.762621+00:00, sha 4b721eef0449)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:20:46.766963+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:20:46.788976+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:20:46.791485+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:20:46.769107+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.