# HKUDS/Auto-Deep-Research

"Your Fully-Automated Personal AI Assistant"

Repository: https://github.com/HKUDS/Auto-Deep-Research
Canonical: https://ross.abutalabs.com/products/auto-deep-research
Homepage: https://arxiv.org/abs/2502.05957
Language: Python
License Family: other
Topics: agent, deep-research, llm
Last push: 2025-10-16T06:38:48+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": 563, "days_push": 321, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1731, forks 247 (observed 2026-08-28T04:05:28.650674+00:00)

## What it is
Auto-Deep-Research is an open-source, cost-efficient alternative to OpenAI's Deep Research, built on the AutoAgent framework. It runs as a fully-automated personal AI assistant that supports many LLM providers via your own API keys, launched with a single command.

## Use cases
- run deep research reports without a $200/month subscription
- automate multi-step research tasks with my own LLM API keys
- use an open-source alternative to OpenAI Deep Research
- chat with an AI assistant that accepts file uploads
- benchmark an agent on GAIA
- use non-OpenAI models like Deepseek or Anthropic for deep research

## When to choose
- you want deep-research-style reports using pay-as-you-go API keys
- you need broad LLM provider support including function-calling and non-function-calling models
- you want a zero-configuration one-command launch

## When to avoid
- you need a permissively licensed dependency (no license is specified)
- you need a fully self-hosted/offline assistant without API keys
- you require production-grade guarantees or long-term support

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, chatbot, cli
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: deep-research, personal-ai-assistant, multi-agent, gaia-benchmark, openai-alternative, no-license, ai-agents

## Member repositories
- HKUDS/Auto-Deep-Research (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:28.650674+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 2026-08-30T03:31:41.031403+00:00, confidence not recorded.
  - readme: https://github.com/HKUDS/Auto-Deep-Research (fetched 2026-08-28T04:05:28.650674+00:00, sha 6ec3f097aa22)
  - homepage: https://arxiv.org/abs/2502.05957 (fetched 2026-08-29T11:08:28.337146+00:00, sha 4b721eef0449)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:08:28.346535+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:08:28.350237+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:08:28.352797+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:08:28.348472+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.