# HKUDS/AI-Researcher

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

Repository: https://github.com/HKUDS/AI-Researcher
Canonical: https://ross.abutalabs.com/products/ai-researcher
Homepage: https://arxiv.org/abs/2505.18705
Language: Python
License Family: other
Topics: ai-researcher
Last push: 2025-10-16T06:47:34+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 38
- inputs: {"age_days": 540, "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 5701, forks 721 (observed 2026-08-28T04:09:28.084996+00:00)

## What it is
AI-Researcher is an autonomous research system that orchestrates the full scientific research pipeline—from literature review and hypothesis generation to algorithm implementation and manuscript preparation—using LLM-powered agents. It accepts research ideas or reference papers and produces implementation code and publication-ready drafts with minimal human intervention.

## Use cases
- automate end-to-end AI research from idea to paper
- generate research paper drafts from a research idea
- automatically implement algorithms described in reference papers
- run literature reviews and hypothesis generation with AI agents
- benchmark autonomous research systems with Scientist-Bench
- accelerate scientific experimentation with LLM agents

## When to choose
- you want to automate or accelerate AI research workflows
- you need an open-source autonomous research agent framework
- you want to reproduce or extend published autonomous-research benchmarks

## When to avoid
- you need a permissively licensed project (no license is provided)
- you require fully verified, human-quality research output without review
- you need a lightweight tool rather than a heavy multi-agent LLM pipeline

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, machine-learning, workflow-automation, data-science
- domain: artificial-intelligence, large-language-models, data-science
- platform: python, self-hosted
- tags: autonomous-research, scientific-discovery, llm-agents, paper-writing, literature-review, neurips-2025, ai-agents, automation, docker

## Member repositories
- HKUDS/AI-Researcher (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.084996+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 2026-08-29T17:53:34.077099+00:00, confidence not recorded.
  - readme: https://github.com/HKUDS/AI-Researcher (fetched 2026-08-28T04:09:28.084996+00:00, sha dc6b34db1df3)
  - homepage: https://arxiv.org/abs/2505.18705 (fetched 2026-08-29T08:49:12.755785+00:00, sha eb4aa7d9a9bf)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:49:12.766843+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:49:12.770840+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:49:12.774448+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:49:12.768809+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.