OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Research Agents

Nanoresearch

Nanoresearch is an open-source autonomous AI research system that generates and executes experiments, analyzes their results, creates figures and produces complete LaTeX papers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Nanoresearch — OpenViST project profile in Research Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a research workflow needs generated experiments and a paper draft tied to collected training results and intermediate artifacts.

Who it is for

  • Researchers prototyping machine-learning ideas
  • Teams running experiment-backed benchmark workflows
  • Developers building self-hosted AI research pipelines
  • Claude Code users who want a research orchestration mode

Documented uses

  • Turn a research topic into an experiment plan and generated training code
  • Submit documented local or SLURM training jobs and collect results
  • Analyze experiment logs and create result figures
  • Assemble code, data, references and results into a LaTeX research paper
Before you choose

Requirements & limits

The repository is public, open source and licensed under MIT. It documents Python 3.10 or later, CLI access, self-hosted execution and a Claude Code mode.

  • The workflow supports local and SLURM execution, while another GPU-cluster backend requires modification.
  • Outputs include paper.tex, paper.pdf, references.bib, figures, code and data.
  • The CLI offers both streaming logs and a full-screen TUI.
  • The pipeline is divided into ideation, planning, setup, coding, execution, analysis, figure generation, writing and review stages.
  • Claude Code integration is Verified by the repository description.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the documented Nanoresearch workflow

Prepare Nanoresearch for its documented Python-based local or SLURM execution workflow.

Before you start

  • Access to the public Nanoresearch repository
  • Python 3.10 or later
  • A local execution environment or a SLURM GPU cluster for the documented execution paths

Steps

  1. Obtain the Nanoresearch repository from its public GitHub project.

  2. Prepare a Python 3.10-or-later environment.

  3. Choose the documented local or SLURM execution path.

  4. Use the CLI or the documented Claude Code mode to orchestrate the research workflow.

Expected outcome

A prepared Nanoresearch workspace with an available CLI or Claude Code entry point for the research pipeline.

Guide limitations

  • The repository evidence does not specify installation commands, dependency commands or configuration values.
  • Using a different GPU-cluster backend requires modification because no adapter for one is documented.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
OpenRaiser/NanoResearch · Official homepage title · retained in its source language
How we review sourcesSuggest a correction