Updated 1w ago
by OpenRaiser
NanoResearch
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
1.3k GitHub stars (1,341)
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | 0 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | −32 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | −1 |
| Oct 6 | +1 |
| Oct 7 | 0 |
| Oct 8 | +1 |
| Oct 9 | +1 |
| Oct 10 | 0 |
| Oct 11 | +1 |
| Oct 12 | 0 |
| Oct 13 | +1 |
| Oct 14 | +1 |
| Oct 15 | −1 |
| Oct 16 | 0 |
- 16 skills (16 skills found in its SKILL.md files)
- 94 forks (94 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add OpenRaiser/NanoResearch
Asks which skills and agents to install. Just one: npx skills add OpenRaiser/NanoResearch --skill nanoresearch-experiment — add -g for every project.
Claude Code
git clone https://github.com/OpenRaiser/NanoResearchcp -r "NanoResearch/skills/nanoresearch-experiment" ~/.claude/skills/
Copies the nanoresearch-experiment skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add OpenRaiser/NanoResearch
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
nanoresearch-experiment
Generate a Python code skeleton from an experiment blueprint
skills/nanoresearch-experiment/SKILL.md on GitHub (opens in a new tab) -
nanoresearch-ideation
Search academic literature and generate research hypotheses
skills/nanoresearch-ideation/SKILL.md on GitHub (opens in a new tab) -
nanoresearch-planning
Produce an experiment blueprint from a research hypothesis
skills/nanoresearch-planning/SKILL.md on GitHub (opens in a new tab) -
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs
skills/nanoresearch-writing/SKILL.md on GitHub (opens in a new tab) -
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces…
skills/vendor-ai-research/0-autoresearch-skill/SKILL.md on GitHub (opens in a new tab) -
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.
skills/vendor-ai-research/academic-plotting/SKILL.md on GitHub (opens in a new tab) -
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
skills/vendor-ai-research/accelerate/SKILL.md on GitHub (opens in a new tab) -
brainstorming-research-ideas
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
skills/vendor-ai-research/brainstorming-research-ideas/SKILL.md on GitHub (opens in a new tab) -
creative-thinking-for-research
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
skills/vendor-ai-research/creative-thinking-for-research/SKILL.md on GitHub (opens in a new tab) -
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
skills/vendor-ai-research/lm-evaluation-harness/SKILL.md on GitHub (opens in a new tab) -
ml-paper-writing
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
skills/vendor-ai-research/ml-paper-writing/SKILL.md on GitHub (opens in a new tab) -
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing…
skills/vendor-ai-research/ml-training-recipes/SKILL.md on GitHub (opens in a new tab) -
peft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
skills/vendor-ai-research/peft/SKILL.md on GitHub (opens in a new tab) -
ray-data
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
skills/vendor-ai-research/ray-data/SKILL.md on GitHub (opens in a new tab) -
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
skills/vendor-ai-research/skypilot/SKILL.md on GitHub (opens in a new tab) -
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
skills/vendor-ai-research/unsloth/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
Awesome-AIToolsby ikaijua Collection of AI-related utilities. Welcome to submit pull requests /收藏AI相关的实用工具，欢迎提交pull requests
-
awesome-design-skillsby bergside List of 67 awesome DESIGN.md and SKILL.md design skill files for agentic tools like Claude Design, Google Stitch, Codex, Cursor, and other…
-
awesome-ai-persona-skillsby momozi1996 全网最全的、持续更新的、最火爆的 100+ 人格 蒸馏skills 合集｜ 多agent系统 ｜名人/导演/天涯大神/古籍/二次元/职场/情感全品类
-
claude-memby thedotmack Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and inject…
-
adhdby UditAkhourii ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts…
-
Vibe-Skillsby foryourhealth111-pixel Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.