Autonomous Research agents

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Autonomous experiment loop extension for pi

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

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

🔬 Harness Vibe Research with Self-evolving AI Scientists

The open-source AI workbench for scientific research

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.

"Your Fully-Automated Personal AI Assistant"

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

🦞+🔬 NanoResearch: The Autonomous AI Research Assistant

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.

🔬🦞 A self-evolving AI research colleague for scientists. 285 skills, zero hallucination, persistent memory.

data-to-paper: Backward-traceable AI-driven scientific research

freephdlabor: customizing personalized multiagent systems that researchs 24/7 on your own scientific problem

The official repo of EurekaClaw

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

No description yet — run the GitHub refresh to fetch one.

Kosmos: An AI Scientist for Autonomous Discovery - An implementation and adaptation to be driven by Claude Code or API - Based on the Kosmos AI Paper - https://arxiv.org/abs/2511.02824

An AI research Agent for scientific innovation.

CodeScientist: An automated scientific discovery system for code-based experiments

OpenLens AI: A Fully Autonomous Multimodal Research Agent｜ OpenLens AI：全自主多模态科研智能体

Open Source Reimplementation of Google Deepmind's Co-Scientist

No description yet — run the GitHub refresh to fetch one.

No description yet — run the GitHub refresh to fetch one.

No description yet — run the GitHub refresh to fetch one.

AI Scientist by Chicago Human+AI Lab

Paired-scientist AI assistant for reproducible research — lightweight Go runtime, lifecycle hooks, manuscript integration, 12 baseline scientific skills. PicoClaw-compatible.

Your AI Research Lab That Never Sleeps. 9 agents, 263 skills, 77 databases — from literature to publication, every discipline, zero boundaries.

Open Coscientist is an open-source adaptation based on Google Research's AI Co-Scientist research paper. We provide an open implementation that generates, reviews, ranks, and evolves research hypotheses using the multi-agent architecture described.

[ICLR 2026] SR-Scientist: Scientific Equation Discovery With Agentic AI

Autonomous agentic system for supervised machine learning model development.

Official Code of LabOS: the AI-XR Co-Scientist that Sees and Works with Humans

Anthropic's closed-source AI workbench for scientists — a coordinating agent with 60+ curated skills and connectors across genomics, single-cell, proteomics, structural biology and cheminformatics, with local, SSH and HPC compute. Beta for Claude Pro, Max, Team and Enterprise.