© 2025-2026 AgentX · Community project, not affiliated with any listed agent.
A Webioinfo project · directory data from multiple sources · live metrics from the GitHub API · benchmark observations located via Benchmark Radar
Registry / Autonomous Research Autonomous Research agents 57 research AI agents in autonomous research, tracked with live GitHub metrics, companion-paper metadata and Verified Run reviews from researchers who ran them. The most-starred records right now: autoresearch, DeepResearch, ARIS.
autoresearch karpathy/autoresearch
Stale
AI agents running research on single-GPU nanochat training automatically
100.2k PythonAutonomous Research pushed 8mo agono reviews CompareDeepResearch Alibaba-NLP/DeepResearch
Star counts on cards are live GitHub metrics; full records include papers, licenses and review evidence.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
20.2k 0 PythonAutonomous Research pushed 9mo agono reviews CompareARIS wanshuiyin/Auto-claude-code-research-in-sleep
Active
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.
19.4k PythonAutonomous Research pushed 2d agono reviews CompareRD-Agent microsoft/RD-Agent
Active
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
Microsoft
15.4k PythonAutonomous Research pushed 28d agono reviews CompareAI-Scientist (v1) SakanaAI/AI-Scientist
Stable
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Sakana-AI
15.0k 1.4k Jupyter NotebookAutonomous Research pushed 11mo agono reviews CompareAutoResearchClaw aiming-lab/AutoResearchClaw
Active
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
14.9k PythonAutonomous Research pushed 3mo agono reviews Comparepi-autoresearch davebcn87/pi-autoresearch
Active
Autonomous experiment loop extension for pi
8.2k TypeScriptAutonomous Research pushed 1mo agono reviews CompareAI-Scientist-v2 SakanaAI/AI-Scientist-v2
Stable
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Sakana-AI Nature
7.5k 399 PythonAutonomous Research pushed 11mo agono reviews Compareautoresearch (uditgoenka) uditgoenka/autoresearch
Active
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
6.8k ShellAutonomous Research pushed 19d agono reviews CompareAgentLaboratory SamuelSchmidgall/AgentLaboratory
Stable
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
EMNLP-Findings
5.9k 606 PythonAutonomous Research pushed 1.2y agono reviews CompareAI-Researcher HKUDS/AI-Researcher
Stable
[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat
HKUDS NeurIPS
5.9k 118 PythonAutonomous Research pushed 1.1y agono reviews CompareSearch-R1 PeterGriffinJin/Search-R1
Stable
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
5.6k 1.8k PythonAutonomous Research pushed 1.0y agono reviews CompareEvoScientist EvoScientist/EvoScientist
Active
🔬 Harness Vibe Research with Self-evolving AI Scientists
5.0k 64 PythonAutonomous Research pushed todayno reviews CompareDeepAnalyze ruc-datalab/DeepAnalyze
Active
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师,自动分析大量数据,一键生成专业分析报告!
4.8k 65 PythonAutonomous Research pushed 17d agono reviews CompareOpenScience synthetic-sciences/openscience
Active
The open-source AI workbench for scientific research
4.4k TypeScriptAutonomous Research pushed 3d agono reviews CompareDeepScientist ResearAI/DeepScientist
Stable
Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.
ICLR
3.4k 73 TypeScriptAutonomous Research pushed 5mo agono reviews CompareA blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
3.0k PythonAutonomous Research pushed 29d agono reviews Compareautoresearch-mlx trevin-creator/autoresearch-mlx
Stale
Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.
1.9k PythonAutonomous Research pushed 5mo agono reviews CompareDATAGEN starpig1129/DATAGEN
Active
DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.
1.8k PythonAutonomous Research pushed 2d agono reviews CompareAuto-Deep-Research HKUDS/Auto-Deep-Research
Stable
"Your Fully-Automated Personal AI Assistant"
HKUDS ACL-Findings
1.8k 2 PythonAutonomous Research pushed 1.1y agono reviews CompareShinkaEvolve SakanaAI/ShinkaEvolve
Active
ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬
1.5k 225 PythonAutonomous Research pushed todayno reviews CompareInternAgent InternScience/InternAgent
Active
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
InternScience
1.5k PythonAutonomous Research pushed 4mo agono reviews CompareNanoResearch OpenRaiser/NanoResearch
Active
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
1.3k PythonAutonomous Research pushed 1mo agono reviews CompareOpenResearcher TIGER-AI-Lab/OpenResearcher
Stale
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
TIGER-AI-Lab
1.3k PythonAutonomous Research pushed 5mo agono reviews CompareA Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.
1.2k JavaScriptAutonomous Research pushed 8d agono reviews Comparefunsearch google-deepmind/funsearch
Stable
No description yet — run the GitHub refresh to fetch one.
Nature
1.1k 1.6k Jupyter NotebookAutonomous Research pushed 2.8y agono reviews CompareScienceClaw (beita6969) beita6969/ScienceClaw
Active
Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
1.0k TypeScriptAutonomous Research pushed 10d agono reviews Comparedata-to-paper Technion-Kishony-lab/data-to-paper
Stable
data-to-paper: Backward-traceable AI-driven scientific research
Technion NEJM-AI
837 38 PythonAutonomous Research pushed 1.3y agono reviews Comparefreephdlabor ltjed/freephdlabor
Active
freephdlabor: customizing personalized multiagent systems that researchs 24/7 on your own scientific problem
724 PythonAutonomous Research pushed 3mo agono reviews CompareEurekaClaw EurekaClaw/EurekaClaw
Stale
The official repo of EurekaClaw
696 PythonAutonomous Research pushed 5mo agono reviews CompareScienceClaw (TaichuAI) AgentTeam-TaichuAI/ScienceClaw
Stale
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.
681 PythonAutonomous Research pushed 6mo agono reviews CompareSciAgents lamm-mit/SciAgentsDiscovery
Stable
No description yet — run the GitHub refresh to fetch one.
MIT Advanced-Materials
642 309 PythonAutonomous Research pushed 1.5y agono reviews CompareKosmos: 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
607 130 PythonAutonomous Research pushed 1mo agono reviews CompareCoI-Agent DAMO-NLP-SG/CoI-Agent
Stable
Official code for paper: Chain of Ideas: Revolutionizing Research via Novel Idea Development with LLM Agents
EMNLP-Findings
512 137 PythonAutonomous Research pushed 1.8y agono reviews CompareNoviScl-AI-Researcher NoviScl/AI-Researcher
Stale
No description yet — run the GitHub refresh to fetch one.
416 538 PythonAutonomous Research pushed 1.3y agono reviews CompareCycleResearcher zhu-minjun/Researcher
Stable
CycleResearcher: Improving Automated Research via Automated Review
ICLR
410 186 Jupyter NotebookAutonomous Research pushed 9mo agono reviews CompareInnoClaw SpectrAI-Initiative/InnoClaw
Active
An AI research Agent for scientific innovation.
399 TypeScriptAutonomous Research pushed 3mo agono reviews CompareCodeScientist allenai/codescientist
Stale
CodeScientist: An automated scientific discovery system for code-based experiments
Allen-AI
352 PythonAutonomous Research pushed 8mo agono reviews CompareAutoKaggle multimodal-art-projection/AutoKaggle
Stale
No description yet — run the GitHub refresh to fetch one.
322 92 PythonAutonomous Research pushed 2.0y agono reviews CompareCo-Scientist Kaimen-Inc/Co-Scientist
Active
Open Source Reimplementation of Google Deepmind's Co-Scientist
DeepMind
292 PythonAutonomous Research pushed 4mo agono reviews CompareOpenLens AI jarrycyx/openlens-ai
Active
OpenLens AI: A Fully Autonomous Multimodal Research Agent| OpenLens AI:全自主多模态科研智能体
284 PythonAutonomous Research pushed 2mo agono reviews CompareScienceClaw (MIT LAMM) lamm-mit/scienceclaw
Active
No description yet — run the GitHub refresh to fetch one.
MIT
251 18 PythonAutonomous Research pushed 19d agono reviews CompareDS-Agent guosyjlu/DS-Agent
Stable
Official implementation of "DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning" in ICML'24
ICML
246 177 PythonAutonomous Research pushed 2.0y agono reviews Compare(NeurIPS 2024) AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning
242 14 PythonAutonomous Research pushed 1.4y agono reviews CompareOmniScientist tsinghua-fib-lab/OmniScientist
Stale
No description yet — run the GitHub refresh to fetch one.
Tsinghua
209Autonomous Research pushed 10mo agono reviews CompareDrClaw (InternScience) InternScience/DrClaw
Stale
No description yet — run the GitHub refresh to fetch one.
InternScience
172 PythonAutonomous Research pushed 8mo agono reviews CompareNeuriCo ChicagoHAI/NeuriCo
Active
AI Scientist by Chicago Human+AI Lab
UChicago
164 PythonAutonomous Research pushed 4d agono reviews CompareVirtual-Scientists InternScience/Virtual-Scientists
Stable
[ACL 2025] Multi-Agent System for Science of Science
ACL
146 98 PythonAutonomous Research pushed 1.3y agono reviews Comparehypothesis-generation ChicagoHAI/hypothesis-generation
Stable
This is the official repository for HypoGeniC (Hypothesis Generation in Context) and HypoRefine, which are automated, data-driven tools that leverage large language models to generate hypothesis for open-domain research. For more details, please see the original paper using the link below.
ACL
139 4 PythonAutonomous Research pushed 1.0y agono reviews CompareSciClaw (drpedapati) drpedapati/sciclaw
Active
Paired-scientist AI assistant for reproducible research — lightweight Go runtime, lifecycle hooks, manuscript integration, 12 baseline scientific skills. PicoClaw-compatible.
90 GoAutonomous Research pushed 2d agono reviews CompareMindstorm metauto-ai/Mindstorm
Stale
🧠 Societies of Mind & Economy of Minds
83 1 PythonAutonomous Research pushed 1.7y agono reviews CompareOpen Co-Scientist jataware/open-coscientist
Stale
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.
67 PythonAutonomous Research pushed 9mo agono reviews CompareScienceClaw (Zaoqu-Liu) Zaoqu-Liu/ScienceClaw
Active
Your AI Research Lab That Never Sleeps. 9 agents, 275 skills, 77 databases — from literature to publication, every discipline, zero boundaries.
60 ShellAutonomous Research pushed 9d agono reviews CompareSR-Scientist GAIR-NLP/SR-Scientist
Stale
[ICLR 2026] SR-Scientist: Scientific Equation Discovery With Agentic AI
SJTU ICLR
58 46 PythonAutonomous Research pushed 10mo agono reviews CompareAgentomics BioGeMT/agentomics-ml
Active
Autonomous agentic system for supervised machine learning model development.
Bioinformatics
42 12 PythonAutonomous Research pushed 2d agono reviews CompareOfficial Code of LabOS: the AI-XR Co-Scientist that Sees and Works with Humans
33 12 PythonAutonomous Research pushed 9mo agono reviews CompareClaude Science anthropic.com/claude-science
No repo
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.
Anthropic
Autonomous Research no reviews Compare