uditgoenka/autoresearch - Claude Code skill that generalizes autoresearch into a reusable loop for software, docs, security, shipping, debugging, and other measurable goals.
leo-lilinxiao/codex-autoresearch - Codex-native autoresearch skill with resume support, lessons across runs, optional parallel experiments, and mode-specific workflows.
supratikpm/gemini-autoresearch - Gemini CLI skill that generalises autoresearch to any measurable goal. Gemini-native: uses Google Search grounding as a live verification source inside the loop, true headless overnight mode via --yolo --prompt, and 1M token context. Also works in Antigravity IDE via .agents/skills/.
davebcn87/pi-autoresearch - pi extension plus dashboard for persistent experiment loops, live metrics, confidence tracking, and resumable autoresearch sessions.
drivelineresearch/autoresearch-claude-code - Claude Code plugin/skill port of pi-autoresearch, with a clean experiment-loop workflow and a concrete biomechanics case study.
greyhaven-ai/autocontext - Closed-loop control plane for repeated agent improvement, with evaluation, persistent knowledge, staged validation, and optional distillation into cheaper local runtimes.
jmilinovich/goal-md - Generalizes autoresearch into a GOAL.md pattern for repos where the agent must first construct a measurable fitness function before it can optimize.
mutable-state-inc/autoresearch-at-home - Collaborative fork of upstream autoresearch that adds experiment claiming, shared best-config syncing, hypothesis exchange, and swarm-style coordination across many single-GPU agents.
zkarimi22/autoresearch-anything - Generalizes autoresearch to any measurable metric — system prompts, API performance, landing pages, test suites, config tuning, SQL queries. "If you can measure it, you can optimize it."
Entrpi/autoresearch-everywhere - Cross-platform expansion that auto-detects hardware config and starts the loop. The "glue and generalization" half of autoresearch.
ShengranHu/ADAS - Automated Design of Agentic Systems — ICLR 2025. Meta-agents that invent novel agent architectures by programming them in code.
MaximeRobeyns/self_improving_coding_agent - SICA: Self-Improving Coding Agent that edits its own codebase. ICLR 2025 Workshop paper demonstrating scaffold-level self-improvement on coding benchmarks.
metauto-ai/HGM - Huxley-Gödel Machine for coding agents — applies self-improvement to SWE-bench performance via meta-level optimization.
gepa-ai/gepa - GEPA (Genetic-Pareto) — ICLR 2026 Oral. Reflective prompt evolution that outperforms RL (GRPO) on benchmarks. Optimizes any textual parameters against any metric using natural language reflection.
MrTsepa/autoevolve - GEPA-inspired autoresearch for self-play: mutate code strategies, evaluate head-to-head, rate with Elo/Bradley-Terry, branch from the Pareto front. Agent reads match traces to target mutations. Works as a Claude Code skill.
HKUDS/ClawTeam - Agent swarm intelligence for autoresearch — spawns parallel GPU research directions, distributes work across agents, aggregates results.
Orchestra-Research/AI-Research-SKILLs - Comprehensive skill library including autoresearch orchestration with two-loop architecture (inner optimization + outer synthesis).
WecoAI/aideml - AIDE: Tree-search ML engineering agent that autonomously improves model performance via iterative code generation and evaluation.
weco.ai - Weco: Cloud platform for AIDE with observability, experiment tracking, and managed runs — brings the autoresearch loop into production.
🔬 Research-agent systems
aiming-lab/AutoResearchClaw - End-to-end research pipeline that turns a topic into literature review, experiments, analysis, peer review, and paper drafts; broader than autoresearch, but clearly in the same lineage.
OpenRaiser/NanoResearch - End-to-end autonomous research engine that plans experiments, generates code, runs jobs locally or on SLURM, analyzes real results, and writes papers grounded in those outputs.
wanshuiyin/Auto-claude-code-research-in-sleep - Markdown-first research workflows for Claude Code and other agents, centered on autonomous literature review, experiments, paper iteration, and cross-model critique.
Sibyl-Research-Team/AutoResearch-SibylSystem - Fully autonomous AI scientist built on Claude Code, with explicit AutoResearch lineage, multi-agent research iteration, GPU experiment execution, and a self-evolving outer loop.
eimenhmdt/autoresearcher - Early open-source package for automating scientific workflows, currently centered on literature-review generation with an ambition toward broader autonomous research.
hyperspaceai/agi - Distributed, peer-to-peer research network where autonomous agents run experiments, gossip findings, maintain CRDT leaderboards, and archive results to GitHub across multiple research domains.
SakanaAI/AI-Scientist - The AI Scientist: First comprehensive system for fully automatic scientific discovery. From idea generation to paper writing with minimal human supervision.
SakanaAI/AI-Scientist-v2 - Workshop-level automated scientific discovery via agentic tree search. Removes template dependency from v1, generalizes across research domains.
HKUDS/AI-Researcher - NeurIPS 2025 paper. Full end-to-end research automation: hypothesis → experiments → manuscript → peer review. Production version at novix.science.
openags/Auto-Research - OpenAGS: Orchestrates a team of AI agents across the full research lifecycle — lit review, hypothesis generation, experiments, manuscript writing, and peer review.
SamuelSchmidgall/AgentLaboratory - End-to-end autonomous research workflow: idea → literature review → experiments → report. Supports both autonomous and co-pilot modes.
AgentRxiv - Collaborative autonomous research framework where agent laboratories share a preprint server to build on each other's work iteratively.
JinheonBaek/ResearchAgent - Iterative research idea generation over scientific literature with LLMs. Multi-agent review and feedback loops.
du-nlp-lab/MLR-Copilot - Autonomous ML research framework — generates ideas, implements experiments, analyzes results.
MASWorks/ML-Agent - Reinforcing LLM agents for autonomous ML engineering. Learns from trial and error to improve model performance.
PouriaRouzrokh/LatteReview - Low-code Python package for automated systematic literature reviews via AI-powered agents.
LitLLM/LitLLM - AI-powered literature review assistant using RAG for accurate, well-structured related-work sections in academic writing.
Agent Laboratory - Three-phase research pipeline: Literature Review → Experimentation → Report Writing, with specialized agents for each phase.
WecoAI/aideml - AIDE: AI-Driven Exploration — tree-search-based ML engineering agent that automates experiment design, code generation, and evaluation. Treats ML engineering as code optimization against any metric.
💻 Platform ports and hardware forks
miolini/autoresearch-macos - Widely adopted macOS fork that adapts upstream autoresearch for Apple Silicon / MPS while preserving the original loop shape.
trevin-creator/autoresearch-mlx - MLX-native Apple Silicon port that keeps the upstream fixed-budget val_bpb loop while removing the PyTorch/CUDA dependency entirely.
jsegov/autoresearch-win-rtx - Windows-native RTX fork focused on consumer NVIDIA GPUs, with explicit VRAM floors and a practical desktop setup path.
iii-hq/n-autoresearch - Multi-GPU autoresearch infrastructure with structured experiment tracking, adaptive search strategy, crash recovery, and queryable orchestration around the classic train.py loop.
lucasgelfond/autoresearch-webgpu - Browser/WebGPU port that lets agents generate training code, run experiments in-browser, and feed results back into the loop without a Python setup.
tonitangpotato/autoresearch-engram - Fork with persistent cognitive memory — frequency-weighted retrieval of cross-session knowledge for improved experiment continuity.
Colab/Kaggle T4 port - Adapts autoresearch for free T4 GPUs (Google Colab / Kaggle) with zero cost and zero local setup. Key changes: Flash Attention 3 → PyTorch SDPA, removes H100-only kernel dependency. (upstream issue #208)
ArmanJR-Lab/autoautoresearch - Jetson AGX Orin port with a director — a Go binary that acts as a "creative director" injecting novelty (arxiv papers + DeepSeek Reasoner) into the loop to escape local minima. Includes multi-experiment comparison (baseline vs director-guided) with detailed stall analysis.
🎯 Domain-specific adaptations
mattprusak/autoresearch-genealogy - Applies the autoresearch pattern to genealogy, using structured prompts, archive guides, source checks, and vault workflows to iteratively expand and verify family-history research.
ArchishmanSengupta/autovoiceevals - Uses adversarial callers plus keep-or-revert prompt edits to harden voice AI agents across Vapi, Smallest AI, and ElevenLabs.
chrisworsey55/atlas-gic - Applies the autoresearch keep-or-revert loop to trading agents, optimizing prompts and portfolio orchestration against rolling Sharpe ratio instead of model loss.
RightNow-AI/autokernel - Applies the autoresearch loop to GPU kernel optimization: profile bottlenecks, edit one kernel, benchmark, keep or revert, repeat.
Rkcr7/autoresearch-sudoku - Enhanced autoresearch workflow where an AI agent iteratively rewrites and benchmarks a Rust sudoku solver, ultimately beating leading human-built solvers on hard benchmark sets.
📊 Evaluation & benchmarks
snap-stanford/MLAgentBench - Benchmark suite for evaluating AI agents on ML experimentation tasks. 13 tasks from CIFAR-10 to BabyLM.
openai/mle-bench - OpenAI's benchmark for measuring how well AI agents perform at ML engineering.
chchenhui/mlrbench - MLR-Bench: Evaluating AI agents on open-ended ML research. 201 tasks from NeurIPS/ICLR/ICML workshops.
gersteinlab/ML-Bench - Evaluates LLMs and agents for ML tasks on repository-level code.
THUDM/AgentBench - Comprehensive benchmark for LLM-as-Agent evaluation across 8 distinct environments. ICLR 2024.
📈 Notable use cases and writeups
Shopify Liquid optimization - Tobi Lütke shared an autoresearch-style optimization run on Shopify's Liquid engine, with public traces showing major parse/render speedups and allocation reductions. (tweet, PR with traces)
Driveline baseball biomechanics - Public autoresearch-style experiment loop for pitch-velocity prediction from biomechanics data, with large reported gains in model quality. (tweet)
Tennis XGBoost prediction + reward hacking writeup - Nick Oak documents an autoresearch-inspired loop for tennis match prediction, including where the optimization setup went wrong. (blog · repo · gamed branch)
Vesuvius Challenge ink detection swarm - Multi-agent experimental loop applied to ancient-scroll ink detection, with a strong writeup on cross-scroll generalization improvements. (blog)
Earth system model optimization - Hybrid workflow where an LLM proposes equation structures and a search process tunes parameters, showing how the autoresearch pattern extends into scientific modeling. (tweet, blog)
The Agentic Researcher - Paper: "A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning." Cites autoresearch as the canonical example of automated ML experiment pipelines. (arxiv 2603.15914)
Scaling Autoresearch to GPU Clusters - SkyPilot blog on running autoresearch on H100/H200 clusters with cloud orchestration. (SkyPilot Blog)
Self-Improving Coding Agents - Addy Osmani's practical guide to setting up self-improving agent loops with Claude Code. (article)
autoresearch@home: Distributed AI Research - SETI@home model applied to autoresearch — contribute GPU time to collective model optimization. (Ensue Blog)
Claude Code + AutoResearch for Self-Improving Skills - MindStudio guide to building self-improving AI skills using Claude Code with autoresearch patterns. (article)
100 ML Experiments Overnight - Particula technical breakdown with domain-agnostic fork applications. (article)
PM's Guide to Autoresearch - Product manager's guide covering setup, community forks, and real-world applications. (article)
Autoresearch 101 Builder's Playbook - Substack deep-dive on applying autoresearch patterns to prompts, agents, and workflows with concrete examples. (article)
Kingy AI Technical Breakdown - Detailed technical walkthrough of the autoresearch loop architecture, mutation operators, and fitness function design. (article)
Fortune Feature - Business and industry context on why autoresearch matters for the future of autonomous AI agents. (article)
📚 Related resources
Curated lists and paper collections for AI agents, autonomous systems, and automated research:
WecoAI/awesome-autoresearch - Curated list of AutoResearch use cases with verifiable traces and progress charts, organized by domain (LLM training, GPU kernels, voice agents, trading, etc.).
- Claude Code skill that generalizes autoresearch into a reusable loop for software, docs, security, shipping, debugging, and other measurable goals.
- Codex-native autoresearch skill with resume support, lessons across runs, optional parallel experiments, and mode-specific workflows.
- Gemini CLI skill that generalises autoresearch to any measurable goal. Gemini-native: uses Google Search grounding as a live verification source inside the loop, true headless overnight mode via --yolo --prompt, and 1M token context. Also works in Antigravity IDE via .agents/skills/.
-
- Claude Code plugin/skill port of
- Closed-loop control plane for repeated agent improvement, with evaluation, persistent knowledge, staged validation, and optional distillation into cheaper local runtimes.
- Generalizes autoresearch into a
- Collaborative fork of upstream autoresearch that adds experiment claiming, shared best-config syncing, hypothesis exchange, and swarm-style coordination across many single-GPU agents.
- Generalizes autoresearch to any measurable metric — system prompts, API performance, landing pages, test suites, config tuning, SQL queries. "If you can measure it, you can optimize it."
- Cross-platform expansion that auto-detects hardware config and starts the loop. The "glue and generalization" half of autoresearch.
- Automated Design of Agentic Systems — ICLR 2025. Meta-agents that invent novel agent architectures by programming them in code.
- SICA: Self-Improving Coding Agent that edits its own codebase. ICLR 2025 Workshop paper demonstrating scaffold-level self-improvement on coding benchmarks.
- Alternative self-improving agent architecture with reflection and meta-learning cycles.
- Huxley-Gödel Machine for coding agents — applies self-improvement to SWE-bench performance via meta-level optimization.
- GEPA (Genetic-Pareto) — ICLR 2026 Oral. Reflective prompt evolution that outperforms RL (GRPO) on benchmarks. Optimizes any textual parameters against any metric using natural language reflection.
- GEPA-inspired autoresearch for self-play: mutate code strategies, evaluate head-to-head, rate with Elo/Bradley-Terry, branch from the Pareto front. Agent reads match traces to target mutations. Works as a Claude Code skill.
- Agent swarm intelligence for autoresearch — spawns parallel GPU research directions, distributes work across agents, aggregates results.
- Comprehensive skill library including autoresearch orchestration with two-loop architecture (inner optimization + outer synthesis).
- AIDE: Tree-search ML engineering agent that autonomously improves model performance via iterative code generation and evaluation.
- End-to-end research pipeline that turns a topic into literature review, experiments, analysis, peer review, and paper drafts; broader than autoresearch, but clearly in the same lineage.
- End-to-end autonomous research engine that plans experiments, generates code, runs jobs locally or on SLURM, analyzes real results, and writes papers grounded in those outputs.
- Markdown-first research workflows for Claude Code and other agents, centered on autonomous literature review, experiments, paper iteration, and cross-model critique.
- Fully autonomous AI scientist built on Claude Code, with explicit AutoResearch lineage, multi-agent research iteration, GPU experiment execution, and a self-evolving outer loop.
- Early open-source package for automating scientific workflows, currently centered on literature-review generation with an ambition toward broader autonomous research.
- Distributed, peer-to-peer research network where autonomous agents run experiments, gossip findings, maintain CRDT leaderboards, and archive results to GitHub across multiple research domains.
- The AI Scientist: First comprehensive system for fully automatic scientific discovery. From idea generation to paper writing with minimal human supervision.
- Workshop-level automated scientific discovery via agentic tree search. Removes template dependency from v1, generalizes across research domains.
- NeurIPS 2025 paper. Full end-to-end research automation: hypothesis → experiments → manuscript → peer review. Production version at novix.science.
- OpenAGS: Orchestrates a team of AI agents across the full research lifecycle — lit review, hypothesis generation, experiments, manuscript writing, and peer review.
- End-to-end autonomous research workflow: idea → literature review → experiments → report. Supports both autonomous and co-pilot modes.
- Iterative research idea generation over scientific literature with LLMs. Multi-agent review and feedback loops.
- Autonomous ML research framework — generates ideas, implements experiments, analyzes results.
- Reinforcing LLM agents for autonomous ML engineering. Learns from trial and error to improve model performance.
- Low-code Python package for automated systematic literature reviews via AI-powered agents.
- AI-powered literature review assistant using RAG for accurate, well-structured related-work sections in academic writing.
- Widely adopted macOS fork that adapts upstream autoresearch for Apple Silicon / MPS while preserving the original loop shape.
- MLX-native Apple Silicon port that keeps the upstream fixed-budget
- Windows-native RTX fork focused on consumer NVIDIA GPUs, with explicit VRAM floors and a practical desktop setup path.
- Multi-GPU autoresearch infrastructure with structured experiment tracking, adaptive search strategy, crash recovery, and queryable orchestration around the classic
- Browser/WebGPU port that lets agents generate training code, run experiments in-browser, and feed results back into the loop without a Python setup.
- Fork with persistent cognitive memory — frequency-weighted retrieval of cross-session knowledge for improved experiment continuity.
- Applies the autoresearch pattern to genealogy, using structured prompts, archive guides, source checks, and vault workflows to iteratively expand and verify family-history research.
- Uses adversarial callers plus keep-or-revert prompt edits to harden voice AI agents across Vapi, Smallest AI, and ElevenLabs.
- Applies the autoresearch keep-or-revert loop to trading agents, optimizing prompts and portfolio orchestration against rolling Sharpe ratio instead of model loss.
- Applies the autoresearch loop to GPU kernel optimization: profile bottlenecks, edit one kernel, benchmark, keep or revert, repeat.
- Enhanced autoresearch workflow where an AI agent iteratively rewrites and benchmarks a Rust sudoku solver, ultimately beating leading human-built solvers on hard benchmark sets.
- Benchmark suite for evaluating AI agents on ML experimentation tasks. 13 tasks from CIFAR-10 to BabyLM.
- OpenAI's benchmark for measuring how well AI agents perform at ML engineering.
- MLR-Bench: Evaluating AI agents on open-ended ML research. 201 tasks from NeurIPS/ICLR/ICML workshops.
- Evaluates LLMs and agents for ML tasks on repository-level code.
- Comprehensive benchmark for LLM-as-Agent evaluation across 8 distinct environments. ICLR 2024.
- Curated list of deep research agent papers and systems.
- Papers on LLM agent optimization methods.
- Curated AI agent papers from 2026 — agent engineering, memory, evaluation, workflows, and autonomous systems.
- AI agent research papers updated biweekly via automated arxiv search with curated selection.
- Autonomous agents research papers, updated daily.
- EMNLP 2025 survey on LLMs in scientific discovery.
- Collection of AI Scientist / Robot Scientist papers.
- Curated list of AutoResearch use cases with verifiable traces and progress charts, organized by domain (LLM training, GPU kernels, voice agents, trading, etc.).