Awesome Ai For Science
Section: Autonomous Research Systems (2023-2025 Breakthroughs) · Fully autonomous research from idea to paper with multi-agent debate, citation verification, and OpenClaw integration (11K+ stars, 2026)
Entry
Appears in 5 awesome lists
April 2026 open-source human-in-the-loop system with six intervention modes (full-auto, gate-only, checkpoint, step-by-step, co-pilot, custom), SmartPause confidence-driven dynamic suspension, and Intervention Learning from human corrections. The cost-guardrail system — aborting runs that exceed…
Section: Autonomous Research Systems (2023-2025 Breakthroughs) · Fully autonomous research from idea to paper with multi-agent debate, citation verification, and OpenClaw integration (11K+ stars, 2026)
Section: Research-agent systems · 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.
Section: Human-in-the-Loop · April 2026 open-source human-in-the-loop system with six intervention modes (full-auto, gate-only, checkpoint, step-by-step, co-pilot, custom), SmartPause confidence-driven dynamic suspension, and Intervention Learning from human corrections. The cost-guardrail system — aborting runs that exceed…
Section: 研究 Research
Section: Other · Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
February 2026 release making human oversight a native workflow primitive: suspend execution at critical decision points, expose review-and-edit UI mid-flow, and route subsequent execution based on human action (approve/reject/escalate). Demonstrates how HITL transitions from bolt-on approval gates…
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.
Andrej Karpathy's autonomous LLM research framework: AI agent runs overnight experiments on a real training setup, auto-editing code→5min training→evaluation in a loop, ~100 experiments per night on a single GPU
First fully autonomous open-ended scientific discovery system with official implementation: hypothesis→experiment→writing→review simulation (13.8K+ stars, 2024)
LLM-driven machine learning engineering agent using agentic tree search to autonomously draft, debug and benchmark ML code; wins 4× more medals than the best linear agent on OpenAI's MLE-Bench (75 Kaggle competitions) (1.3K+ stars, MIT License)
Open-source implementation of AlphaEvolve's evolutionary coding agent paradigm, enabling LLMs to autonomously discover and optimize algorithms through iterative evolution, matching the approach behind DeepMind's breakthrough matrix multiplication discovery (6.2K+ stars, 2025)
Open-source LLM-powered R&D agent framework automating data-driven AI solution building through automated research, development, and evolution; achieves top open-source performance on MLE-Bench with dual Researcher-Developer agents and supports research copilot, data mining, Kaggle, and quant R&D…
Full-stack local AI research workspace spanning literature review, ideation, experiments, academic writing, and research artifact production (OpenLAIR, 1.2K+ stars, 2026)