Entry
Appears in 4 awesome lists
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)
Section: Autonomous Research Systems (2023-2025 Breakthroughs) · 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)
Section: General-purpose descendants · AIDE: Tree-search ML engineering agent that autonomously improves model performance via iterative code generation and evaluation.
Section: Code AI · Open-source ML engineering agent that uses tree search to explore solution spaces. Automates machine learning experimentation from data analysis to model training. Paper.
Section: AutoML · AIDE is an open-source ML engineering agent that uses a tree search algorithm to autonomously explore, implement, and evaluate solution strategies for machine learning tasks.
Continue is an open-source autopilot plugin for VS Code and JetBrains, enhancing coding with LLMs through features like task and tab autocomplete, natural language edits, file generation, and customization options, available under the Apache 2.0 license github | website
Tabby is a self-hosted, open-source AI coding assistant similar to GitHub Copilot, featuring a self-contained setup with no DBMS/cloud dependency, OpenAPI for easy integration, consumer-grade GPU support, and a full-feature admin UI in its latest release github | website | docs
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.
Deterministic scheduler for 40+ CLI coding agents running in parallel git worktrees with an HMAC-signed audit chain, signed agent cards, and per-artefact lineage. The zero-LLM coordination loop and tamper-evident audit trail make it the only open-source orchestrator designed for…
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)
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…
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…