A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

Autonomous self-improving multi-swarm AI platform with CRDT state, memory, simulation, execution governance, and verified repair loops.

Self-improving multi-level optimization & scientific discovery with meta-meta-learning

A framework for building AI-driven systems that execute work, observe outcomes, learn from failures, and continuously improve their code, processes, and operating procedures.

Automate crypto trading strategies with AI agents using evolution, high-fidelity backtesting, and live execution on DEX and CEX platforms.

Autonomous, evidence-gated improvement loop for any codebase — Praxis truth kernel + Janus adversarial council (Explorer/Red Team). Explore freely. Prove ruthlessly.

Explore curated AutoResearch use cases with optimization traces and open source implementations for each entry

Pure RL Agents: I implemented Q-Learning agents that learn through Self-Play. They play against each other to get smarter without human help! Symmetry Optimization: To make them "genius" faster, I added logic so they understand that a board mirrored left-to-right is the same situation. This cuts the learning time in half!

Compare AdaL and Claude Code on Autoresearch benchmarks to find better hyperparameters, run more experiments, and converge faster

A recursive research system that improves how AI agents are organized across fresh reasoning problems.