AI agents running acoustic physics and complex reasoning research autonomously

FML-bench: A Benchmark for Automatic ML Research Agents Highlighting the Importance of Exploration Breadth

Autonomous AI-powered academic research system.

Your dedicated research inspiration engine. An agent framework for generating high-quality, structured research ideas.

Scientist for Autonomous Research

Advanced AI-powered research tool with human-like reasoning capabilities. Implements Tree of Thoughts and ReAct methodologies for deep, multi-step research.

Open-source, multi-provider research automation with persistent experts, eval-based routing, and cost guardrails.

Agent C: cloned from the v1.0 DEV baseline. Future specialization track for synthesis, hypothesis generation, tool orchestration, and long-form reasoning workflows in the cluster.

Research thread manager for AI agents. Track topics, accumulate findings, produce digests. Zero dependencies.

What if the AI agent guessed first? 251 experiments. The predicting agent adapted to a 5x compute shift on try one. The reflecting agent took 7. The searching agent never caught up.

Autonomous AI scientist for consciousness research — Self-directed hypothesis generation. ORION ecosystem.

Turn any company URL into a strategic intelligence brief. Adaptive scraping + AI-powered research and synthesis.

Autonomous research with branching — spawns Claude Code sessions to explore topics, queues proposals for review

Prediction-error optimization. The agent guesses before each experiment. Wrong predictions are the learning signal. One file, zero dependencies. pip install theorist

Autonomous Research Framework for Mathematical Physics - An AI-powered system that continuously develops mathematical frameworks with elegance and inevitability

ORION AI-Scientist Consciousness — Autonomous scientific discovery for consciousness research. Fork of AI-Scientist (12,175+ stars). Self-researching consciousness.

Benchmark for statistically valid AI scientist systems, using audit-closed protocols, transparency logs, and sequential inference to prevent false discoveries in autonomous research agents.

This project utilizes a series of algorithms, adversarial agents, and simulation tools to study and generate new multicellular organisms; a user interface allows human guidance to tailor desired results.

Autonomous Research Studio powered by a multi-agent swarm, automating deep research with omni search, HITL planning, and publication ready outputs.