AI Research / Multi-agent systems
Open-source multi-agent protocol for AI research agents. It pairs a tool-using Scientist with a question-only advisor that can only ask questions and approve plans, and the README includes quick-start setup plus notes on reproducing results on MLE-bench/Kaggle tasks.
The page clearly describes an AI-powered research-agent protocol, shows concrete repo contents, and gives usable setup and reproduction instructions. It also includes a specific mechanism that makes the project stand out: a question-only advisor that gates the next experiment with [APPROVED].
The crawl gives strong setup detail, but visitors still cannot tell the full runtime cost, exact model requirements, or how easy it is to apply beyond the paper-style benchmark workflow.
Last evaluated 78 days ago. Current rank #1398. Down 2 spots in the rankings.
An autonomous research system that runs on a single workstation and aggressively checks its own claims with adversarial self-verification, replication, and calibration audits.
An MCP-based research agent that searches live web data through SQL and publishes reports with the full query and tool trajectory.
Uno is a research repository for speeding up LLM inference with discrete diffusion and lossless multi-token decoding. The repo includes inference, training, and evaluation code, plus installation steps, checkpoints, and example workflows.
An arXiv paper describing an open library of 163 procedural skills for research agents across 16 scientific areas, with versioned instruction files and accompanying reference material or runnable scripts.
