InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.

This is the official repository for HypoGeniC (Hypothesis Generation in Context) and HypoRefine, which are automated, data-driven tools that leverage large language models to generate hypothesis for open-domain research. For more details, please see the original paper using the link below.

Research feedback grounded in the papers that define your field

Systematically learn and evaluate the latent geometry of high-dimensional data, with a focus on scRNAseq analysis

Official implementation of the ACL 2024: Scientific Inspiration Machines Optimized for Novelty

AGATHA: Automatic Graph-mining And Transformer based Hypothesis generation Approach

A platform for Interactive AI-assisted Hypothesis Generation [ACL 2025]

Deep Critical Research Agent : The first AI-driven Critical Analysis to turn the huge amount of preclinical biology data and information into knowledge and hence disease cures.

Locally hosted AI Agent Python Tool To Generate Novel Research Hypothesis + Titles + Abstracts

Symbolic XAI explainable machine learning & non-linear regression platform for MATLAB

AstroAgents: Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data

Workflow to generate interactive feature selection report for cross-sectional or longitudinal studies

Official code for the paper: "Simple LLM Baselines are Competitive for Model Diffing"

A open source Literature Based Discovery system, using Groovy & Grails, including a re-implementation of the Arrowsmith algorithm(s)

How do you train retrievers to find inspirations? [ACL 2025]

A Python library for creating and exploring structured review articles.

Autonomous scientific discovery engine - 82 discovery modules, 16-phase pipeline with refinement and reflexion. GFlowNet hypothesis tournaments, adversarial skeptic review, multi-agent debate, causal reasoning, knowledge graphs, 17 domain ontologies. Terminal-native.

IRIS Gate Protocol: Cross-architecture phenomenological convergence research (RFC v0.2)

Scientific agent skills for Claude Code and Codex that turn research goals into auditable hypothesis generation, review, ranking, evolution, and synthesis.