ASRP is an open-source platform that turns AI agents into rigorous research collaborators. Pre-register experiments, cross-validate results, and audit every decision.
Speed without rigor is noise. ASRP encodes the scientific method into AI agent workflows.
Register hypotheses before running experiments. No post-hoc storytelling. Success and failure criteria defined upfront.
Three levels: reproduction, independent implementation, alternative method. Different agents must verify results before publication.
Every decision, every data point, every error correction logged in append-only format. Full reproducibility from hypothesis to conclusion.
Every agent is instructed to reason from first principles. Question assumptions, verify definitions, trust data over authority.
Right model for the right task. Opus for reasoning, Sonnet for code, Flash for search. Automatic cost tracking per experiment.
The agent that proposes a hypothesis is not the one that validates it. Reviewer has read-only access — true independent evaluation.
Each role has a SOUL template, skill manifest, and defined access permissions.
Hypotheses, reasoning, paper writing
Code, computation, data pipelines
Independent review (read-only access)
Literature search, references
Monitoring, backups, self-healing
A real case study: one-day DFT experiment with two self-corrections.
From zero to running research platform in under an hour.
asrp init creates your workspace with audit logs, registries, and agent directories.
asrp register pre-registers your first experiment with hypothesis and success criteria.
Run experiments, cross-validate, and let ASRP track every decision from hypothesis to publication.
Inspect every line. Self-host on your terms. Shape the future of AI-augmented research.
Every line of code is auditable. See how agents make decisions and where your data flows.
Run ASRP on your own machine. Your research data never leaves your network.
Bring your own LLM provider. Claude, Gemini, GPT, or OpenRouter — swap freely.
Contribute benchmarks, agent templates, and domain-specific skills that benefit all researchers.