Curing All Human Disease
ClawCures is an experimental, fully autonomous AI drug-discovery agent built on the OpenClaw framework. It runs continuously, searching for cures to every human disease — prioritizing the most severe and neglected conditions and pursuing the most biologically plausible therapeutic paths.
Find cures for all diseases by prioritizing the highest-burden conditions and researching the best drug design strategies for each.
— The default ClawCures prompt, verbatim
ClawCures is a fully autonomous AI agent that works around the clock to find cures for human disease. It can be directed towards a specific condition or approach, but by default it prioritizes the most severe and neglected diseases.
It operates across the full stack of modern biotech: reading and synthesizing scientific literature, running machine-learning models, designing and prioritizing compounds, coordinating CRO wet-lab experiments, and preparing regulatory documentation such as IND applications.
Yes, this sounds wild. That's because it is. But wild or not, it's available now for you to play with.
ClawCures runs from a single command. Point it at any disease — or let it decide.
$ clawcures run
🦞 Initializing ClawCures autonomous agent...
📋 Loading default objective: cure all human disease
🔬 Ranking disease portfolio by global burden...
🧬 Generating therapeutic hypotheses...
⚡ Planning via OpenClaw gateway...
✅ Campaign running. Iteration 1 of ∞
ClawCures separates planning from execution. OpenClaw generates strategic plans, while Refua MCP executes typed scientific tools in an auditable workflow.
Set a disease target or let ClawCures default to its all-disease mission.
The agent reads and synthesizes scientific papers to identify the best therapeutic strategies.
ML models design and optimize candidates — small molecules, peptides, or de novo antibodies.
ClawCures coordinates CRO wet-lab experiments to validate promising candidates.
Generate IND applications and regulatory documentation automatically.
ClawCures operates across every layer of modern biotech, from computational modeling to wet-lab coordination to regulatory filing.
Reads, indexes, and synthesizes the global scientific literature to identify the most promising therapeutic avenues.
Runs machine-learning models to design and score compounds, predict binding affinity, and optimize drug-likeness.
Designs antibodies from scratch with highly optimized properties — binding, stability, developability — all computationally.
Interfaces with CRO partners to commission and track real-world experiments, bridging the in silico–in vitro gap.
Prepares IND applications, study reports, and regulatory dossiers — the paperwork that gets drugs to patients.
Ranks every human disease by severity and neglect, then allocates effort to where AI-driven discovery can have the most impact.
ClawCures is part of the AgentCures Refua ecosystem — an open-source, end-to-end drug-discovery framework built for the AI era.
It integrates with every component of the Refua stack: Amiti for molecular screening, Refua MCP for tool execution, OpenClaw for planning, and the full suite of clinical, regulatory, and data tools.
In principle, with the right integrations, it could even place phone calls to regulators on your behalf.
ClawCures is the autonomous engine behind the AgentCures mission to cure every human disease. It's open source, it's running right now, and it only gets more advanced every day.