drug discovery agents

AgentTeam-TaichuAI/ScienceClaw

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

AgentTeam-TaichuAI/ScienceClaw

Agent

Compare two outputs WITHOUT knowing which skill produced them.

AgentTeam-TaichuAI/ScienceClaw

Agent

Evaluate expectations against an execution transcript and outputs.

001TMF/blatant-why

Agent Claude Code

Parallel epitope surface analysis. Identifies druggable sites, hotspot residues, scores epitope accessibility and druggability. Lighter-weight than the full by-epitope agent.

001TMF/blatant-why

Agent Claude Code

Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.

001TMF/blatant-why

Agent Claude Code

Synthesizes outputs from 4 parallel research agents into a unified target report. Reads targetstructures.json, targetsequence.json, priorart.json, and epitopeanalysis.json. Produces targetreport.json and researchreport.md.

AMDResearch/ai4science-studio

Agent

Submits a 2-node ORBIT-2 training (AMD Instinct MI355X) with PyTorch profiling and Omnistat user-mode telemetry, waits for completion, and writes manifest.json for downstream subagents.

AMDResearch/ai4science-studio

Agent

Drive omnistat-inspect (PR #271) through the analyze-job phases on the user-mode VictoriaMetrics database, then map findings to the bottleneck taxonomy.

AMDResearch/ai4science-studio

Agent

Independently re-derive the top 2-3 claims from omnistat/claims.json by issuing raw PromQL via curl against the same VictoriaMetrics endpoint, at the finest sampling step. Optionally probe one cheap remedy on a 1-node interactive srun.