Scientific agents

microsoft/P.808

Agent ✓ vendor

Analyzes crowdsourced subjective test results — runs resultparser.py for data cleaning, quality checks, and per-clip/per-worker MOS aggregation, and writes a re-runnable rerunresultparser.bat that re-runs resultparser.py.

microsoft/P.808

Agent ✓ vendor

Creates subjective speech quality tests using the P.808 toolkit — handles study setup, gold/trapping clip generation, storage upload, project building for crowdsourcing platforms, prompts for study-specific screen-out completion codes (never reused across studies) and for the internal-vs-general master-script assets…

frenzymath/Archon

Agent

Part of lean4

Golf Lean 4 proofs after they compile; improve proofs for directness, clarity, performance, and brevity without changing semantics. Use after successful compilation to achieve 30-40% size reduction.

Imbad0202/experiment-agent

Agent

You execute and monitor code-based experiments. Your job is to run user-specified commands, watch for problems in real-time, and collect results when done. You cover any experiment that runs as a process: ML training, statistical analysis, data processing, simulation, benchmarks.

andrehuang/academic-writing-agents

Agent

Part of academic-writing-agents

Creates and adjusts TikZ/pgfplots figures, manages figure placement and layout, ensures proper label/ref wiring and figure-text-caption consistency.

K-Dense-AI/scientific-agents

Agent

Part of accelerator-physicist

Reasons from beam optics, RF cavities, emittance budgets, and loss maps while treating halo and impedance-driven instabilities as first-class failure modes.

K-Dense-AI/scientific-agents

Agent

Part of actuarial-scientist

Reasons from mortality tables (qx, period/cohort, select/ultimate) and Chain-Ladder/Mack reserving through GLM/GAM frequency–severity and Tweedie pricing, limited-fluctuation and Bühlhmann-Straub credibility, Solvency II SCR standard formula, and IFRS 17 CSM/RA while treating triangle truncation, overfitting, and tail…

K-Dense-AI/scientific-agents

Agent

Part of anatomist

Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating fixation shrinkage, segmentation artifacts, landmark homology error, and collection bias…

Dogacel/auto-gpu-kernel

Agent Claude Code

Clean-context diagnosis for planning next experiments.

sweetcornna/mathodology

Agent Claude Code

Use for independent review of assumptions, model validity, evidence, reproducibility, writing, and final submission risk.

sweetcornna/mathodology

Agent Claude Code

Use for award-level paper structure, abstract, narrative, equations, figures, captions, and final polish.

equinor/neqsim

Agent

Analyzes engineering tasks to identify required capabilities (physics, chemistry, process, economics), checks NeqSim's existing coverage, identifies gaps, plans implementations, and recommends skills to load. Use before starting any complex engineering task to ensure all needed tools and models are available.

AnastasiyaW/codex-claude-code-config

Agent

Part of claude-code-config

Independent reviewer of OBJECT INTERACTION physics in pixel-art scenes (gravity, occlusion order, surface support, light direction consistency, anchor points, scale plausibility). The 4th specialized reviewer in the pixel-art-quality-board orchestrator. Use when the user asks "do objects interact correctly", "is…

CattleZ/dance-video-to-prompt

Agent

An agent role that runs a rhythm analysis using files already produced by a local script. It uses the supplied analysis and brief rather than creating BPM values itself.

maxwell2732/paper-replicate-agent-demo

Agent Claude Code

Substantive domain review for biomedical epidemiology replication scripts and reports. Acts as a senior epidemiology journal referee (NEJM/Lancet/IJE standard). Checks confounding/bias assumptions, method verification, citation fidelity, code-theory alignment, and logical consistency. Use after replication scripts are…

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.

GRIND-Lab-Core/night_owl_research_agent

Agent Claude Code

Geospatial domain expert agent that injects spatial analysis context into the research pipeline. Use this agent to: Recommend appropriate spatial methods for the research question Suggest open-source datasets with spatial coverage and resolution Review spatial analysis code for CRS, projection, and autocorrelation…

GRIND-Lab-Core/night_owl_research_agent

Agent Claude Code

Research hypothesis generation and scoring agent. Use this agent to: Generate testable research hypotheses from identified gaps Score hypotheses on novelty, feasibility, and alignment with program.md Suggest datasets and methods for each hypothesis Rank hypotheses and recommend the top candidate(s).

xd-liu/AutoResearch-Idea

Agent Claude Code

Step 6 of the research-idea pipeline. Adversarially reviews each generated paper idea — strengths/novelty/impact, defects, and overlap with the retrieved literature — and assigns credit/blame to the pipeline step that produced each. Spawned (often in parallel) by the research-ideas orchestrator.

xd-liu/AutoResearch-Idea

Agent Claude Code

A helper agent that combines insights from research papers and brainstorming variations to create new candidate paper ideas.

xd-liu/AutoResearch-Idea

Agent Claude Code

Step 3 of the research-idea pipeline. Reads the retrieved papers and digests each into a reusable structured "gene". Runs in-context on Sonnet (your Claude Code subscription) — no API key needed. Spawned by the research-ideas orchestrator.

VirtualPatientEngine/AIAgents4Pharma

Agent

Talk2BioModels is an AI-agent designed to interact with mathematical models in systems biology. You can choose to either interact with a model available in the BioModels database or upload your own model.