Scientific agents

aiming-lab/AutoResearchClaw

Agent Claude Code

FBA simulation agent. Runs standard FBA, parsimonious FBA, Flux Variability Analysis, and gene/reaction knockout simulations using COBRApy. Use after a validated metabolic model is available and the user wants to compute growth rates, flux distributions, or knockout phenotypes.

ResearAI/DeepScientist

Agent Claude Code

Core operating contract shared by all DeepScientist quest turns.

HarleyCoops/Math-To-Manim

Agent Claude Code

Stage 6 of the GLM chain. Writes the ThreeDScene contract and the full Manim source as glmscene.py, then calls local verifyscene until it passes. Camera moves use setcameraorientation or movecamera only.

pedrohcgs/claude-code-my-workflow

Agent Claude Code

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

PharMolix/OpenBioMed

Agent Claude Code

Autonomous Retrosynthetic Tree Search Loop. Continuously expands nodes, checks vendors via AI models, and backpropagates until the target is solved or interrupted.

psi-oss/get-physics-done

Agent Claude Code

Default writable implementation agent for bounded GPD research execution. Handles PLAN.md files or scoped tasks with checkpointing, deviation handling, state updates, and physics discipline. Spawned by execute-phase, quick, and parameter-sweep workflows.

aristoteleo/PantheonOS

Agent Claude Code

Specialized execution agent for OmicVerse-based analysis. Uses OmicVerse lookup helpers from the same Python runtime as notebook execution, avoiding dependency on a separate Pantheon omicverse toolset.

Dogacel/auto-gpu-kernel

Agent Claude Code

Clean-context diagnosis for planning next experiments.

sweetcornna/mathodology

Agent Claude Code

Implement reproducible modeling calculations, experiments, figures and tables.

equinor/neqsim

Agent Claude Code

Solves process-engineering problems using the NeqSim Java API with proportional depth: quick answer-first calculations, notebook-backed studies, or full reports. Delivers auditable task folders with validation evidence, runner-executed notebooks/scripts, and reports when needed. When NeqSim lacks a needed capability…

flonat/flonat-research

Agent Claude Code

Adversarial auditor for LaTeX papers. Read-only with respect to project files (paper, bib, code, data); writes its own report at reviews/ /paper-critic/ .md plus a findings.json sidecar. Finds problems without fixing them — produces a structured report with scored issues that the fixer agent can action. Assumes the…

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.

morankor/theorist-toolbox

Agent Claude Code

Adversarial reviewer agent for the AI co-mathematician system. Gates workstream completion — a workstream cannot be marked complete until paper-reviewer writes an explicit approval file. Cross-checks references resolve, that proofs have no leftover \unproven blocks (or are properly flagged), that code outputs match…

SteadfastAsArt/geoscience-skills

Agent Claude Code

Geoscience data quality control specialist. Reviews well log, seismic, and spatial datasets for common data quality issues. Use when loading new datasets or before running analysis pipelines.

xlx777/ccg-scholar

Agent Claude Code

An agent for planning a research paper's structure using IMRaD: introduction, methods, results, and discussion. It also plans sections, figures, tables, page space, and dependencies between sections.

amirkiarafiei/open-scholar-peer

Agent Claude Code

Open ScholarPeer Baseline Scout Agent — adversarial auditor that identifies missing baselines and datasets the authors failed to compare against. Activate this persona when the user invokes /4-osp-baseline-scout. Operates with an intentionally skeptical posture — its job is to find omissions, not validate what's there.

DeevsDeevs/agent-system

Agent Claude Code

Alpha Squad - microstructure and entropy lens. Models the order book as a physical system. Decomposes order flow informativity, tracks entropy regime shifts, derives testable predictions from structural models. Kyle, Glosten-Milgrom, Hawkes, Shannon.

BeppeTemp/cartographer

Agent Claude Code

Answers questions about the night sky using this astronomy atlas.

PolicyEngine/policyengine-claude

Agent Claude Code

Stage-5 comparator. Takes the microsim output and the prior-scores anchor, returns PASS (within expected band, write up the result) or INVESTIGATE (mismatch, trigger calibration-diagnostics). Normalizes single-year vs 10-year scores and accounts for dataset-version drift.

jkitchin/discopt

Agent Claude Code

Deep expert on SCIP (Solving Constraint Integer Programs) and MINLP solver architecture — spatial branch-and-bound, constraint handlers, separators/cuts, presolve, expression/nonlinear handling, grounded in the SCIP Optimization Suite source. Use when comparing discopt against SCIP, reasoning about MINLP solver…

ajhcs/mbse-agents

Agent Claude Code

Principal aerospace SE specializing in ARP4754A/4761A development assurance, DO-178C/DO-254 certification evidence, airborne cybersecurity, and multi-tool MBSE crosswalks for civil and space programs.

huggingface/physics-intern-skills

Agent Claude Code ✓ vendor

Perform symbolic and numerical computation for a target claim. Default backend SymPy + NumPy. Runs symbolic and numerical paths together when both are feasible and flags disagreements. Writes computations/C-NNN.md (narrative) and computations/C-NNN.py (executed script).

hdu-ailab/EasyResearch

Agent Claude Code

User-facing Research Assistant for evidence-driven paper projects, using session-selected subagent-driven or single-Agent execution within the user's authority and reporting clear results and useful deliverables.

MadGraphTeam/MadAgents

Agent Claude Code

The primary expert on MadGraph and related tools (e.g. Pythia8, Delphes, MadSpin), with access to authoritative local documentation. Specialized in MadGraph5aMC@NLO: process definition, event generation, shower/hadronisation, detector simulation setup, generation/prediction-level studies.