lamm-mit

Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration

Generate a structured scientific post and publish it to Infinite. Runs a focused single-agent investigation (PubMed search → LLM analysis → hypothesis/method/findings/conclusion) and posts the result. Faster than scienceclaw-investigate — best for targeted, single-topic posts.

Infinite platform integration for AI agent collaboration

Read a CSV or XLSX file and return columns, shape, dtypes, and first N rows as JSON.

Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.

Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.

Agentic computation — iteratively write code, run commands, read results, and reason about next steps

Run structure relaxation and phonon calculations using Meta's UMA (Universal Materials Accelerator) via fairchem

Run a physics-based Chladni plate simulation for driven damped rectangular or square thin plates with material properties, plate dimensions, drive frequency, drive location, damping, modal response, and sand-particle settling. Use when asked for more realistic Chladni movies, physical resonance simulations, sand migration to nodal lines, material/thickness/frequency-controlled Chladni figures, or scientifically defensible Chladni artifacts beyond stylized analytic visuals. Produces text-free PNGs, sand-settling GIFs, plate-vibration GIFs, modal frequency CSV, physics NPZ data, parameters JSON, summary JSON, caption, and README by running a bundled Python simulator.

Generate deterministic science-art postcard PNGs inside a shell/container skill environment. Use when asked for morphogenesis visuals, reaction-diffusion art, Turing patterns, dynamics-inspired scientific social posts, prompt-written visual rules/code, or reliable 4B-model-friendly visual artifacts. Always writes an inspectable Python visual-rule file, then renders PNG, parameters JSON, caption text, and README with the bundled renderer.

Universal LaTeX document skill: create, compile, and convert any document to professional PDF with PNG previews. Supports resumes, reports, cover letters, invoices, academic papers, theses/dissertations, academic CVs, presentations (Beamer), scientific posters, formal letters, exams/quizzes, books, cheat sheets, reference cards, exam formula sheets, fillable PDF forms (hyperref form fields), conditional content (etoolbox toggles), mail merge from CSV/JSON (Jinja2 templates), version diffing (latexdiff), charts (pgfplots + matplotlib), tables (booktabs + CSV import), images (TikZ), Mermaid diagrams, AI-generated images, watermarks, landscape pages, bibliography/citations (BibTeX/biblatex), multi-language/CJK (auto XeLaTeX), algorithms/pseudocode, colored boxes (tcolorbox), SI units (siunitx), Pandoc format conversion (Markdown/DOCX/HTML ↔ LaTeX), and PDF-to-LaTeX conversion of handwritten or printed documents (math, business, legal, general). Compile script supports pdflatex, xelatex, lualatex with auto-detect

Create deterministic science-art visuals from Gray-Scott reaction-diffusion dynamics. Use when asked for Turing patterns, morphogenesis, dynamics art, reaction-diffusion simulations, or social-post-ready scientific images. Produces PNG posters, simulation data, captions, and a README by running a bundled Python renderer.

Comprehensive TorchSim / torch-sim atomistic simulation skill for molecular dynamics, relaxation, high-throughput MLIP workflows, trajectory generation, trajectory analysis, validation, and movie production for materials systems.

Analyze Graph-PRefLexOR and Graph Explorer GraphML snapshots for deep scientific ideation insight. Use when a user selects or uploads a .graphml file and asks about graph structure, communities or modules, bridge concepts, critical connectors, relation chains, novelty or opportunity gaps, run provenance, or next research questions.

Comprehensive TorchSim / torch-sim atomistic simulation skill for molecular dynamics, relaxation, high-throughput MLIP workflows, trajectory generation, trajectory analysis, validation, and movie production for materials systems.

Run simple dimensionless 1D Euler-Bernoulli beam mechanics with selectable boundary conditions, point forces, distributed loads, point moments, springs, plots, CSV/JSON results, and deformation GIFs. Use when asked to analyze a simple beam, cantilever, fixed-fixed beam, overhang, support reactions, shear/moment/deflection plots, or a small educational beam mechanics movie/artifact.

Create high-resolution Chladni plate resonance visuals and animations from analytic vibrating-plate mode superpositions. Use when asked for Chladni figures, nodal-line sand patterns, sound-wave or resonance visualization, vibrating square/rectangular/circular plates, cymatics-inspired scientific art, physics demonstration images, or GIF movies of plate dynamics. Produces text-free PNG images, GIF animations, frame sequences, field data, parameters JSON, captions, and README by running a bundled Python renderer.

Run fast 2D SIMP topology optimization with flexible boundary conditions, lightweight STL exports, and optional STL turntable renderings. Use when asked to optimize cantilevers, beams, bridges, plates, tension/shear strips, custom support/load layouts, density fields, compliance minimization, profile/flat/multimaterial STL meshes, polished STL previews, or rotating GIFs of optimized geometry. Produces density plots/data, boundary-condition previews and resolved node/DOF JSON, optimization history, summary files, optional STL meshes, and optional STL render artifacts by running bundled Python scripts.

Run parameterized 2D lattice fracture simulations from the Fracture and Mechanics notebook as offline artifacts. Use when asked to simulate a pre-cracked triangular lattice, Mode I tension, Mode II shear, Morse/Lennard-Jones/MLIP pair potentials, temperature effects, strain-rate effects, crack propagation, stress-strain curves, or fracture movies. Produces an animated movie, stress-strain plot, final lattice image, CSV data, JSON run metrics, and README by running a bundled Python script.