Skip to content

AIPOCH Open-Science

AIPOCH / AIPOCH

Local-first scientific AI workbench combining project files, agents, Python/R analysis and traceable research outputs.

Catalog updated ·

Overview

AIPOCH Open-Science organizes scientific questions, source files, literature and generated results in a desktop workspace for macOS, Windows and Linux. Chemistry and materials research are among the domains described by the project. Researchers connect a model and prepare the runtimes and services their task requires.

The workbench keeps artifact versions and available execution evidence for inspection. It can consume external MCP tools through connectors. Local storage does not make external model or service calls private to the computer. Recorded provenance and shared research packages help inspect a process; they do not establish scientific validity or guarantee that a result can be rerun.

Key Features

  • Python and R Notebook execution with recorded outputs.
  • Projects and sessions retain source files and generated reports, tables and figures.
  • Local-command and remote MCP connectors with separate access and tool policies.
  • Portable .science packages collect selected conversations, file versions and evidence.

Use Cases

  • Organize a literature investigation and inspect source-backed notes.
  • Analyze an attached research table and retain the code and output files.
  • Hand over a research session with selected files and its available evidence.

How to Use

Choose an official release installer for your OS and architecture using the installation guide. Complete setup and test the model connection; enable Python/R only when calculations require it. Create a project, attach a small table, and request a saved report with explicit inputs and outputs. Open that report and compare it with the table and tool records. Configure required connectors separately. A received .science record is read-only and does not execute its calculations. Release assets and documentation baselines can differ; check the selected release.

Sources and verification

This entry describes capabilities documented by the linked project sources. Catalog edits are not evidence of a successful run, compatibility test or scientific performance evaluation.

Read the editorial and verification policy

Related resources

OpenAI4S is an MIT-licensed scientific research agent combining JSON tool orchestration with persistent Python/R analysis and documented chemistry data connectors.

Open sourcePython

Cheminformatics · Literature & Research · Scientific Data

3Dmol.js

Open Source

3Dmol.js is a WebGL-accelerated JavaScript library for embeddable 3D molecular visualization in web pages.

Open sourceTypeScriptJavaScript

Scientific Data

AiiDA

Open Source

AiiDA is a computational-science workflow manager that records calculation inputs, outputs and metadata in a provenance graph.

Open sourcePython

Computational Chemistry · Scientific Data

alchemiscale

Open Source

alchemiscale is a high-throughput execution system for alchemical free energy calculations that distributes work across HPC, cloud, bare-metal and volunteer compute resources.

Open sourcePython

Computational Chemistry · Drug Discovery · Scientific Data

alchemlyb

Open Source

alchemlyb extracts alchemical free energy data from molecular dynamics output and estimates free energies with MBAR, BAR and thermodynamic integration on the PyData stack.

Open sourcePython

Computational Chemistry · Drug Discovery · Scientific Data

Benchling MCP (longevity-genie) is a Python MCP server that connects AI clients to Benchling notebook entries, biological sequences, projects, and entity search using API credentials.

Open sourcePython

Lab Automation · Scientific Data

Related guides

Workflows

AI Literature Research for Chemistry

Build a traceable chemistry literature workflow with PubMed MCP: refine searches, inspect metadata and abstracts, synthesize multiple papers, follow citations, and separate retrieved evidence from agent-generated hypotheses.

MCP

MCP for Chemistry: What It Is and Why It Matters

Understand how MCP connects AI applications to chemistry tools and scientific databases. Compare nine implementations, define traceable input/output contracts, and plan a bounded workflow with appropriate permissions, failure handling, and reproducibility records.