100100 Ideas AI
Submit Tool

open-science

MCPOpen source

Open-source, local-first AI research workbench with agents, MCP tools, and Python/R execution for reproducible science.

4.8kApache-2.0

The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.

Pros

  • +Local-first and model-agnostic desktop app for macOS, Windows, and Linux
  • +Extensible skills, MCP tools, and scientific data connectors (NCBI, ENA, Genes)
  • +Python/R execution with traceable artifacts and provenance for reproducibility
  • +Top-ranked on BiomniBench-DA public benchmark

Cons

  • −Desktop app install and local environment setup add operational overhead
  • −Scientific connector coverage is still expanding and may not fit every domain
  • −Agent workflows can be non-deterministic and require review of outputs

Target audience: Scientists, researchers, and data-intensive analysts who want an open-source, local AI workbench for reproducible computational research.

Related tools

Other open-source tools that share tags with open-science.

ECC

MCPMIT

Open-source agent harness performance optimization system with skills, memory, and security for AI coding tools.

243k·Developer Tools·Open source
TypeScriptPythonShellGoJava