OpenScience
synthetic-sciences
Open-source AI workbench that runs the full scientific research loop - literature, code, experiments, write-up - from a single goal.
What is OpenScience?
A browser-based research workbench that takes a goal and autonomously reads the literature, writes and runs code, executes experiments and writes up findings across ML, biology, physics and chemistry. It ships specialized research agents plus critique and literature-review sub-agents, 290+ built-in skills, and connectors to 30+ scientific databases (UniProt, PDB, ChEMBL, arXiv, Semantic Scholar).
Pros & Cons
Pros
- Domain-deep out of the box: 290+ skills and 30+ scientific database connectors
- Model-agnostic (Anthropic, OpenAI, Google, local) and extensible via MCP, LSP, plugins and a TypeScript SDK
- Full workbench UI with file tree, editor, terminal and inline molecule/plot rendering
Cons
- "Reads the literature and runs experiments" is a broad promise; the quality of its autonomous research output is unproven and unvalidated here
- Scientific-research scope means a steep learning curve and a narrow audience
- Young and ambitious (13 releases, ~236 commits) for the breadth it claims
License
Apache-2.0 (OSI-open)
When it is interesting
You do computational science and want an agentic workbench that already speaks your databases and tooling.
When it is too early
You need reproducible, auditable results you can trust without heavy human verification, or you work outside its science domains.
This repo featured in the 2026-07 edition of the Open-Source AI Radar.
deta Surf
deta
Local-first AI notebook desktop app that pulls files and web content into notebooks with source-linked citations.
Data-Analysis-Agent
Zafer-Liu
Self-hostable chat-with-your-data agent: upload Excel/CSV or a database, ask in natural language, get SQL, charts and reports.
marimo-pair
marimo-team
Agent skill that lets coding agents discover a running marimo notebook and execute code in the live session.