OpenScience: An Open-Source AI Platform for Scientific Research Workflows

Wait what...there's an open-source alternative to Claude Science 🤯 And it runs the entire scientific research LOOP right in your browser. 100% Open Source. Meet OpenScience. It works with any model you already use. Claude, OpenAI GPT, Gemini, GLM, Kimi, DeepSeek, or your own local fine-tune. Give it a research goal and it reads the papers, forms a hypothesis, writes and runs the code, runs the experiment on real compute, and writes up what it found. Most research tooling locks you into one vendor's model, one vendor's stack, and your data sitting on someone else's servers. OpenScience runs on your machine with your own keys. Requests go straight to the provider, nothing leaves your box. You give it a goal and it works the loop the way a good collaborator would: • A research agent by default, plus biology, physics, and ML specialists, with critique and literature-review sub-agents • 290+ editable skills across training, evals, LaTeX, and cloud compute • 30+ scientific databases as native tools: UniProt, PDB, ChEMBL, arXiv • A browser workspace with a file tree, editor, terminal, and inline rendering for molecules, genomes, structures, and plots Bring-your-own-key usage is free and never throttled. The workspace opens in your browser. No account required. Every skill is readable and editable, so you can open any research playbook, change how it works, and add your own. The tools we discover with shouldn't be owned by one company. Link to the GitHub repo in the comments. ____ 100+ AI Agents, Agent Skills, and Agent teams (free and open-source with 118,000+ stars): https://lnkd.in/dW6b_dEn ♻️ Repost to share it with your network. Follow me at Shubham Saboo for more such AI Agent, Loop Engineering and Agent Skill workflows.

This post is based on a real open-source project but combines verified features with promotional language and a few misleading comparisons.

Confirmed Accurate

• OpenScience is a real open-source platform designed to automate parts of the scientific research workflow using AI agents.
• It supports multiple LLM providers, including models from Anthropic, OpenAI, Google, DeepSeek, GLM, Kimi, and locally hosted models through bring-your-own API keys.
• The platform includes specialized research agents and supports literature review, hypothesis generation, experiment execution, and report writing.
• It provides editable skills and workflows that users can customize.
• It integrates with numerous scientific resources and databases, including arXiv, UniProt, PDB, and ChEMBL.
• The browser-based workspace includes features such as a file explorer, code editor, terminal, and visualization tools for scientific outputs.
• Users can run the platform using their own API keys without creating an account.

Not Fully Accurate / Misleading

• The claim that it is an "open-source alternative to Claude Science" is an opinion rather than an official positioning. While both target AI-assisted scientific research, they are different projects with different architectures and capabilities.
• The statement that it "runs the entire scientific research loop" is a simplification. Many stages still require human oversight, validation, and interpretation.
• Claims that "nothing leaves your box" depend on the model being used. If you connect to cloud-hosted models (such as Claude, GPT, or Gemini), prompts are still sent to those providers. Only locally hosted models keep all inference on the user's machine.
• The claim that "bring-your-own-key usage is free and never throttled" refers only to the OpenScience application. API usage is still subject to the pricing and rate limits of the chosen model provider.