Open Science Assistant (OSA)¶

An extensible AI assistant platform for researchers working with open science tools. Built with LangGraph/LangChain and FastAPI.

Overview¶

OSA provides domain-specific AI assistants for open science tools such as HED, BIDS, EEGLAB, and FieldTrip (see Specialist Assistants below for the full list) with:

• Modular tool system for document retrieval, validation, and code execution
• Multi-source knowledge bases from GitHub, OpenALEX, Discourse forums, mailing lists
• Extensible architecture for adding new assistants and tools
• Production-ready observability via LangFuse

Design Philosophy¶

• Precision over features: Researchers need accurate, citation-backed answers
• Simple infrastructure: Lab server deployment, no complex scaling
• Extensible tools: General tool system that communities can adapt
• Domain expertise: Deep knowledge of specific tools, not broad generalist

Target Users¶

• Researchers learning HED annotations, BIDS formatting, EEGLAB analysis, FieldTrip pipelines, or any of the other supported tools
• Lab members needing quick, accurate answers from documentation
• Developers integrating these tools who need API/usage guidance

Quick Start¶

As a User (CLI)¶

# Install the CLI (lightweight, ~7 dependencies)
pip install open-science-assistant

# Set up your API key
osa init

# Ask a question
osa ask -a hed "How do I annotate a button press?"

# Interactive chat
osa chat -a hed

You will need your own API key: Anthropic at platform.claude.com/settings/keys (recommended), or OpenRouter at openrouter.ai/keys. osa init reads the provider off the key's prefix.

As a Developer¶

# Clone the repository
git clone https://github.com/OpenScience-Collective/osa
cd osa

# Install all dependencies (including server)
uv sync

# Run development server
uv run uvicorn src.api.main:app --reload --port 38528

# Run tests
uv run pytest tests/ -v

Specialist Assistants¶

Documentation¶

• Getting Started - Installation and setup
• Architecture - System design and diagrams
• Community Registry - YAML-driven assistant configuration
  • Adding a Community - Add a new assistant in 5 minutes
  • Schema Reference - Full YAML config reference
  • Extensions - Python plugins and MCP servers
• CLI Reference - Command-line interface
• API Reference - REST API documentation
• Knowledge Sync - Syncing GitHub, papers, and forums
• Widget Deployment - Embed the chat widget
• Tools - Available tools
• Development - Contributing to OSA

External API Integrations¶

OSA integrates with existing validator and tool APIs rather than hosting validation engines locally:

License¶

MIT