Welcome

Research Intelligence monitors academic papers and GitHub projects, scores them with AI, and learns your preferences over time. This setup will configure your instance.

You'll configure:
• API key for AI scoring
• Which research domains to monitor
• GitHub & events tracking
• Pipeline schedule

API Key

{% if is_hf_space and has_env_api_key %}

Your Anthropic API key is configured via Space Secrets.

API key configured via Space Secrets
{% else %}

An Anthropic API key is required for paper scoring. {% if is_hf_space %} Add it as ANTHROPIC_API_KEY in your Space's Settings → Secrets, then restart. {% else %} It will be stored in a local .env file, not in the config. {% endif %}

Get one at console.anthropic.com
{% endif %}

Research Domains

Choose which research areas to monitor.

AI / ML
Papers from arXiv + HuggingFace trending
Scoring Weights
Code & Weights %
Novelty %
Practical Applicability %
Security
Security research from arXiv cs.CR
Scoring Weights
Has Code / PoC %
Novel Attack Surface %
Real-World Impact %

Optional Features

Enable or disable additional monitoring features.

GitHub Tracking
Monitor trending repos in AI/ML and Security via OSSInsight
Events
Conference deadlines, releases, and RSS news feeds

Scoring Models

Choose which models to use for paper scoring. A fast model scores all papers, then a stronger model re-ranks the top papers for better precision.

Scores all papers. Haiku handles 700+ papers quickly at ~10x lower cost.
Re-ranks the top papers for better precision after the initial bulk pass.
Number of top papers per domain to re-score. Set to 0 to disable.

Schedule

How often should pipelines run automatically?

You can always trigger runs manually from the dashboard.

Review & Save

Here's your configuration. Click Save to get started.