Agentic AI research assistant that interprets lab results and turns research questions into cited, evidence-backed briefs
Free AI chat with open models, no account or sign-up required
Stage
Established
Not given
Founded
2018
Not given
Based in
CY
Not given
Pricing model
Freemium
Free
Pricing
Basic (free) with monthly usage allowance; Plus €18/month with 3x the Basic allowance; Pro €75/month with 13x the Basic allowance; Team €125/month for 3 seats then €37 per extra seat with 9x the Basic allowance per seat; Organization €150 per seat per month with Pro usage limits. Paid plans can purc
Free with 10 prompts per day. UsingOpen Studio desktop app is $19 USD one-time purchase, or ¥99 CNY in mainland China.
Key features
Semantic search across 40 million biomedical papers
Full-text reading and citation tracking
Trust Index for result reliability screening
Research landscape and concept mapping
Zotero library integration
Weekly research digest and personalized feed
PDF and Word report export with citations
Mechanistic links and hypothesis generation
Saved clusters for organizing research
Access to 20+ open-weight AI models including DeepSeek, Qwen, GLM, Gemma, GPT-OSS, Kimi K3 and MiniMax M3
No account required, no sign-up, no email or password needed
10 free prompts per day, reset at midnight UTC
Chat history saved locally on your device, never sent to servers
Streaming responses with visible reasoning for thinking models
Compare two models side by side in the same conversation
Live model availability status and real-time capacity information
Responsive design, installable as standalone mobile app
What makes it different
Reads full-text papers instead of just abstracts for comprehensive analysis
Every claim grounded in verified citations with evidence-typed sources
Monitors when literature moves on and notifies users of updates
Constrained reasoning engine reduces AI hallucinations through literature grounding
Biology-native evidence engine with knowledge graphs for semantic understanding
Complete privacy - chat history stays only on your device and is never sent to servers
Model picker with real-time availability, not a single locked-in assistant