AI attention layer that learns what matters to you and surfaces priorities before they slip
Web infrastructure platform for AI agents to search, extract, browse and automate web workflows
Stage
MVP
Not given
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Free
Freemium
Pricing
Not given
TinySearch: free (30 requests/min, 500 requests/hour). TinyFetch: free (150 urls/min, 1,000 urls/day). TinyAgent: $0.016 per step. TinyBrowser: $0.002 per minute. TinyMonitor: $0.005 per check. TinyResearch: $2.00 per run ($3.00 for Max mode). TinySets: $0.10 per row. New accounts start with $8 in W
Key features
Connects to Gmail, Google Calendar, Slack and Google Meet
Shadow mode analyzes 30 days of past communications
Resolves people across channels into canonical contacts
Captures meeting decisions with reasoning and participants
Joins Google Meet as visible participant or captures from device
AI assistant Thara searches professional context and answers questions
Earns autonomy progressively through repeated approvals
Coverage honesty alerts when data sources fall behind
Categorizes attention into Needs You, Might Need You and Watching tiers
TinyVault: secure credential storage with 1Password and Bitwarden integration
TinyProfiles: save signed-in sessions for reuse with automatic re-authentication
Run recordings: step-by-step recordings and replay links for every execution
Free allowances: TinySearch at 30 requests/min, TinyFetch at 150 urls/min
What makes it different
Never claims certainty, only surfaces what may matter based on evidence
Learns around the way you work across different roles and professions
Maintains decision memory with reasoning and what changed
Requires explicit approval before acting on consequential items
Operates with read-only access and full user control over what is remembered
Unified platform combining search, fetch, browser and agent in one API key
Free search with lowest cost per task at $0.0093 on average
Live Google index through real browser, not cached results
Secure authentication without exposing credentials to the LLM
Industry-leading agent accuracy of 81.9% on hard tasks vs competitors at 43.2% and 32.4%