An open-source office where people and AI agents share the work
Web infrastructure platform for AI agents to search, extract, browse and automate web workflows
Stage
Not given
Not given
Founded
Not given
Not given
Based in
AU
US
Pricing model
Freemium
Freemium
Pricing
Restless Core is free and open source. Hosted Restless: Founder plan $49/month for two companies, Scale plan $149/month for five companies. AI use is included in hosted plans; additional usage available as top-ups at cost.
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
Shared rooms for people and agents to communicate
Collaborative documents with feedback and version tracking
Task board with status tracking and gates
Persistent Linux computer for continuous work
AI agents that run builds, exports, and research
Prepared decisions requiring only human judgment
Work continues after people leave the office
Model switching and session management
Account permissions and role tagging for team members
Spending caps for AI usage control
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
AI agents handle routine work, so people focus only on decisions requiring judgment
Built as a company workspace, not just a chat window
Open source core available free to self-host
Scales from single maker with one AI lead to larger organizations
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%