An AI agent research tool that reads forums, papers, filings and markets to answer questions with sources
Stage
Not given
Startup
Founded
Not given
2024
Based in
Not given
US
Pricing model
Freemium
Freemium
Pricing
Free: $0/mo for 1 agent with scanner, approvals, kill switch, phone and Telegram alerts, and 7-day history. Pro: $24.99/mo for up to 5 agents with learned autonomy, Time Machine, data-leak tripwire, vault, and unlimited history. Team: $79.99/mo for unlimited agents with everything in Pro plus priori
Free for non-commercial use (subject to capacity); queries cost a fraction of a cent to a few cents for commercial use
Key features
Skill scanner for hidden instructions in documentation
Encrypted vault for secrets kept away from agent context
Kill switch for instant agent stopping
Rewind time machine to walk back agent actions
Data-leak tripwire for PII and secrets detection
Live operations dashboard monitoring all agents
Phone and Telegram alerts for held and blocked actions
Integration with ChatGPT and Claude via MCP protocol
Complex query execution including phrase matching, time windows and joins
Two-minute setup with no code required
Live schema and data freshness information
HTTP API for developers without MCP clients
Support for Claude Code, Codex, Cursor and other MCP clients
Results with source citations and links
What makes it different
Runtime gate checks actions before they execute, not after like logs
External to agent so injected content cannot override security rules
Differentiates between reversible actions that flow immediately and irreversible ones needing approval
Catches runtime threats that static scanning misses
Built for individual developers, not enterprise
Runs arbitrary programs over the internet rather than returning simple link lists
Affordable pricing with free non-commercial access