Personal AI agents that run on their own computers, watch your pipeline, inbox and calendar, report problems early, and do the work you delegate
Proof of what an AI agent was allowed to do, and what it then did
Stage
Startup
Startup
Founded
2024
2026
Based in
US
Not given
Pricing model
Freemium
Open source
Pricing
Free: one bot with 5,000 credits and standard models (no browser, pauses when idle). Essential: $49/month per computer. Professional: $99/month per computer. Business: $199/month per computer. Any paid tier includes a 10-day free trial.
Not given
Key features
Personal AI agents with their own cloud computer and browser
Multi-channel deployment on Slack, Telegram, iPhone, and voice
Approval workflow for all agent actions
Signed permissions with passkey authentication
Receipts for each agent action with signatures
Free checker tool to verify compliance
Quantum-safe signatures (Ed25519 and ML-DSA-87)
Permission narrowing for helper agents
Permission cancellation with signed acknowledgement
JavaScript and Python libraries
LangChain and Pydantic AI middleware
What makes it different
Agents run on their own dedicated cloud computer, not shared infrastructure
Built on open-source agent (Hermes) and open-weight models, not proprietary AI
Employee-owned with no outside investors, focused on augmentation not replacement
Every action requires user approval before execution
All work handled by the agent is human-designed and user-coached
Only open-source project combining machine-checkable limits, permission narrowing for helpers, and signed permission cancellation
Built entirely from published standards with no hand-made components
Free and no dependencies, sends nothing anywhere or holds money
Distinguishes between record integrity and whether agent stayed within permission
All published versions stay available for backward compatibility
PageLines
Provared