AI teammates that write code, answer customers, run marketing and chase leads
Stage
MVP
Not given
Founded
Not given
Not given
Based in
US
FR
Pricing model
Contact for pricing
Freemium
Pricing
Per-execution pricing: one fee per execution that returns proof, charged only when proof comes back. Failed or cancelled runs cost nothing. Planning and approvals are free.
Free: teammates run on your own computer with unlimited teammates, threads and members. Cloud: $99/month per workspace (€99 in the euro zone), includes a computer for each teammate that keeps working when yours is off and email addresses for teammates. Both require your own Claude or ChatGPT plan su
Key features
Boundary approval system for controlled execution
Checkpoint-based resumable execution
Verifiable proof of completion
Composable proof for multi-agent workflows
Per-execution pricing model
Integration with multiple agent frameworks
Support email sorting and drafting replies from documentation
Bug fixing with live preview and approval workflow
Release notes generation from merged pull requests
Lead follow-ups from conversation history
Weekly revenue, refunds and signups reporting
Competitor monitoring for pricing and product changes
Task automation with approval controls
Encrypted password vault with secure login
Automatic triggers and scheduled routines
Team collaboration with shared threads and files
What makes it different
Pay only for verified results, not for attempts or planning
Human-approved boundaries ensure agent actions stay within limits
Interruptible checkpoints allow pausing and resuming executions
Proof is built into results for auditability and composability
Completely open source under MIT license with no gated features
Each teammate maintains its own memory and can remember team decisions
Full transparency with every step logged for review and audit