Persistent AI coworkers that remember your projects, use your tools, and become a lasting company asset
Stage
Growing
Not given
Founded
Not given
Not given
Based in
Not given
JP
Pricing model
Paid
Freemium
Pricing
Not given
Free trial: 14-day free trial of Pro plan with 3 Standard Agent slots. Pro: $299/month with 3 Standard Agent slots. Team: $699/month with 6 Standard Agent slots. Crew: $1,299/month with 12 Standard Agent slots. Business: $2,499/month with 24 Standard Agent slots (additional Standard Agent slots $100
Key features
Run agents with Python tools
Deploy agents as MCP servers
Validate structured inputs and outputs
Inspect run results and artifacts
Secrets management
24-hour result retention
Voice conversations with transcripts stored in project context
Tool integrations with GitHub, Slack, Teams, Microsoft, AWS, Confluence, Box
12-Factor Coworker Model with identity, memory, reasoning, and learning
Durable task tracking with dependencies, retries, and approval controls
Computer use and desktop automation
Pre-configured starter teams for Sales, Engineering, and Customer Ops
Multi-team coordination and knowledge sharing
On-premise and private cloud deployment options
Local open-source runtime with XpressClaw
What makes it different
No subscription or idle charges for usage-based pricing
Zero markup on model tokens
Hosting included with deployment
Available through MCP clients like Claude and Codex
Full visibility into agent execution and results
Persistent memory and context that survives across sessions and team members
Measurable business outcomes with tracked work and task management
Team collaboration with multiple teammates working with the same coworker
Inspectable and composable architecture with clear interaction visibility
Flexible deployment with cloud-hosted or local open-source options
Recurse
Xpress AI