Persistent AI coworkers that remember your projects, use your tools, and become a lasting company asset
A persistent team of coding agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
JP
Not given
Pricing model
Freemium
Open source
Pricing
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
Not given
Key features
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
Start teams with one command and manage agents across multiple machines
Mix Claude Code, Codex and Pi agents in one team
Agents delegate and coordinate work with named task assignments and queue ownership
Agents message each other directly and read each other's screens
Restore agent conversations after restart or reboot from snapshots
Choose different models and reasoning effort per agent
Bring custom harnesses and integrate with MCP servers and Claude Desktop
Start Docker Compose services alongside agent teams
Control message filtering with typing guards and chat broadcasts
What makes it different
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
One conversation interface with a lead agent coordinating specialists behind the scenes
Mix multiple coding models and harnesses in one managed team
Run entirely self-hosted on your own machine with no external coordination
Open source with Apache 2.0 license and extensible harness contracts
Xpress AI
OpenRig