Free: $0 per month for 1 user. Pro: $19/month for up to 10 members. Enterprise: custom pricing.
Free: $0 per month with 2 connections, 1 agent, 500 protected actions per month. Developer: $99/month with 25,000 billable executions included, then $0.001 per billable execution with $500 default overage cap. Business: Contact Sales for paid pilots and enterprise contracts.
Key features
Run multiple coding agents in parallel on separate git worktrees and branches
Task board with live terminals for each agent session
Access Profiles to control permissions for each agent
Integration with 100+ providers
Audit logs of all agent actions and refusals
Self-hostable access layer
On-demand GPU compute by the second
Local-first execution keeping source code and output on user's machine
Support for Claude Code, Codex, and other agentic clients
Cryptographically signed receipts and verifiable evidence
Multi-party approval for organizational authority
Open-source SDK, MCP server, and framework adapters
Authority lifecycle management from grant to revocation
Supported integrations with payments and cloud accounts
Individual, family, business, and enterprise deployment options
Enforcement at tool execution boundaries
What makes it different
Open-source access layer under Apache-2.0 so you can read the security model
Enforce access permissions at the system level, not through prompts
Centralized access control across all agents and platforms simultaneously
Keep data portable with plain files on your own disk, no vendor lock-in
Complete audit visibility of what every agent accessed and was denied
Write-once signed decisions verifiable by auditors without trusting the vendor
Controls sit at the point where AI systems take consequential actions
One company integrating security and compliance disciplines
Open-source cores and published research allow vendor review