Cloud computer for every agent, with your tools and team.
Agent harness infrastructure that gives AI agents memory for each user, connected accounts, action limits and an audit record.
Stage
Not given
Not given
Founded
Not given
Not given
Based in
NO
CA
Pricing model
Freemium
Freemium
Pricing
Free: $10 monthly usage credit. Pro: $20/month for $100 monthly usage credit. Max: $100/month for $500 monthly usage credit. Enterprise: custom volume pricing. All plans include 5× usage credit for model calls at provider's API price with no markup. Pay-as-you-go top-ups available.
Free: first 500 monthly-active end users per month, free forever. Paid: $0.30 per monthly-active end user above 500, billed monthly.
Key features
Each agent gets its own dedicated computer in the cloud
Agents keep working after you close your laptop
Run many tasks in parallel, each on its own computer
Encrypted vault for credentials and secrets
Connect tools once, all agents can use them
Support for any AI model including your own subscriptions
Multiplayer chats teammates can continue
Scheduled recurring work on a schedule
Approval controls for risky actions
Start tasks from Slack, web app or phone
Timestamped memory ingestion with backdating capability
Per-user data isolation and privacy scoping
Ranked memory recall with dated evidence
Connected accounts integration per user
Long-running agent jobs with folder-level operations
Configurable token ceiling per API call
Enforced action limits on agent operations
Complete action audit trail with hash chaining
MCP server integration for Claude and other clients
What makes it different
Open source under Apache 2.0, self-hostable or run on managed cloud
Same harness works for team agents, software development automation, and embedding in your product
No markup on model API costs; credits give 5× value
Agents run real terminal commands, tests and git operations
Teams share one workspace with shared integrations and role-based access
Highest published BEAM benchmark score at 128K tokens: 85.1, compared to competing memory systems
98% fewer tokens required than raw tool output, making responses 4× cheaper
Works with 20+ agent frameworks including LangChain, LangGraph and LlamaIndex
First 500 monthly-active end users free forever
Per-person billing model scales with user growth, not API calls
Opengeni
Harny