Agent harness infrastructure that gives AI agents memory for each user, connected accounts, action limits and an audit record.
Stage
Startup
Not given
Founded
2024
Not given
Based in
EE
CA
Pricing model
Freemium
Freemium
Pricing
Agent plan $9.99/month with 5,000 notifications/month after 3-day free trial. Agent Pro $19.99/month with unlimited notifications. Team plan $59/month for 5 people. Partner Launch $99/month, Partner Growth $299/month, Partner Scale $799/month. Enterprise custom. All paid plans include 3-day free tri
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
Push notifications to phone for agent approvals
Mac notch app for desktop approvals
Append-only audit trail of all decisions
Supports Claude Code, Codex, Cursor, Hermes and MCP agents
Slack approval notifications
Partner APIs for embedding approvals in products
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
Agent decisions saved as permanent, uneditable audit trail
Smart policies that auto-approve safe actions and escalate risky ones
Partner APIs let customers approve without separate Pushary account
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
Pushary
Harny