Long-term memory for AI agents that organizes itself and corrects itself
Stage
Startup
MVP
Founded
2024
Not given
Based in
EE
SE
Pricing model
Freemium
Free
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
Personal: Free during early access. Unlimited memories, all agents with separate memories, no card required. Enterprise: On request, set up by the team for departmental organization with cross-department sharing and direct support.
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
Self-correcting memory that updates when facts change
Historical memory queries with time-based retrieval
Automatic topic organization and hierarchy
Separate memory for each agent with controlled sharing
Multi-agent support via MCP, REST API, or LangGraph
AES-256 encryption at rest and in backups
OAuth 2.1 authentication and API key management
Data export and deletion capabilities
37 MCP tools with automated verification on every code change
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
Understands what changed, when it was true, and where it belongs - beyond vector database similarity
Never contradicts itself by automatically replacing outdated facts
Fully GDPR aligned with built-in privacy by design
Two-minute integration with Claude, ChatGPT, Cursor and any MCP client
Data stays in Europe on AWS eu-north-1 and never used for model training
Pushary