Long-term memory for AI agents that organizes itself and corrects itself
Reliable browser use with a fast path: deterministic mechanics, safety and verification, and a model asked only for judgement.
Stage
MVP
Not given
Founded
Not given
Not given
Based in
SE
ID
Pricing model
Free
Not given
Pricing
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.
Not given
Key features
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
Observe page state in atomic passes without screenshots
Model picks operations only from compatible targets
Risk classification for payments, deletions, sends and secrets
Typed actions with freshness, visibility and occlusion checks
Append-only event log for replay and audit
Chrome automation through Playwright
Browser extension for agent isolation
What makes it different
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Never contradicts itself by automatically replacing outdated facts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
Deterministic browser mechanics as default, models only for judgement and writing
Safety enforced through code boundaries, not prompt requests
Every step verified independently before proceeding
Mlola