Long-term memory for AI agents that organizes itself and corrects itself
Talk to Iris, inspect work and files, and explore local data in a terminal.
Stage
MVP
Not given
Founded
Not given
Not given
Based in
SE
Not given
Pricing model
Free
Free
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
Chat with Iris AI assistant
File inspection and management
Local data exploration
MCP integration
Multi-theme support
Configuration management
Passkey-based authentication
Multiple device support
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Never contradicts itself by automatically replacing outdated facts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
Runs natively on Windows and Linux without requiring Bun installation
Supports multiple installation methods including npm, pip, PowerShell, and shell scripts
Integrates with OpenAI-compatible and Anthropic-compatible APIs
Manages skills, plugins and MCP extensions without requiring package rebuilds
Dyadic Terminal