Features
Outcome-based memory scoring (wilson score)
Two-lane retrieval: 4 summaries + 4 facts per turn
TagCascade retrieval pipeline
Automatic summarization of conversations
Noun tagging at store time
Memory lifecycle: working (24h), history (30d), patterns (∞)
Demotion of low-scoring memories
Poison-resilient against semantic match + spoofed trust
Works with Claude Code and OpenCode
Local-first, no cloud dependency
Desktop GUI with Ollama/LM Studio support
MCP (Model Context Protocol) tools
Multi-agent orchestration (multiple AI agents)
File editing via VS Code extension
Terminal control and command execution
Git integration for version-aware assistance
Autonomous mode (coming soon)
Advanced task routing rules
Local processing for privacy
Customizable model deployment
