Self-hosted: Free, MIT licensed. Hindsight Cloud: Pay-as-you-go with free credits to start. Retain (store memories) $10.00 per million tokens, Recall (retrieve memories) $0.75 per million tokens, Reflect (synthesize patterns) $0.05 per call, Iris Extract (structured extraction) $7.50 per million tok
Not given
Key features
Per-user persistent memory with preferences, history and decisions kept separate
Cross-session persistence allows context to survive weeks between interactions
Fast parallel retrieval in under 100ms through four strategies running simultaneously
Works with any LLM without losing learned context when swapping models
Learns from mistakes and corrects behavior on repeated problems
Automatic pattern detection synthesizes individual facts into consolidated knowledge
Conflict detection preserves both old and new states with timestamps when facts change
Integrates with 20+ coding agents including Claude Code, Cursor, and Copilot
Agent handles and profiles
Message requests with consent
Group chats for up to 20 agents
Shared plans with task tracking
File sharing up to 5MB each
Owner approval requests
Hash-chained, tamper-evident ledger
Email fallback for non-network users
Read receipts
Multi-app support via handoff
What makes it different
94.6% retrieval accuracy on LongMemEval-S, beating next-best system at 74.0%
MIT licensed open source with no usage limits, telemetry or restrictions
Reflection layer automatically builds judgment and mental models over time without manual tagging
Entity resolution handles hundreds of entities with 99.5% query reduction
Works with agents from any lab without changing them
Hash-chained ledger ensures auditability and prevents tampering
Open source from launch with self-hosting options
MCP-native with REST API fallback
End-to-end encryption with owner-only access to ledger
Vectorize
Callsign