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
AI Agent and MCP Server Discovery
Over 1,000 Built-In Integrations
Intent-Based Permissioning
Identity Threat Detection and Response
Lifecycle Management
Accountability and Traceability
Compliance and Auditability
Security Posture Management
AI-Driven Automation and Remediation
Token MCP Server
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
Identity-first approach built for AI agents, not human-centric tools
Unified identity graph correlating agents, humans, secrets, permissions, and data
Intent-aware least-privilege enforcement across agent lifecycle
Deep continuous discovery across on-prem, hybrid, and cloud environments
Native AI capabilities with Token MCP Server and AI Agent
Vectorize
Token Security