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
One context layer connecting all GTM tools and AI agents
Agent observability with end-to-end tracing
Source citations for every answer
Permission-aware answers scoped to user access levels
Playbook grounding to enforce business semantics
Corrections inbox for agent-generated changes
Integration with Claude, ChatGPT, Slack, Salesforce and other tools
Open Model Context Protocol (MCP) for any client
SOC 2 Type II compliance and GDPR/CCPA support
140x faster answers via pre-compiled context
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
40x lower cost through pre-compiled context vs raw data processing
98% answer accuracy with no hallucinations through checked data
Agent-agnostic: works with any AI tool your team uses
Never trains on customer data with enterprise-grade security
Set up within days with forward-deployed engineer support