Trusted autonomy for industrial operations built on machine teaching
Stage
Startup
Not given
Founded
2024
Not given
Based in
US
US
Pricing model
Freemium
Contact for pricing
Pricing
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
60+ tools for data to autonomy
CLI and API access
MCP server for autonomous coding agents
Flexible compute deployment on cloud, on-premises, or edge
Dedicated supercomputer cluster infrastructure
12-week deployment timeline
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
Built on machine teaching methodology for systems that learn from human expertise
Proven ROI with documented industrial results up to $1.7M per year
Data never leaves your walls with on-premises deployment options
No-code platform for enterprise deployment without extensive technical expertise
Vectorize
AMESA