Open-source AI infrastructure you self-host on your own hardware with your own keys
Stage
Startup
Not given
Founded
2024
Not given
Based in
US
Not given
Pricing model
Freemium
Open source
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
Self-host: $0 (open source, MIT-licensed). Service and Enterprise tiers available on contact for integration and custom development work.
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
Provider routing with LiteLLM
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
Complete ownership: your keys, hardware, data and audit logs stay under your control
No vendor lock-in: compose individual modules with your existing stack rather than replacing it
Full transparency: MIT-licensed, publicly developed on GitHub with open issues, PRs and commit history
Every request traceable: one ID threads through all services with full audit logging
Vectorize
digithings