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
Connect to Claude via custom connector in Settings
Add to ChatGPT with developer mode
Automatic session save for Claude Code and Codex
Save and resume sessions with brief summaries
GitHub sign-in for private separate memory
Delete individual memories or all data by email
Zero model calls to save a session
Session brief generated in ~450 tokens
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
Shared memory across multiple AI apps and agents, not confined to one app
Setup in about one minute with no credit card or waitlist
Open source code so users can verify data handling
No data selling, ads or use for AI model training
Private per-account database with no cross-account access
Vectorize
CogniCore