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 once through MCP endpoint across Claude, ChatGPT, Cursor and Claude Code
Shared memory automatically synced across all connected AI tools
Plain markdown storage with YAML frontmatter
EU-hosted data with no vendor lock-in
Lexical search across memory
No API keys or complex configuration needed
Account created automatically on first connection
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
Cross-vendor memory through MCP instead of locked to one assistant
Plain readable markdown you own forever, not black-box vectors or rented format
EU-hosted by architecture so data stays in your region
Survives AI tool changes and deprecations unlike built-in assistant memory
No maintenance needed unlike DIY scripts and cron jobs
Vectorize
Agentage Memory