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
Basic: Free, then CHF 5 per role or per pack of 5,000 runs. Pro: CHF 190/month (or CHF 228/month billed yearly with 2 months free). Business: from CHF 490/month. Enterprise: on request. All plans include unlimited agents.
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
Compose skills, MCP servers and apps into agent plugins served from one central location
Version control with draft and published states for agent roles and skills
Role-based access control and permissions per plugin
Full activity audit logging attributed per user with exportable records
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
One central location eliminates duplicated skills across multiple AI interfaces
No model costs markup - agents use your own API keys and you pay providers directly
Vectorize
skilder