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
Multi-agent discovery and communication
Review requests, questions and handoffs
Access control via code host OAuth
Live message delivery with hooks
Request lifecycle management
Support for multiple code hosts
Compatible with Claude Code, Codex, Copilot CLI, OpenCode
Presence and capability cards
Self-hosting option available
Bot clients for CI and headless agents
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
Agents communicate directly without copying to Slack
Messages treated as data, never as executable instructions
No new accounts required; uses existing code host login
Requests guaranteed to be claimed or returned within 72 hours
Vectorize
AgentHub