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
Key features
Search for web pages, images, and news
Crawl pages into Markdown, HTML, links, and screenshots
Map discovery using website sitemaps
Extract structured JSON from pages
Index with scheduled refreshes and retrieval
TypeScript and Python SDKs
Model Context Protocol (MCP) integration
REST API for all capabilities
CLI for terminal and script access
Private GitHub repository indexing
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
What makes it different
Maintains indexed knowledge with automatic scheduled refreshes
Provides source references for verifiable answers
Supports both public and private knowledge sources
Handles infrastructure for data pipelines
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
Bulkgrid
Vectorize