Skip to main content

Overview

Why Hindsight?

AI agents forget everything between sessions. Every conversation starts from zero—no context about who you are, what you've discussed, or what the assistant has learned. This isn't just an implementation detail; it fundamentally limits what AI Agents can do.

The problem is harder than it looks:

  • Simple vector search isn't enough — "What did Alice do last spring?" requires temporal reasoning, not just semantic similarity
  • Facts get disconnected — Knowing "Alice works at Google" and "Google is in Mountain View" should let you answer "Where does Alice work?" even if you never stored that directly
  • AI Agents needs to form opinions — A coding assistant that remembers "the user prefers functional programming" should weigh that when making recommendations
  • Context matters — The same information means different things to different memory banks with different personalities

Hindsight solves these problems with a memory system designed specifically for AI agents.

What Hindsight Does

Your AI agent stores information via retain(), searches with recall(), and reasons with reflect() — all interactions with its dedicated memory bank

Key Components

Three Memory Types

Hindsight separates memories by type for epistemic clarity:

TypeWhat it storesExample
WorldObjective facts received"Alice works at Google"
BankBank's own actions"I recommended Python to Bob"
OpinionFormed beliefs + confidence"Python is best for ML" (0.85)

Multi-Strategy Retrieval (TEMPR)

Four search strategies run in parallel:

StrategyBest for
SemanticConceptual similarity, paraphrasing
Keyword (BM25)Names, technical terms, exact matches
GraphRelated entities, indirect connections
Temporal"last spring", "in June", time ranges

Personality Framework (CARA)

Memory banks have Big Five personality traits that influence opinion formation:

TraitLowHigh
OpennessPrefers proven methodsEmbraces new ideas
ConscientiousnessFlexible, spontaneousSystematic, organized
ExtraversionIndependentCollaborative
AgreeablenessDirect, analyticalDiplomatic, harmonious
NeuroticismCalm, optimisticRisk-aware, cautious

The bias_strength parameter (0-1) controls how much personality influences opinions.

Next Steps

Getting Started

  • Quick Start — Install and get up and running in 60 seconds

Core Concepts

  • Retain — How memories are stored with multi-dimensional facts
  • Recall — How TEMPR's 4-way search retrieves memories
  • Reflect — How personality influences reasoning and opinion formation

API Methods

  • Retain — Store information in memory banks
  • Recall — Search and retrieve memories
  • Reflect — Reason with personality
  • Memory Banks — Configure personality and background
  • Entities — Track people, places, and concepts
  • Documents — Manage document sources
  • Operations — Monitor async tasks

Deployment