Hindsight API

Funktionen

• Temporal and semantic memory retrieval
• Entity graph for relationship tracking
• Configurable disposition traits for opinion formation
• Support for multiple LLM providers
• REST API, CLI, and MCP server interfaces

Anwendungsfälle

• Building persistent memory for long-running AI agents
• Enabling agents to reason about past events and user preferences
• Integrating memory capabilities into existing AI workflows via MCP
• Developing AI assistants that learn and adapt over time

Nicht-Ziele

• Acting as a general-purpose database
• Providing direct LLM inference capabilities
• Replacing the core agent execution logic

Workflow

1. Initialize memory engine
2. Create or select a memory bank
3. Store (retain) facts, events, or opinions
4. Recall memories based on queries
5. Reflect on memories to form new opinions or reason

Praktiken

• Data management
• AI memory architecture
• API design
• Security best practices

Voraussetzungen

• PostgreSQL (or embedded pg0)
• LLM API key and provider configuration
• Python 3.11+