knowledge-graph
Knowledge Graphs vs. Vector Search for Agent Memory
Should your agent's memory be a vector store or a knowledge graph? They solve different halves of the problem. Here is where each one wins, where each breaks, and why agent memory needs both.
Inside retain(): What Actually Happens When Your Agent Remembers
Calling retain() is one line of code. Underneath, a sentence becomes extracted facts, resolved entities, a knowledge graph, and consolidated observations. Here is the whole write path.
Entity Resolution in Agent Memory: One Person, Many Names
How agent memory decides that Sarah, Sarah Chen, and she are one person, and why Hindsight resolves entities with a co-occurrence graph, not embeddings.
Pipecat Voice AI Persistent Memory: Add Memory to Your Voice Pipeline
Add persistent long-term memory to Pipecat voice AI pipelines. Recall relevant past conversations and retain new exchanges with a single FrameProcessor between your user aggregator and LLM service.
Pydantic AI Persistent Memory: Add It in 5 Lines of Code
Pydantic AI agents start from scratch on every run. hindsight-pydantic-ai adds long-term memory in five lines of Python.
How to Add Persistent Memory to OpenClaw with Hindsight
OpenClaw only remembers what the agent chooses to save. The Hindsight plugin saves every conversation and brings back the right context before each reply.