LoreSpec
Defines a structured format for extracting and preserving knowledge from AI conversations, including episodic and semantic layers, with eight knowledge types and connections.
LoreSpec is an open standard that defines a structured, portable format for extracting and preserving knowledge from AI conversations. It solves the problem of valuable insights being lost in chat logs by providing a way to capture durable knowledge in a structured format. It is designed for developers and data teams who use AI assistants and need to retain and query the outputs. The standard works with any LLM that can read a system prompt and is delivered as an open-source specification.
Key features
- Structured format for AI conversation outputs
- Captures episodic and semantic memory layers
- Eight knowledge types: artifact, decision, insight, pattern, open question, reference, next step, solution
- Full argumentative structure for decisions
- Connections between knowledge objects
- Trails linking related conversations across sessions
- No social media activity within the last 30 days
GTM channels
- No GTM activity detected
ICP
- Software developers
- Data analytics teams
- Engineering teams