I accidentally turned LLM memory into program analysis
- LLM: 9 events in the last 90 days
- Previous: earlier the same day · Show HN: Conduct, open-source guardrails for LLM and MCP tool calls
What happened
Why I stopped trying to give LLM agents a better memory and instead built Lemmalog, a Datalog engine that maintains an agent's knowledge as analysis state, with provenance, retractions and incremental evaluation, plus what happened when I benchmarked it on LongMemEval and LoCoMo.
Summary assembled by rule from the sources below