What context graph and memory architecture is practical?
Context
The conference graph repeatedly asks how agents should retrieve, preserve, update, and reason over context without stuffing everything into a prompt.
Working Answer
This page is a first-pass research question, not a final recommendation. Use the linked evidence to refine the answer as more exact session recordings, transcripts, and reviewed slide readings become available.
Evidence
- agent memory — Topic synthesis
- agentic search — Topic synthesis
- autoresearch — Topic synthesis
- neo4j — Tool inventory
- zep — Tool inventory
- graphrag — Tool inventory
- 2026 06 29 louis fran ois bouchard context engineering in 2026 compaction memory and cost — Official schedule
- 2026 06 30 gil feig why your company needs a context graph and how to build it — Official schedule
- 2026 06 30 prukalpa sankar wtf is the context layer the missing infrastructure for production agents — Official schedule
- 2026 06 30 stefania druga memory harnesses for long running research agents — Official schedule
- youtube 4sX_He5c4sI — YouTube resource
- youtube 4sX_He5c4sI slides — Slide/OCR evidence
- youtube B9h9ovW5H9U slides — Slide/OCR evidence
Next Questions
- Extract specific claims from the linked source pages.
- Separate official schedule evidence from supporting YouTube, transcript, and OCR evidence.
- Convert stable answers into playbooks, harnesses, or evaluations where appropriate.