I'm on a deep dive fine-tuning how I organize and manage my personal knowledge base - focused on entity extraction and strategic information retrieval and based on the AgREE paper from Apple[0] and persisting it in Memgraph.
I've got a nice ingest, extract, enrich process going for the graph - I'm currently working on a fork of claude-mem[1] that uses the graph as a contextual backend for agentic coding workflows.
If you're like me you're doing it to establish a greater level of trust in generated code. It feels easier to draw out the hard guard-rails and have something fill out the middle -- giving both you, and the models, a reference point or contract as to what's "correct"
This is a great use case for sub-agents IMO. By default, sub-agents use sonnet. You can have opus orchestrate the various agents and get (close to) the best of both worlds.
We have tools today that are uniquely good at wading through disparate sources and aggregating things into a format that we can easily digest. The worry of course - is that these tools are generally on offer from huge tech giants (google, openai, etc). The good news is, we have open-source versions of these tools that perform almost as well as the closed-source versions for these types of categorization and aggregation.
I would agree that information is now more scattered (like bread for ducks as the author notes) than ever before -- but we now have the unprecedented ability to wrangle it ourselves.
- settings.json - set for machine, project
- env var - set for an environment/shell/sandbox
- slash command - set for a session
- magical keyword - set for a turn